modelId
stringlengths 5
139
| author
stringlengths 2
42
| last_modified
timestamp[us, tz=UTC]date 2020-02-15 11:33:14
2025-09-05 00:41:53
| downloads
int64 0
223M
| likes
int64 0
11.7k
| library_name
stringclasses 539
values | tags
listlengths 1
4.05k
| pipeline_tag
stringclasses 55
values | createdAt
timestamp[us, tz=UTC]date 2022-03-02 23:29:04
2025-09-05 00:41:31
| card
stringlengths 11
1.01M
|
|---|---|---|---|---|---|---|---|---|---|
often/removebg
|
often
| 2023-10-15T08:36:04Z | 0 | 1 |
transformers
|
[
"transformers",
"PyTorch",
"image-to-image",
"arxiv:1910.09700",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
image-to-image
| 2023-10-12T09:41:30Z |
---
license: apache-2.0
pipeline_tag: image-to-image
tags:
- PyTorch
library_name: transformers
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
This modelcard aims to be a base template for new models. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/modelcard_template.md?plain=1).
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
ahhany/constructionEmbeddingModel
|
ahhany
| 2023-10-15T08:23:50Z | 1 | 0 |
sentence-transformers
|
[
"sentence-transformers",
"pytorch",
"bert",
"feature-extraction",
"sentence-similarity",
"transformers",
"autotrain_compatible",
"text-embeddings-inference",
"endpoints_compatible",
"region:us"
] |
sentence-similarity
| 2023-10-08T09:12:41Z |
---
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- transformers
---
# {MODEL_NAME}
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 384 dimensional dense vector space and can be used for tasks like clustering or semantic search.
<!--- Describe your model here -->
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('{MODEL_NAME}')
embeddings = model.encode(sentences)
print(embeddings)
```
## Usage (HuggingFace Transformers)
Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
```python
from transformers import AutoTokenizer, AutoModel
import torch
#Mean Pooling - Take attention mask into account for correct averaging
def mean_pooling(model_output, attention_mask):
token_embeddings = model_output[0] #First element of model_output contains all token embeddings
input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
# Sentences we want sentence embeddings for
sentences = ['This is an example sentence', 'Each sentence is converted']
# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('{MODEL_NAME}')
model = AutoModel.from_pretrained('{MODEL_NAME}')
# Tokenize sentences
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
# Compute token embeddings
with torch.no_grad():
model_output = model(**encoded_input)
# Perform pooling. In this case, mean pooling.
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
print("Sentence embeddings:")
print(sentence_embeddings)
```
## Evaluation Results
<!--- Describe how your model was evaluated -->
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name={MODEL_NAME})
## Training
The model was trained with the parameters:
**DataLoader**:
`torch.utils.data.dataloader.DataLoader` of length 125 with parameters:
```
{'batch_size': 16, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
```
**Loss**:
`sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss` with parameters:
```
{'scale': 20.0, 'similarity_fct': 'cos_sim'}
```
Parameters of the fit()-Method:
```
{
"epochs": 1,
"evaluation_steps": 0,
"evaluator": "NoneType",
"max_grad_norm": 1,
"optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
"optimizer_params": {
"lr": 2e-05
},
"scheduler": "WarmupLinear",
"steps_per_epoch": null,
"warmup_steps": 12,
"weight_decay": 0.01
}
```
## Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 256, 'do_lower_case': False}) with Transformer model: BertModel
(1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
)
```
## Citing & Authors
<!--- Describe where people can find more information -->
|
alphahg/CodeLlama-13b-hf-rust-finetune-full
|
alphahg
| 2023-10-15T08:16:40Z | 9 | 1 |
transformers
|
[
"transformers",
"pytorch",
"llama",
"text-generation",
"generated_from_trainer",
"base_model:codellama/CodeLlama-13b-hf",
"base_model:finetune:codellama/CodeLlama-13b-hf",
"license:llama2",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-10-15T08:01:47Z |
---
license: llama2
base_model: codellama/CodeLlama-13b-hf
tags:
- generated_from_trainer
model-index:
- name: CodeLlama-13b-hf-rust-finetune
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# CodeLlama-13b-hf-rust-finetune
This model is a fine-tuned version of [codellama/CodeLlama-13b-hf](https://huggingface.co/codellama/CodeLlama-13b-hf) on an [ammarnasr/the-stack-rust-clean](https://huggingface.co/datasets/ammarnasr/the-stack-rust-clean) dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4809
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2.5e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1
- training_steps: 500
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 0.4848 | 0.02 | 500 | 0.4809 |
### Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
|
alphahg/CodeLlama-13b-hf-rust-finetune
|
alphahg
| 2023-10-15T08:16:01Z | 0 | 0 | null |
[
"generated_from_trainer",
"base_model:codellama/CodeLlama-13b-hf",
"base_model:finetune:codellama/CodeLlama-13b-hf",
"license:llama2",
"region:us"
] | null | 2023-10-15T07:55:59Z |
---
license: llama2
base_model: codellama/CodeLlama-13b-hf
tags:
- generated_from_trainer
model-index:
- name: CodeLlama-13b-hf-rust-finetune
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# CodeLlama-13b-hf-rust-finetune
This model is a fine-tuned version of [codellama/CodeLlama-13b-hf](https://huggingface.co/codellama/CodeLlama-13b-hf) on an [ammarnasr/the-stack-rust-clean](https://huggingface.co/datasets/ammarnasr/the-stack-rust-clean) dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4809
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2.5e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1
- training_steps: 500
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 0.4848 | 0.02 | 500 | 0.4809 |
### Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
|
Jin123012/wgefef
|
Jin123012
| 2023-10-15T08:08:19Z | 0 | 0 | null |
[
"license:bigscience-openrail-m",
"region:us"
] | null | 2023-10-15T08:08:19Z |
---
license: bigscience-openrail-m
---
|
satpalsr/the-beginning
|
satpalsr
| 2023-10-15T08:07:18Z | 5 | 0 |
transformers
|
[
"transformers",
"pytorch",
"deberta-v2",
"text-classification",
"generated_from_trainer",
"base_model:microsoft/deberta-v3-base",
"base_model:finetune:microsoft/deberta-v3-base",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-10-15T08:06:47Z |
---
license: mit
base_model: microsoft/deberta-v3-base
tags:
- generated_from_trainer
model-index:
- name: reward-model-out
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# reward-model-out
This model is a fine-tuned version of [microsoft/deberta-v3-base](https://huggingface.co/microsoft/deberta-v3-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- eval_loss: 0.6737
- eval_accuracy: 0.6041
- eval_precision: 0.6041
- eval_recall: 1.0
- eval_f1: 0.7532
- eval_runtime: 23.9877
- eval_samples_per_second: 32.85
- eval_steps_per_second: 5.503
- epoch: 0.35
- step: 4500
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 6
- eval_batch_size: 6
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Framework versions
- Transformers 4.35.0.dev0
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.14.1
|
aiknight87/mistralai-7b-new2
|
aiknight87
| 2023-10-15T08:06:26Z | 12 | 0 |
peft
|
[
"peft",
"mistral",
"arxiv:1910.09700",
"base_model:mistralai/Mistral-7B-v0.1",
"base_model:adapter:mistralai/Mistral-7B-v0.1",
"4-bit",
"bitsandbytes",
"region:us"
] | null | 2023-10-15T05:57:26Z |
---
library_name: peft
base_model: mistralai/Mistral-7B-v0.1
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Data Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: bfloat16
### Framework versions
- PEFT 0.6.0.dev0
|
pipizhao/Pandalyst-7B-V1.2
|
pipizhao
| 2023-10-15T08:06:14Z | 20 | 7 |
transformers
|
[
"transformers",
"pytorch",
"llama",
"text-generation",
"code",
"en",
"license:llama2",
"model-index",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-10-14T07:16:05Z |
---
license: llama2
library_name: transformers
tags:
- code
model-index:
- name: Pandalyst-7B-V1.2
results:
- task:
type: text-generation
metrics:
- name: acc@1
type: acc@1
value: 0.0
verified: false
language:
- en
---
## Pandalyst: A large language model for mastering data analysis using pandas
<p align="center">
<img src="https://raw.githubusercontent.com/pipizhaoa/Pandalyst/master/imgs/pandalyst.png" width="300"/>
</p>
<p align="center">
🐱 <a href="https://github.com/pipizhaoa/Pandalyst" target="_blank">Github Repo</a> <br>
</p>
**What is Pandalyst**
- Pandalyst is a general large language model specifically trained to process and analyze data using the pandas library.
**How is Pandalyst**
- Pandalyst has strong generalization capabilities for data tables in different fields and different data analysis needs.
**Why is Pandalyst**
- Pandalyst is open source and free to use, and its small parameter size (7B/13B) allows us to easily deploy it on local PC.
- Pandalyst can handle complex data tables (multiple columns and multiple rows), allowing us to enter enough context to describe our table in detail.
- Pandalyst has very competitive performance, significantly outperforming models of the same size and even outperforming some of the strongest closed-source models.
## News
- 🔥[2023/10/15] Now we can **plot** 📈! and much more powerful! We released **Pandalyst-7B-V1.2**, which was trained on **CodeLlama-7b-Python** and it surpasses **ChatGPT-3.5 (2023/06/13)**, **Pandalyst-7B-V1.1** and **WizardCoder-Python-13B-V1.0** in our **PandaTest_V1.0**.
- 🤖️[2023/09/30] We released **Pandalyst-7B-V1.1** , which was trained on **CodeLlama-7b-Python** and achieves the **76.1 exec@1** in our **PandaTest_V1.0** and surpasses **WizardCoder-Python-13B-V1.0** and **ChatGPT-3.5 (2023/06/13)**.
| Model | Checkpoint | Support plot | License |
|---------------------|--------------------------------------------------------------------------------------------|--------------| ----- |
| 🔥Pandalyst-7B-V1.2 | 🤗 <a href="https://huggingface.co/pipizhao/Pandalyst-7B-V1.2" target="_blank">HF Link</a> | ✅ | <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama2</a> |
| Pandalyst-7B-V1.1 | 🤗 <a href="https://huggingface.co/pipizhao/Pandalyst-7B-V1.1" target="_blank">HF Link</a> | ❌ | <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama2</a> |
## Usage and Human evaluation
Please refer to <a href="https://github.com/pipizhaoa/Pandalyst" target="_blank">Github</a>.
|
pipizhao/Pandalyst-7B-V1.1
|
pipizhao
| 2023-10-15T08:05:59Z | 18 | 13 |
transformers
|
[
"transformers",
"pytorch",
"llama",
"text-generation",
"code",
"en",
"license:llama2",
"model-index",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-09-30T03:09:54Z |
---
license: llama2
library_name: transformers
tags:
- code
model-index:
- name: Pandalyst-7B-V1.1
results:
- task:
type: text-generation
metrics:
- name: acc@1
type: acc@1
value: 0.0
verified: false
language:
- en
---
## Pandalyst: A large language model for mastering data analysis using pandas
<p align="center">
<img src="https://raw.githubusercontent.com/pipizhaoa/Pandalyst/master/imgs/pandalyst.png" width="300"/>
</p>
<p align="center">
🐱 <a href="https://github.com/pipizhaoa/Pandalyst" target="_blank">Github Repo</a> <br>
</p>
**What is Pandalyst**
- Pandalyst is a general large language model specifically trained to process and analyze data using the pandas library.
**How is Pandalyst**
- Pandalyst has strong generalization capabilities for data tables in different fields and different data analysis needs.
**Why is Pandalyst**
- Pandalyst is open source and free to use, and its small parameter size (7B/13B) allows us to easily deploy it on local PC.
- Pandalyst can handle complex data tables (multiple columns and multiple rows), allowing us to enter enough context to describe our table in detail.
- Pandalyst has very competitive performance, significantly outperforming models of the same size and even outperforming some of the strongest closed-source models.
## News
- 🔥[2023/10/15] Now we can **plot** 📈! and much more powerful! We released **Pandalyst-7B-V1.2**, which was trained on **CodeLlama-7b-Python** and it surpasses **ChatGPT-3.5 (2023/06/13)**, **Pandalyst-7B-V1.1** and **WizardCoder-Python-13B-V1.0** in our **PandaTest_V1.0**.
- 🤖️[2023/09/30] We released **Pandalyst-7B-V1.1** , which was trained on **CodeLlama-7b-Python** and achieves the **76.1 exec@1** in our **PandaTest_V1.0** and surpasses **WizardCoder-Python-13B-V1.0** and **ChatGPT-3.5 (2023/06/13)**.
| Model | Checkpoint | Support plot | License |
|---------------------|--------------------------------------------------------------------------------------------|--------------| ----- |
| 🔥Pandalyst-7B-V1.2 | 🤗 <a href="https://huggingface.co/pipizhao/Pandalyst-7B-V1.2" target="_blank">HF Link</a> | ✅ | <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama2</a> |
| Pandalyst-7B-V1.1 | 🤗 <a href="https://huggingface.co/pipizhao/Pandalyst-7B-V1.1" target="_blank">HF Link</a> | ❌ | <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama2</a> |
## Usage and Human evaluation
Please refer to <a href="https://github.com/pipizhaoa/Pandalyst" target="_blank">Github</a>.
|
alvion427/PerroPastorModels
|
alvion427
| 2023-10-15T08:02:42Z | 2 | 0 | null |
[
"gguf",
"endpoints_compatible",
"region:us"
] | null | 2023-10-14T19:35:22Z |
These are quantizations of models that work well with (https://github.com/alvion427/PerroPastor).
|
aurekero/Taxi-v3
|
aurekero
| 2023-10-15T07:59:11Z | 0 | 0 | null |
[
"Taxi-v3",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-10-15T07:55:20Z |
---
tags:
- Taxi-v3
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: Taxi-v3
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Taxi-v3
type: Taxi-v3
metrics:
- type: mean_reward
value: 7.56 +/- 2.71
name: mean_reward
verified: false
---
# **Q-Learning** Agent playing1 **Taxi-v3**
This is a trained model of a **Q-Learning** agent playing **Taxi-v3** .
## Usage
```python
model = load_from_hub(repo_id="aurekero/Taxi-v3", filename="q-learning.pkl")
# Don't forget to check if you need to add additional attributes (is_slippery=False etc)
env = gym.make(model["env_id"])
```
|
Pampkinus/Andrej-Babis
|
Pampkinus
| 2023-10-15T07:15:31Z | 0 | 0 | null |
[
"license:openrail",
"region:us"
] | null | 2023-10-14T16:37:25Z |
---
license: openrail
---
RVC2 model of the czech politician Andrej Babiš, 500 epochs, dataset = 15min of his speaches
https://cs.wikipedia.org/wiki/Andrej_Babi%C5%A1
|
Yntec/DreamWorld
|
Yntec
| 2023-10-15T07:11:12Z | 264 | 2 |
diffusers
|
[
"diffusers",
"safetensors",
"Anime",
"Disney",
"Pixar",
"DucHaiten",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] |
text-to-image
| 2023-10-15T05:20:19Z |
---
license: creativeml-openrail-m
library_name: diffusers
pipeline_tag: text-to-image
tags:
- Anime
- Disney
- Pixar
- DucHaiten
- stable-diffusion
- stable-diffusion-diffusers
- diffusers
- text-to-image
---
# DucHaitenDreamWorld v1.3
No-ema version of this model.
If you like this content, support DucHaiten at: https://linktr.ee/Duc_Haiten
Sample and prompts:
textured EYES, Portrait of Pretty CUTE LITTLE Girl dressed of coke clothes countryside country style country house fantasy character portrait, 1949, cinematic lighting. hayao miyazaki on canvas By design key visual and rossdraws and ross tran
Original page: https://civitai.com/models/7039?modelVersionId=8275
|
nuttachot/bert-finetuned-mrpc
|
nuttachot
| 2023-10-15T07:10:41Z | 4 | 0 |
transformers
|
[
"transformers",
"tf",
"bert",
"text-classification",
"generated_from_keras_callback",
"base_model:google-bert/bert-base-uncased",
"base_model:finetune:google-bert/bert-base-uncased",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-10-15T04:14:13Z |
---
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_keras_callback
model-index:
- name: bert-finetuned-mrpc
results: []
---
<!-- This model card has been generated automatically according to the information Keras had access to. You should
probably proofread and complete it, then remove this comment. -->
# bert-finetuned-mrpc
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5e-05, 'decay_steps': 1377, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
- training_precision: float32
### Training results
### Framework versions
- Transformers 4.34.0
- TensorFlow 2.13.0
- Datasets 2.14.5
- Tokenizers 0.14.1
|
Avinash64/ppo-LunarLander-v2
|
Avinash64
| 2023-10-15T07:10:23Z | 0 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-10-15T07:10:02Z |
---
library_name: stable-baselines3
tags:
- LunarLander-v2
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: PPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: LunarLander-v2
type: LunarLander-v2
metrics:
- type: mean_reward
value: 258.83 +/- 18.58
name: mean_reward
verified: false
---
# **PPO** Agent playing **LunarLander-v2**
This is a trained model of a **PPO** agent playing **LunarLander-v2**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
## Usage (with Stable-baselines3)
TODO: Add your code
```python
from stable_baselines3 import ...
from huggingface_sb3 import load_from_hub
...
```
|
randomshit11/fin-bert-1st-shit
|
randomshit11
| 2023-10-15T07:05:45Z | 12 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tf",
"pegasus",
"text2text-generation",
"Summarization",
"summarization",
"en",
"dataset:xsum",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
summarization
| 2023-10-13T14:07:07Z |
---
language:
- en
metrics:
- rouge
tags:
- Summarization
datasets:
- xsum
pipeline_tag: summarization
---
|
Moriacrafter/1lama2-qlora-finetunined-french
|
Moriacrafter
| 2023-10-15T07:03:16Z | 1 | 0 |
peft
|
[
"peft",
"arxiv:1910.09700",
"base_model:TinyPixel/Llama-2-7B-bf16-sharded",
"base_model:adapter:TinyPixel/Llama-2-7B-bf16-sharded",
"region:us"
] | null | 2023-10-15T07:03:09Z |
---
library_name: peft
base_model: TinyPixel/Llama-2-7B-bf16-sharded
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Data Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float16
### Framework versions
- PEFT 0.6.0.dev0
|
mor40/BulBERT-ner-bsnlp
|
mor40
| 2023-10-15T06:48:44Z | 5 | 0 |
transformers
|
[
"transformers",
"pytorch",
"bert",
"token-classification",
"generated_from_trainer",
"base_model:mor40/BulBERT-ner-bsnlp",
"base_model:finetune:mor40/BulBERT-ner-bsnlp",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
token-classification
| 2023-09-23T19:10:28Z |
---
base_model: mor40/BulBERT-ner-bsnlp
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: BulBERT-ner-bsnlp
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# BulBERT-ner-bsnlp
This model is a fine-tuned version of [mor40/BulBERT-ner-bsnlp](https://huggingface.co/mor40/BulBERT-ner-bsnlp) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1443
- Precision: 0.7728
- Recall: 0.8862
- F1: 0.8257
- Accuracy: 0.9726
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
### Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| No log | 1.0 | 91 | 0.1395 | 0.7736 | 0.8690 | 0.8185 | 0.9717 |
| No log | 2.0 | 182 | 0.1386 | 0.7466 | 0.8849 | 0.8099 | 0.9705 |
| No log | 3.0 | 273 | 0.1408 | 0.7695 | 0.8782 | 0.8203 | 0.9726 |
| No log | 4.0 | 364 | 0.1426 | 0.7680 | 0.8851 | 0.8224 | 0.9721 |
| No log | 5.0 | 455 | 0.1443 | 0.7728 | 0.8862 | 0.8257 | 0.9726 |
### Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
|
thomasdavidwang/out
|
thomasdavidwang
| 2023-10-15T06:44:50Z | 1 | 0 |
diffusers
|
[
"diffusers",
"tensorboard",
"safetensors",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"dreambooth",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] |
text-to-image
| 2023-10-15T00:55:00Z |
---
license: creativeml-openrail-m
base_model: ./out
instance_prompt: a photo of ksk man
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- dreambooth
inference: true
---
# DreamBooth - thomasdavidwang/out
This is a dreambooth model derived from ./out. The weights were trained on a photo of ksk man using [DreamBooth](https://dreambooth.github.io/).
You can find some example images in the following.
DreamBooth for the text encoder was enabled: True.
|
FredNajjar/bigbird-QA-squad_v2.3
|
FredNajjar
| 2023-10-15T06:31:34Z | 6 | 0 |
transformers
|
[
"transformers",
"pytorch",
"big_bird",
"question-answering",
"generated_from_trainer",
"dataset:squad_v2",
"base_model:google/bigbird-roberta-base",
"base_model:finetune:google/bigbird-roberta-base",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
question-answering
| 2023-10-15T04:59:31Z |
---
license: apache-2.0
base_model: google/bigbird-roberta-base
tags:
- generated_from_trainer
datasets:
- squad_v2
model-index:
- name: bigbird-QA-squad_v2.3
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# bigbird-QA-squad_v2.3
This model is a fine-tuned version of [google/bigbird-roberta-base](https://huggingface.co/google/bigbird-roberta-base) on the squad_v2 dataset.
It achieves the following results on the evaluation set:
- Loss: 1.3324
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 32
- total_train_batch_size: 512
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 121
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 1.7892 | 1.0 | 203 | 1.6201 |
| 1.4879 | 2.0 | 407 | 1.3778 |
| 1.3885 | 2.99 | 609 | 1.3324 |
### Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
|
haesun/xlm-roberta-base-finetuned-panx-all
|
haesun
| 2023-10-15T06:29:09Z | 5 | 0 |
transformers
|
[
"transformers",
"pytorch",
"xlm-roberta",
"token-classification",
"generated_from_trainer",
"base_model:FacebookAI/xlm-roberta-base",
"base_model:finetune:FacebookAI/xlm-roberta-base",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
token-classification
| 2022-07-04T16:25:36Z |
---
license: mit
base_model: xlm-roberta-base
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: xlm-roberta-base-finetuned-panx-all
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# xlm-roberta-base-finetuned-panx-all
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1770
- F1: 0.8519
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 24
- eval_batch_size: 24
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 0.3034 | 1.0 | 835 | 0.1916 | 0.8183 |
| 0.1582 | 2.0 | 1670 | 0.1714 | 0.8405 |
| 0.1028 | 3.0 | 2505 | 0.1770 | 0.8519 |
### Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
|
Supersaiyan1729/mistrail_9_epichs_dolly
|
Supersaiyan1729
| 2023-10-15T06:19:13Z | 12 | 0 |
peft
|
[
"peft",
"arxiv:1910.09700",
"base_model:mistralai/Mistral-7B-v0.1",
"base_model:adapter:mistralai/Mistral-7B-v0.1",
"region:us"
] | null | 2023-10-15T06:19:07Z |
---
library_name: peft
base_model: mistralai/Mistral-7B-v0.1
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Data Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
## Training procedure
### Framework versions
- PEFT 0.6.0.dev0
|
haesun/xlm-roberta-base-finetuned-panx-fr
|
haesun
| 2023-10-15T06:16:44Z | 5 | 0 |
transformers
|
[
"transformers",
"pytorch",
"xlm-roberta",
"token-classification",
"generated_from_trainer",
"dataset:xtreme",
"base_model:FacebookAI/xlm-roberta-base",
"base_model:finetune:FacebookAI/xlm-roberta-base",
"license:mit",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
token-classification
| 2022-07-04T02:57:33Z |
---
license: mit
base_model: xlm-roberta-base
tags:
- generated_from_trainer
datasets:
- xtreme
metrics:
- f1
model-index:
- name: xlm-roberta-base-finetuned-panx-fr
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: xtreme
type: xtreme
config: PAN-X.fr
split: validation
args: PAN-X.fr
metrics:
- name: F1
type: f1
value: 0.8418401611820013
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# xlm-roberta-base-finetuned-panx-fr
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the xtreme dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2747
- F1: 0.8418
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 24
- eval_batch_size: 24
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 0.566 | 1.0 | 191 | 0.3098 | 0.7784 |
| 0.2515 | 2.0 | 382 | 0.2832 | 0.8253 |
| 0.1732 | 3.0 | 573 | 0.2747 | 0.8418 |
### Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
|
haesun/xlm-roberta-base-finetuned-panx-de-fr
|
haesun
| 2023-10-15T06:13:44Z | 4 | 0 |
transformers
|
[
"transformers",
"pytorch",
"xlm-roberta",
"token-classification",
"generated_from_trainer",
"base_model:FacebookAI/xlm-roberta-base",
"base_model:finetune:FacebookAI/xlm-roberta-base",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
token-classification
| 2022-07-04T02:31:15Z |
---
license: mit
base_model: xlm-roberta-base
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: xlm-roberta-base-finetuned-panx-de-fr
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# xlm-roberta-base-finetuned-panx-de-fr
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1636
- F1: 0.8559
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 24
- eval_batch_size: 24
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 0.2904 | 1.0 | 715 | 0.1834 | 0.8188 |
| 0.147 | 2.0 | 1430 | 0.1622 | 0.8489 |
| 0.0938 | 3.0 | 2145 | 0.1636 | 0.8559 |
### Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
|
JOSALPHO/my_awesome_billsum_model
|
JOSALPHO
| 2023-10-15T06:08:39Z | 3 | 0 |
transformers
|
[
"transformers",
"pytorch",
"t5",
"text2text-generation",
"generated_from_trainer",
"dataset:arxiv-summarization",
"base_model:google-t5/t5-small",
"base_model:finetune:google-t5/t5-small",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text2text-generation
| 2023-10-14T16:51:35Z |
---
license: apache-2.0
base_model: t5-small
tags:
- generated_from_trainer
datasets:
- arxiv-summarization
metrics:
- rouge
model-index:
- name: my_awesome_billsum_model
results:
- task:
name: Sequence-to-sequence Language Modeling
type: text2text-generation
dataset:
name: arxiv-summarization
type: arxiv-summarization
config: section
split: test
args: section
metrics:
- name: Rouge1
type: rouge
value: 0.1446
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# my_awesome_billsum_model
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the arxiv-summarization dataset.
It achieves the following results on the evaluation set:
- Loss: 2.8844
- Rouge1: 0.1446
- Rouge2: 0.0426
- Rougel: 0.1172
- Rougelsum: 0.117
- Gen Len: 19.0
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
| No log | 1.0 | 63 | 3.0098 | 0.1319 | 0.0348 | 0.105 | 0.1049 | 19.0 |
| No log | 2.0 | 126 | 2.9186 | 0.1383 | 0.0393 | 0.1121 | 0.1119 | 19.0 |
| No log | 3.0 | 189 | 2.8920 | 0.1441 | 0.0424 | 0.1166 | 0.1165 | 19.0 |
| No log | 4.0 | 252 | 2.8844 | 0.1446 | 0.0426 | 0.1172 | 0.117 | 19.0 |
### Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1+cpu
- Datasets 2.14.5
- Tokenizers 0.13.3
|
salohiddin94/ppo-PyramidsTraining
|
salohiddin94
| 2023-10-15T06:06:28Z | 1 | 0 |
ml-agents
|
[
"ml-agents",
"tensorboard",
"onnx",
"Pyramids",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-Pyramids",
"region:us"
] |
reinforcement-learning
| 2023-10-15T06:06:26Z |
---
library_name: ml-agents
tags:
- Pyramids
- deep-reinforcement-learning
- reinforcement-learning
- ML-Agents-Pyramids
---
# **ppo** Agent playing **Pyramids**
This is a trained model of a **ppo** agent playing **Pyramids**
using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
## Usage (with ML-Agents)
The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
- A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
- A *longer tutorial* to understand how works ML-Agents:
https://huggingface.co/learn/deep-rl-course/unit5/introduction
### Resume the training
```bash
mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
```
### Watch your Agent play
You can watch your agent **playing directly in your browser**
1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
2. Step 1: Find your model_id: salohiddin94/ppo-PyramidsTraining
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
haesun/xlm-roberta-base-finetuned-panx-de
|
haesun
| 2023-10-15T06:00:49Z | 4 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"xlm-roberta",
"token-classification",
"generated_from_trainer",
"dataset:xtreme",
"base_model:FacebookAI/xlm-roberta-base",
"base_model:finetune:FacebookAI/xlm-roberta-base",
"license:mit",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
token-classification
| 2022-06-30T14:17:31Z |
---
license: mit
base_model: xlm-roberta-base
tags:
- generated_from_trainer
datasets:
- xtreme
metrics:
- f1
model-index:
- name: xlm-roberta-base-finetuned-panx-de
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: xtreme
type: xtreme
config: PAN-X.de
split: validation
args: PAN-X.de
metrics:
- name: F1
type: f1
value: 0.8657241810026685
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# xlm-roberta-base-finetuned-panx-de
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the xtreme dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1338
- F1: 0.8657
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 24
- eval_batch_size: 24
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 0.257 | 1.0 | 525 | 0.1557 | 0.8218 |
| 0.126 | 2.0 | 1050 | 0.1460 | 0.8521 |
| 0.0827 | 3.0 | 1575 | 0.1338 | 0.8657 |
### Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
|
yesj1234/xlsr_mid1_ja-ko
|
yesj1234
| 2023-10-15T05:59:59Z | 3 | 0 |
transformers
|
[
"transformers",
"pytorch",
"wav2vec2",
"automatic-speech-recognition",
"./sample_speech.py",
"generated_from_trainer",
"base_model:facebook/wav2vec2-large-xlsr-53",
"base_model:finetune:facebook/wav2vec2-large-xlsr-53",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
automatic-speech-recognition
| 2023-10-15T05:55:46Z |
---
license: apache-2.0
base_model: facebook/wav2vec2-large-xlsr-53
tags:
- automatic-speech-recognition
- ./sample_speech.py
- generated_from_trainer
model-index:
- name: ja-xlsr
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# ja-xlsr
This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the ./SAMPLE_SPEECH.PY - NA dataset.
It achieves the following results on the evaluation set:
- Loss: 2.5952
- Cer: 0.3240
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0003
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- total_train_batch_size: 16
- total_eval_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 50
- num_epochs: 300
### Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|:-------------:|:------:|:----:|:---------------:|:------:|
| 4.9138 | 6.52 | 150 | 4.7965 | 1.0 |
| 4.7484 | 13.04 | 300 | 4.6081 | 1.0 |
| 4.5894 | 19.57 | 450 | 4.4697 | 0.9851 |
| 4.2024 | 26.09 | 600 | 4.0373 | 0.9077 |
| 2.7314 | 32.61 | 750 | 2.5507 | 0.5341 |
| 1.2293 | 39.13 | 900 | 2.0146 | 0.4139 |
| 0.5544 | 45.65 | 1050 | 1.9821 | 0.3556 |
| 0.3224 | 52.17 | 1200 | 2.0190 | 0.3587 |
| 0.1951 | 58.7 | 1350 | 2.1229 | 0.3612 |
| 0.1539 | 65.22 | 1500 | 2.1114 | 0.3470 |
| 0.1165 | 71.74 | 1650 | 2.2748 | 0.3315 |
| 0.1119 | 78.26 | 1800 | 2.2391 | 0.3488 |
| 0.0989 | 84.78 | 1950 | 2.3438 | 0.3383 |
| 0.0915 | 91.3 | 2100 | 2.1218 | 0.3587 |
| 0.0721 | 97.83 | 2250 | 2.2428 | 0.3519 |
| 0.0742 | 104.35 | 2400 | 2.2293 | 0.3364 |
| 0.0629 | 110.87 | 2550 | 2.2878 | 0.3371 |
| 0.0495 | 117.39 | 2700 | 2.2672 | 0.3408 |
| 0.0466 | 123.91 | 2850 | 2.2532 | 0.3525 |
| 0.0424 | 130.43 | 3000 | 2.2844 | 0.3259 |
| 0.0446 | 136.96 | 3150 | 2.2763 | 0.3253 |
| 0.0411 | 143.48 | 3300 | 2.3011 | 0.3302 |
| 0.0419 | 150.0 | 3450 | 2.3201 | 0.3420 |
| 0.0333 | 156.52 | 3600 | 2.3644 | 0.3439 |
| 0.0384 | 163.04 | 3750 | 2.3685 | 0.3532 |
| 0.0367 | 169.57 | 3900 | 2.3970 | 0.3470 |
| 0.0307 | 176.09 | 4050 | 2.3530 | 0.3309 |
| 0.0328 | 182.61 | 4200 | 2.3415 | 0.3315 |
| 0.0271 | 189.13 | 4350 | 2.4165 | 0.3309 |
| 0.0213 | 195.65 | 4500 | 2.4478 | 0.3451 |
| 0.0193 | 202.17 | 4650 | 2.5241 | 0.3556 |
| 0.0204 | 208.7 | 4800 | 2.5700 | 0.3463 |
| 0.0185 | 215.22 | 4950 | 2.5837 | 0.3178 |
| 0.0161 | 221.74 | 5100 | 2.5139 | 0.3377 |
| 0.0167 | 228.26 | 5250 | 2.5288 | 0.3352 |
| 0.0148 | 234.78 | 5400 | 2.5741 | 0.3389 |
| 0.0141 | 241.3 | 5550 | 2.5174 | 0.3389 |
| 0.0122 | 247.83 | 5700 | 2.5573 | 0.3352 |
| 0.0115 | 254.35 | 5850 | 2.5790 | 0.3296 |
| 0.0141 | 260.87 | 6000 | 2.5774 | 0.3203 |
| 0.0123 | 267.39 | 6150 | 2.6147 | 0.3309 |
| 0.0214 | 273.91 | 6300 | 2.6202 | 0.3302 |
| 0.0107 | 280.43 | 6450 | 2.6264 | 0.3234 |
| 0.0086 | 286.96 | 6600 | 2.6075 | 0.3216 |
| 0.0106 | 293.48 | 6750 | 2.5960 | 0.3247 |
| 0.0085 | 300.0 | 6900 | 2.5952 | 0.3240 |
### Framework versions
- Transformers 4.34.0
- Pytorch 2.1.0+cu121
- Datasets 2.14.5
- Tokenizers 0.14.1
|
Alex2575/aleksis_heb_tiny
|
Alex2575
| 2023-10-15T05:40:06Z | 5 | 0 |
transformers
|
[
"transformers",
"pytorch",
"whisper",
"automatic-speech-recognition",
"generated_from_trainer",
"he",
"dataset:Alex2575/heb_anna",
"base_model:openai/whisper-tiny",
"base_model:finetune:openai/whisper-tiny",
"license:apache-2.0",
"model-index",
"endpoints_compatible",
"region:us"
] |
automatic-speech-recognition
| 2023-10-12T15:11:03Z |
---
language:
- he
license: apache-2.0
base_model: openai/whisper-tiny
tags:
- generated_from_trainer
datasets:
- Alex2575/heb_anna
metrics:
- wer
model-index:
- name: aleksis_heb_tiny
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: heb_anna
type: Alex2575/heb_anna
metrics:
- name: Wer
type: wer
value: 8.471596527854082
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# aleksis_heb_tiny
This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the heb_anna dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0918
- Wer Ortho: 8.4716
- Wer: 8.4716
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 1
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant_with_warmup
- lr_scheduler_warmup_steps: 50
- training_steps: 500
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|
| 0.123 | 4.24 | 500 | 0.0918 | 8.4716 | 8.4716 |
### Framework versions
- Transformers 4.35.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
|
Mahmoud7/output_dir
|
Mahmoud7
| 2023-10-15T05:33:58Z | 8 | 0 |
diffusers
|
[
"diffusers",
"tensorboard",
"safetensors",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"textual_inversion",
"base_model:runwayml/stable-diffusion-v1-5",
"base_model:adapter:runwayml/stable-diffusion-v1-5",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] |
text-to-image
| 2023-10-15T02:45:24Z |
---
license: creativeml-openrail-m
base_model: runwayml/stable-diffusion-v1-5
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- textual_inversion
inference: true
---
# Textual inversion text2image fine-tuning - Mahmoud7/output_dir
These are textual inversion adaption weights for runwayml/stable-diffusion-v1-5. You can find some example images in the following.
|
joshhu1123/Llama-2-7b-chat-hf-Qlora-BI55-BImedqa-no6
|
joshhu1123
| 2023-10-15T05:33:36Z | 0 | 0 |
peft
|
[
"peft",
"arxiv:1910.09700",
"base_model:joshhu1123/Llama-2-7b-chat-hf-Qlora-BI55",
"base_model:adapter:joshhu1123/Llama-2-7b-chat-hf-Qlora-BI55",
"region:us"
] | null | 2023-10-15T05:33:29Z |
---
library_name: peft
base_model: joshhu1123/Llama-2-7b-chat-hf-Qlora-BI55
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: bfloat16
### Framework versions
- PEFT 0.6.0.dev0
|
abhijeet06793/mistral-finetuned-samsum
|
abhijeet06793
| 2023-10-15T05:32:17Z | 0 | 0 | null |
[
"generated_from_trainer",
"base_model:TheBloke/Mistral-7B-Instruct-v0.1-GPTQ",
"base_model:finetune:TheBloke/Mistral-7B-Instruct-v0.1-GPTQ",
"license:apache-2.0",
"region:us"
] | null | 2023-10-15T04:47:13Z |
---
license: apache-2.0
base_model: TheBloke/Mistral-7B-Instruct-v0.1-GPTQ
tags:
- generated_from_trainer
model-index:
- name: mistral-finetuned-samsum
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# mistral-finetuned-samsum
This model is a fine-tuned version of [TheBloke/Mistral-7B-Instruct-v0.1-GPTQ](https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.1-GPTQ) on the None dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- training_steps: 250
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- Transformers 4.35.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
|
apage43/MetaMath-7B-V1.0-GGUF
|
apage43
| 2023-10-15T05:31:09Z | 8 | 0 | null |
[
"gguf",
"license:llama2",
"endpoints_compatible",
"region:us"
] | null | 2023-10-15T04:44:57Z |
---
license: llama2
---
see https://huggingface.co/meta-math/MetaMath-7B-V1.0
|
salohiddin94/ppo-SnowballTarget
|
salohiddin94
| 2023-10-15T05:27:04Z | 0 | 0 |
ml-agents
|
[
"ml-agents",
"tensorboard",
"onnx",
"SnowballTarget",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-SnowballTarget",
"region:us"
] |
reinforcement-learning
| 2023-10-15T05:16:50Z |
---
library_name: ml-agents
tags:
- SnowballTarget
- deep-reinforcement-learning
- reinforcement-learning
- ML-Agents-SnowballTarget
---
# **ppo** Agent playing **SnowballTarget**
This is a trained model of a **ppo** agent playing **SnowballTarget**
using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
## Usage (with ML-Agents)
The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
- A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
- A *longer tutorial* to understand how works ML-Agents:
https://huggingface.co/learn/deep-rl-course/unit5/introduction
### Resume the training
```bash
!mlagents-push-to-hf --run-id="SnowballTarget1" --local-dir="./results/SnowballTarget1" --repo-id="salohiddin94/ppo-SnowballTarget" --commit-message="First Push"
```
### Watch your Agent play
You can watch your agent **playing directly in your browser**
1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
2. Step 1: Find your model_id: salohiddin94/ppo-SnowballTarget
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
provezano/distilbert-base-uncased-finetuned-emotion
|
provezano
| 2023-10-15T04:57:49Z | 3 | 0 |
transformers
|
[
"transformers",
"pytorch",
"distilbert",
"text-classification",
"generated_from_trainer",
"dataset:emotion",
"base_model:distilbert/distilbert-base-uncased",
"base_model:finetune:distilbert/distilbert-base-uncased",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-09-22T15:18:08Z |
---
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
datasets:
- emotion
metrics:
- accuracy
- f1
model-index:
- name: distilbert-base-uncased-finetuned-emotion
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: emotion
type: emotion
config: split
split: validation
args: split
metrics:
- name: Accuracy
type: accuracy
value: 0.9215
- name: F1
type: f1
value: 0.9215828481864327
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# distilbert-base-uncased-finetuned-emotion
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the emotion dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2183
- Accuracy: 0.9215
- F1: 0.9216
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| 0.8087 | 1.0 | 250 | 0.3274 | 0.8995 | 0.8985 |
| 0.2499 | 2.0 | 500 | 0.2183 | 0.9215 | 0.9216 |
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1
- Datasets 2.14.4
- Tokenizers 0.13.3
|
sankar82/q-Taxi-v3_2
|
sankar82
| 2023-10-15T04:51:41Z | 0 | 0 | null |
[
"Taxi-v3",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-10-15T04:44:51Z |
---
tags:
- Taxi-v3
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: q-Taxi-v3_2
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Taxi-v3
type: Taxi-v3
metrics:
- type: mean_reward
value: 7.56 +/- 2.71
name: mean_reward
verified: false
---
# **Q-Learning** Agent playing1 **Taxi-v3**
This is a trained model of a **Q-Learning** agent playing **Taxi-v3** .
## Usage
```python
model = load_from_hub(repo_id="sankar82/q-Taxi-v3_2", filename="q-learning.pkl")
# Don't forget to check if you need to add additional attributes (is_slippery=False etc)
env = gym.make(model["env_id"])
```
|
LoneStriker/Mistral-11B-CC-Air-6.0bpw-h6-exl2
|
LoneStriker
| 2023-10-15T04:46:38Z | 4 | 0 |
transformers
|
[
"transformers",
"safetensors",
"mistral",
"text-generation",
"pretrained",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-10-15T04:45:58Z |
---
license: apache-2.0
tags:
- mistral
- pretrained
---
CollectiveCognition-v1.1-Mistral-7B and airoboros-mistral2.2-7b glued together.
<!-- description start -->
## Description
This repo contains fp16 files of Mistral-11B-CC-Air.
<!-- description end -->
<!-- description start -->
## Model used
- [CollectiveCognition-v1.1-Mistral-7B](https://huggingface.co/teknium/CollectiveCognition-v1.1-Mistral-7B)
- [airoboros-mistral2.2-7b](https://huggingface.co/teknium/airoboros-mistral2.2-7b/)
<!-- description end -->
<!-- prompt-template start -->
## Prompt template: Alpaca or default
```
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{prompt}
### Response:
```
```
USER: <prompt>
ASSISTANT:
```
## The secret sauce
```
slices:
- sources:
- model: teknium/CollectiveCognition-v1.1-Mistral-7B
layer_range: [0, 24]
- sources:
- model: teknium/airoboros-mistral2.2-7b
layer_range: [8, 32]
merge_method: passthrough
dtype: float16
```
Special thanks to Sushi.
If you want to support me, you can [here](https://ko-fi.com/undiai).
|
1TuanPham/Instruction_tune_8k_e3_en-vi_EleutherAI_pythia-410m-deduped-v0_LORA_CAUSAL_LM
|
1TuanPham
| 2023-10-15T04:40:13Z | 1 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-10-15T03:15:56Z |
---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: True
- load_in_4bit: False
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: True
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: fp4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float32
### Framework versions
- PEFT 0.5.0
|
LoneStriker/Mistral-11B-CC-Air-5.0bpw-h6-exl2
|
LoneStriker
| 2023-10-15T04:27:21Z | 6 | 0 |
transformers
|
[
"transformers",
"safetensors",
"mistral",
"text-generation",
"pretrained",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-10-15T04:26:49Z |
---
license: apache-2.0
tags:
- mistral
- pretrained
---
CollectiveCognition-v1.1-Mistral-7B and airoboros-mistral2.2-7b glued together.
<!-- description start -->
## Description
This repo contains fp16 files of Mistral-11B-CC-Air.
<!-- description end -->
<!-- description start -->
## Model used
- [CollectiveCognition-v1.1-Mistral-7B](https://huggingface.co/teknium/CollectiveCognition-v1.1-Mistral-7B)
- [airoboros-mistral2.2-7b](https://huggingface.co/teknium/airoboros-mistral2.2-7b/)
<!-- description end -->
<!-- prompt-template start -->
## Prompt template: Alpaca or default
```
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{prompt}
### Response:
```
```
USER: <prompt>
ASSISTANT:
```
## The secret sauce
```
slices:
- sources:
- model: teknium/CollectiveCognition-v1.1-Mistral-7B
layer_range: [0, 24]
- sources:
- model: teknium/airoboros-mistral2.2-7b
layer_range: [8, 32]
merge_method: passthrough
dtype: float16
```
Special thanks to Sushi.
If you want to support me, you can [here](https://ko-fi.com/undiai).
|
sankar82/q-Taxi-v3
|
sankar82
| 2023-10-15T04:26:33Z | 0 | 0 | null |
[
"Taxi-v3",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-10-15T04:26:31Z |
---
tags:
- Taxi-v3
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: q-Taxi-v3
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Taxi-v3
type: Taxi-v3
metrics:
- type: mean_reward
value: 7.50 +/- 2.72
name: mean_reward
verified: false
---
# **Q-Learning** Agent playing1 **Taxi-v3**
This is a trained model of a **Q-Learning** agent playing **Taxi-v3** .
## Usage
```python
model = load_from_hub(repo_id="sankar82/q-Taxi-v3", filename="q-learning.pkl")
# Don't forget to check if you need to add additional attributes (is_slippery=False etc)
env = gym.make(model["env_id"])
```
|
LoneStriker/Mistral-11B-CC-Air-4.0bpw-h6-exl2
|
LoneStriker
| 2023-10-15T04:11:58Z | 4 | 0 |
transformers
|
[
"transformers",
"safetensors",
"mistral",
"text-generation",
"pretrained",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-10-15T04:11:32Z |
---
license: apache-2.0
tags:
- mistral
- pretrained
---
CollectiveCognition-v1.1-Mistral-7B and airoboros-mistral2.2-7b glued together.
<!-- description start -->
## Description
This repo contains fp16 files of Mistral-11B-CC-Air.
<!-- description end -->
<!-- description start -->
## Model used
- [CollectiveCognition-v1.1-Mistral-7B](https://huggingface.co/teknium/CollectiveCognition-v1.1-Mistral-7B)
- [airoboros-mistral2.2-7b](https://huggingface.co/teknium/airoboros-mistral2.2-7b/)
<!-- description end -->
<!-- prompt-template start -->
## Prompt template: Alpaca or default
```
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{prompt}
### Response:
```
```
USER: <prompt>
ASSISTANT:
```
## The secret sauce
```
slices:
- sources:
- model: teknium/CollectiveCognition-v1.1-Mistral-7B
layer_range: [0, 24]
- sources:
- model: teknium/airoboros-mistral2.2-7b
layer_range: [8, 32]
merge_method: passthrough
dtype: float16
```
Special thanks to Sushi.
If you want to support me, you can [here](https://ko-fi.com/undiai).
|
OckerGui/videomae-base-finetuned-ESBD
|
OckerGui
| 2023-10-15T04:02:02Z | 3 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"videomae",
"video-classification",
"generated_from_trainer",
"license:cc-by-nc-4.0",
"endpoints_compatible",
"region:us"
] |
video-classification
| 2023-10-15T03:18:28Z |
---
license: cc-by-nc-4.0
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: videomae-base-finetuned-ESBD
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# videomae-base-finetuned-ESBD
This model is a fine-tuned version of [MCG-NJU/videomae-base](https://huggingface.co/MCG-NJU/videomae-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.6116
- Accuracy: 0.3095
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 12
- eval_batch_size: 12
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- training_steps: 300
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 1.4599 | 0.09 | 27 | 1.3408 | 0.3333 |
| 1.217 | 1.09 | 54 | 1.3656 | 0.3571 |
| 1.2652 | 2.09 | 81 | 1.2593 | 0.3095 |
| 0.797 | 3.09 | 108 | 0.9102 | 0.5952 |
| 1.2926 | 4.09 | 135 | 0.9243 | 0.6429 |
| 0.4508 | 5.09 | 162 | 0.9276 | 0.6905 |
| 0.3649 | 6.09 | 189 | 0.6216 | 0.7857 |
| 0.1679 | 7.09 | 216 | 1.1307 | 0.6667 |
| 0.1277 | 8.09 | 243 | 0.9728 | 0.6667 |
| 0.0665 | 9.09 | 270 | 0.8415 | 0.7619 |
| 0.0148 | 10.09 | 297 | 0.7911 | 0.7857 |
| 0.0136 | 11.01 | 300 | 0.7950 | 0.7857 |
### Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
|
LoneStriker/Mistral-11B-CC-Air-3.0bpw-h6-exl2
|
LoneStriker
| 2023-10-15T03:59:19Z | 5 | 0 |
transformers
|
[
"transformers",
"safetensors",
"mistral",
"text-generation",
"pretrained",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-10-15T03:58:50Z |
---
license: apache-2.0
tags:
- mistral
- pretrained
---
CollectiveCognition-v1.1-Mistral-7B and airoboros-mistral2.2-7b glued together.
<!-- description start -->
## Description
This repo contains fp16 files of Mistral-11B-CC-Air.
<!-- description end -->
<!-- description start -->
## Model used
- [CollectiveCognition-v1.1-Mistral-7B](https://huggingface.co/teknium/CollectiveCognition-v1.1-Mistral-7B)
- [airoboros-mistral2.2-7b](https://huggingface.co/teknium/airoboros-mistral2.2-7b/)
<!-- description end -->
<!-- prompt-template start -->
## Prompt template: Alpaca or default
```
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{prompt}
### Response:
```
```
USER: <prompt>
ASSISTANT:
```
## The secret sauce
```
slices:
- sources:
- model: teknium/CollectiveCognition-v1.1-Mistral-7B
layer_range: [0, 24]
- sources:
- model: teknium/airoboros-mistral2.2-7b
layer_range: [8, 32]
merge_method: passthrough
dtype: float16
```
Special thanks to Sushi.
If you want to support me, you can [here](https://ko-fi.com/undiai).
|
mitchyAI/haerinmchy
|
mitchyAI
| 2023-10-15T03:48:30Z | 0 | 0 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-10-15T03:42:42Z |
---
license: creativeml-openrail-m
---
|
ahatamiz/FasterViT
|
ahatamiz
| 2023-10-15T03:43:34Z | 0 | 0 | null |
[
"dataset:imagenet-1k",
"arxiv:2306.06189",
"license:other",
"region:us"
] | null | 2023-08-03T18:02:47Z |
---
license: other
datasets:
- imagenet-1k
---
[**FasterViT: Fast Vision Transformers with Hierarchical Attention**](https://arxiv.org/abs/2306.06189).
FasterViT achieves a new SOTA Pareto-front in
terms of accuracy vs. image throughput without extra training data !
<p align="center">
<img src="https://github.com/NVlabs/FasterViT/assets/26806394/253d1a2e-b5f5-4a9b-a362-6cdd16bfccc1" width=62% height=62%
class="center">
</p>
Note: Please use the [**latest NVIDIA TensorRT release**](https://docs.nvidia.com/deeplearning/tensorrt/container-release-notes/index.html) to enjoy the benefits of optimized FasterViT ops.
## Quick Start
We can import pre-trained FasterViT models with **1 line of code**. First, FasterViT can be simply installed by:
```bash
pip install fastervit
```
A pretrained FasterViT model with default hyper-parameters can be created as in the following:
```python
>>> from fastervit import create_model
# Define fastervit-0 model with 224 x 224 resolution
>>> model = create_model('faster_vit_0_224',
pretrained=True,
model_path="/tmp/faster_vit_0.pth.tar")
```
`model_path` is used to set the directory to download the model.
We can also simply test the model by passing a dummy input image. The output is the logits:
```python
>>> import torch
>>> image = torch.rand(1, 3, 224, 224)
>>> output = model(image) # torch.Size([1, 1000])
```
We can also use the any-resolution FasterViT model to accommodate arbitrary image resolutions. In the following, we define an any-resolution FasterViT-0
model with input resolution of 576 x 960, window sizes of 12 and 6 in 3rd and 4th stages, carrier token size of 2 and embedding dimension of
64:
```python
>>> from fastervit import create_model
# Define any-resolution FasterViT-0 model with 576 x 960 resolution
>>> model = create_model('faster_vit_0_any_res',
resolution=[576, 960],
window_size=[7, 7, 12, 6],
ct_size=2,
dim=64,
pretrained=True)
```
Note that the above model is intiliazed from the original ImageNet pre-trained FasterViT with original resolution of 224 x 224. As a result, missing keys and mis-matches could be expected since we are addign new layers (e.g. addition of new carrier tokens, etc.)
We can simply test the model by passing a dummy input image. The output is the logits:
```python
>>> import torch
>>> image = torch.rand(1, 3, 576, 960)
>>> output = model(image) # torch.Size([1, 1000])
```
---
## Results + Pretrained Models
### ImageNet-1K
**FasterViT ImageNet-1K Pretrained Models**
<table>
<tr>
<th>Name</th>
<th>Acc@1(%)</th>
<th>Acc@5(%)</th>
<th>Throughput(Img/Sec)</th>
<th>Resolution</th>
<th>#Params(M)</th>
<th>FLOPs(G)</th>
<th>Download</th>
</tr>
<tr>
<td>FasterViT-0</td>
<td>82.1</td>
<td>95.9</td>
<td>5802</td>
<td>224x224</td>
<td>31.4</td>
<td>3.3</td>
<td><a href="https://drive.google.com/uc?export=download&id=1twI2LFJs391Yrj8MR4Ui9PfrvWqjE1iB">model</a></td>
</tr>
<tr>
<td>FasterViT-1</td>
<td>83.2</td>
<td>96.5</td>
<td>4188</td>
<td>224x224</td>
<td>53.4</td>
<td>5.3</td>
<td><a href="https://drive.google.com/uc?export=download&id=1r7W10n5-bFtM3sz4bmaLrowN2gYPkLGT">model</a></td>
</tr>
<tr>
<td>FasterViT-2</td>
<td>84.2</td>
<td>96.8</td>
<td>3161</td>
<td>224x224</td>
<td>75.9</td>
<td>8.7</td>
<td><a href="https://drive.google.com/uc?export=download&id=1n_a6s0pgi0jVZOGmDei2vXHU5E6RH5wU">model</a></td>
</tr>
<tr>
<td>FasterViT-3</td>
<td>84.9</td>
<td>97.2</td>
<td>1780</td>
<td>224x224</td>
<td>159.5</td>
<td>18.2</td>
<td><a href="https://drive.google.com/uc?export=download&id=1tvWElZ91Sia2SsXYXFMNYQwfipCxtI7X">model</a></td>
</tr>
<tr>
<td>FasterViT-4</td>
<td>85.4</td>
<td>97.3</td>
<td>849</td>
<td>224x224</td>
<td>424.6</td>
<td>36.6</td>
<td><a href="https://drive.google.com/uc?export=download&id=1gYhXA32Q-_9C5DXel17avV_ZLoaHwdgz">model</a></td>
</tr>
<tr>
<td>FasterViT-5</td>
<td>85.6</td>
<td>97.4</td>
<td>449</td>
<td>224x224</td>
<td>975.5</td>
<td>113.0</td>
<td><a href="https://drive.google.com/uc?export=download&id=1mqpai7XiHLr_n1tjxjzT8q369xTCq_z-">model</a></td>
</tr>
<tr>
<td>FasterViT-6</td>
<td>85.8</td>
<td>97.4</td>
<td>352</td>
<td>224x224</td>
<td>1360.0</td>
<td>142.0</td>
<td><a href="https://drive.google.com/uc?export=download&id=12jtavR2QxmMzcKwPzWe7kw-oy34IYi59">model</a></td>
</tr>
</table>
### ImageNet-21K
**FasterViT ImageNet-21K Pretrained Models (ImageNet-1K Fine-tuned)**
<table>
<tr>
<th>Name</th>
<th>Acc@1(%)</th>
<th>Acc@5(%)</th>
<th>Resolution</th>
<th>#Params(M)</th>
<th>FLOPs(G)</th>
<th>Download</th>
</tr>
<tr>
<td>FasterViT-4-21K-224</td>
<td>86.6</td>
<td>97.8</td>
<td>224x224</td>
<td>271.9</td>
<td>40.8</td>
<td><a href="https://huggingface.co/ahatamiz/FasterViT/resolve/main/fastervit_4_21k_224_w14.pth.tar">model</a></td>
</tr>
<tr>
<td>FasterViT-4-21K-384</td>
<td>87.6</td>
<td>98.3</td>
<td>384x384</td>
<td>271.9</td>
<td>120.1</td>
<td><a href="https://huggingface.co/ahatamiz/FasterViT/resolve/main/fastervit_4_21k_384_w24.pth.tar">model</a></td>
</tr>
<tr>
<td>FasterViT-4-21K-512</td>
<td>87.8</td>
<td>98.4</td>
<td>512x512</td>
<td>271.9</td>
<td>213.5</td>
<td><a href="https://huggingface.co/ahatamiz/FasterViT/resolve/main/fastervit_4_21k_512_w32.pth.tar">model</a></td>
</tr>
<tr>
<td>FasterViT-4-21K-768</td>
<td>87.9</td>
<td>98.5</td>
<td>768x768</td>
<td>271.9</td>
<td>480.4</td>
<td><a href="https://huggingface.co/ahatamiz/FasterViT/resolve/main/fastervit_4_21k_768_w48.pth.tar">model</a></td>
</tr>
</table>
### Robustness (ImageNet-A - ImageNet-R - ImageNet-V2)
All models use `crop_pct=0.875`. Results are obtained by running inference on ImageNet-1K pretrained models without finetuning.
<table>
<tr>
<th>Name</th>
<th>A-Acc@1(%)</th>
<th>A-Acc@5(%)</th>
<th>R-Acc@1(%)</th>
<th>R-Acc@5(%)</th>
<th>V2-Acc@1(%)</th>
<th>V2-Acc@5(%)</th>
</tr>
<tr>
<td>FasterViT-0</td>
<td>23.9</td>
<td>57.6</td>
<td>45.9</td>
<td>60.4</td>
<td>70.9</td>
<td>90.0</td>
</tr>
<tr>
<td>FasterViT-1</td>
<td>31.2</td>
<td>63.3</td>
<td>47.5</td>
<td>61.9</td>
<td>72.6</td>
<td>91.0</td>
</tr>
<tr>
<td>FasterViT-2</td>
<td>38.2</td>
<td>68.9</td>
<td>49.6</td>
<td>63.4</td>
<td>73.7</td>
<td>91.6</td>
</tr>
<tr>
<td>FasterViT-3</td>
<td>44.2</td>
<td>73.0</td>
<td>51.9</td>
<td>65.6</td>
<td>75.0</td>
<td>92.2</td>
</tr>
<tr>
<td>FasterViT-4</td>
<td>49.0</td>
<td>75.4</td>
<td>56.0</td>
<td>69.6</td>
<td>75.7</td>
<td>92.7</td>
</tr>
<tr>
<td>FasterViT-5</td>
<td>52.7</td>
<td>77.6</td>
<td>56.9</td>
<td>70.0</td>
<td>76.0</td>
<td>93.0</td>
</tr>
<tr>
<td>FasterViT-6</td>
<td>53.7</td>
<td>78.4</td>
<td>57.1</td>
<td>70.1</td>
<td>76.1</td>
<td>93.0</td>
</tr>
</table>
A, R and V2 denote ImageNet-A, ImageNet-R and ImageNet-V2 respectively.
## Citation
Please consider citing FasterViT if this repository is useful for your work.
```
@article{hatamizadeh2023fastervit,
title={FasterViT: Fast Vision Transformers with Hierarchical Attention},
author={Hatamizadeh, Ali and Heinrich, Greg and Yin, Hongxu and Tao, Andrew and Alvarez, Jose M and Kautz, Jan and Molchanov, Pavlo},
journal={arXiv preprint arXiv:2306.06189},
year={2023}
}
```
## Licenses
Copyright © 2023, NVIDIA Corporation. All rights reserved.
This work is made available under the NVIDIA Source Code License-NC. Click [here](LICENSE) to view a copy of this license.
For license information regarding the timm repository, please refer to its [repository](https://github.com/rwightman/pytorch-image-models).
For license information regarding the ImageNet dataset, please see the [ImageNet official website](https://www.image-net.org/).
## Acknowledgement
This repository is built on top of the [timm](https://github.com/huggingface/pytorch-image-models) repository. We thank [Ross Wrightman](https://rwightman.com/) for creating and maintaining this high-quality library.
|
asdhell096/BreastCancerUCE
|
asdhell096
| 2023-10-15T03:38:45Z | 0 | 0 | null |
[
"es",
"license:afl-3.0",
"region:us"
] | null | 2023-10-13T01:22:39Z |
---
license: afl-3.0
language:
- es
---
|
lauraparra28/Distilbert-base-uncased-finetuned-SQuAD2.0
|
lauraparra28
| 2023-10-15T03:34:17Z | 4 | 0 |
transformers
|
[
"transformers",
"pytorch",
"distilbert",
"question-answering",
"generated_from_trainer",
"dataset:squad_v2",
"base_model:distilbert/distilbert-base-uncased",
"base_model:finetune:distilbert/distilbert-base-uncased",
"license:apache-2.0",
"model-index",
"endpoints_compatible",
"region:us"
] |
question-answering
| 2023-10-15T00:41:23Z |
---
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
datasets:
- squad_v2
model-index:
- name: distilbert-base-uncased-finetuned-SQuAD2.0
results:
- task:
type: question-answering
name: Question Answering
dataset:
name: squad_v2
type: squad_v2
config: squad_v2
split: validation
metrics:
- type: exact_match
value: 63.9097
name: Exact Match
- type: f1
value: 67.6732
name: F1
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# distilbert-base-uncased-finetuned-squad-squad_v2
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the squad_v2 dataset.
It achieves the following results on the evaluation set:
- Loss: 1.8785
- Exact Match: 63.9097
- F1-score: 67.6732
## Overview
**Language model:** distilbert-base-uncased
**Language:** English
**Downstream-task:** Extractive QA
**Training data:** SQuAD 2.0
**Eval data:** SQuAD 2.0
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:-----:|:---------------:|
| 1.2231 | 1.0 | 8235 | 1.2833 |
| 0.9337 | 2.0 | 16470 | 1.2849 |
| 0.7437 | 3.0 | 24705 | 1.4186 |
| 0.5927 | 4.0 | 32940 | 1.6308 |
| 0.4795 | 5.0 | 41175 | 1.8785 |
### Framework versions
- Transformers 4.34.0
- Pytorch 1.12.1
- Datasets 2.14.5
- Tokenizers 0.14.1
|
LoneStriker/Mistral-11B-CC-Air-8.0bpw-h6-exl2
|
LoneStriker
| 2023-10-15T03:33:57Z | 7 | 0 |
transformers
|
[
"transformers",
"safetensors",
"mistral",
"text-generation",
"pretrained",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-10-15T03:33:07Z |
---
license: apache-2.0
tags:
- mistral
- pretrained
---
CollectiveCognition-v1.1-Mistral-7B and airoboros-mistral2.2-7b glued together.
<!-- description start -->
## Description
This repo contains fp16 files of Mistral-11B-CC-Air.
<!-- description end -->
<!-- description start -->
## Model used
- [CollectiveCognition-v1.1-Mistral-7B](https://huggingface.co/teknium/CollectiveCognition-v1.1-Mistral-7B)
- [airoboros-mistral2.2-7b](https://huggingface.co/teknium/airoboros-mistral2.2-7b/)
<!-- description end -->
<!-- prompt-template start -->
## Prompt template: Alpaca or default
```
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{prompt}
### Response:
```
```
USER: <prompt>
ASSISTANT:
```
## The secret sauce
```
slices:
- sources:
- model: teknium/CollectiveCognition-v1.1-Mistral-7B
layer_range: [0, 24]
- sources:
- model: teknium/airoboros-mistral2.2-7b
layer_range: [8, 32]
merge_method: passthrough
dtype: float16
```
Special thanks to Sushi.
If you want to support me, you can [here](https://ko-fi.com/undiai).
|
yesj1234/xlsr_mid2_ko-en
|
yesj1234
| 2023-10-15T03:29:17Z | 3 | 0 |
transformers
|
[
"transformers",
"pytorch",
"wav2vec2",
"automatic-speech-recognition",
"./sample_speech.py",
"generated_from_trainer",
"base_model:facebook/wav2vec2-large-xlsr-53",
"base_model:finetune:facebook/wav2vec2-large-xlsr-53",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
automatic-speech-recognition
| 2023-10-15T03:25:24Z |
---
license: apache-2.0
base_model: facebook/wav2vec2-large-xlsr-53
tags:
- automatic-speech-recognition
- ./sample_speech.py
- generated_from_trainer
model-index:
- name: en-xlsr
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# en-xlsr
This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the ./SAMPLE_SPEECH.PY - NA dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3889
- Cer: 0.1082
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0003
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- total_eval_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1500
- num_epochs: 15
### Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|:-------------:|:-----:|:-----:|:---------------:|:------:|
| 1.4503 | 1.22 | 2000 | 1.0610 | 0.2687 |
| 1.0239 | 2.45 | 4000 | 0.6962 | 0.1904 |
| 0.8977 | 3.67 | 6000 | 0.5945 | 0.1687 |
| 0.804 | 4.9 | 8000 | 0.5328 | 0.1492 |
| 0.698 | 6.12 | 10000 | 0.5014 | 0.1365 |
| 0.6426 | 7.35 | 12000 | 0.4715 | 0.1322 |
| 0.61 | 8.57 | 14000 | 0.4530 | 0.1258 |
| 0.5709 | 9.79 | 16000 | 0.4300 | 0.1201 |
| 0.5235 | 11.02 | 18000 | 0.4168 | 0.1166 |
| 0.4778 | 12.24 | 20000 | 0.4057 | 0.1129 |
| 0.4571 | 13.47 | 22000 | 0.3945 | 0.1100 |
| 0.4388 | 14.69 | 24000 | 0.3891 | 0.1081 |
### Framework versions
- Transformers 4.34.0
- Pytorch 2.1.0+cu121
- Datasets 2.14.5
- Tokenizers 0.14.1
|
yesj1234/xlsr_mid1_zh-ko
|
yesj1234
| 2023-10-15T03:20:44Z | 3 | 0 |
transformers
|
[
"transformers",
"pytorch",
"wav2vec2",
"automatic-speech-recognition",
"./sample_speech.py",
"generated_from_trainer",
"base_model:facebook/wav2vec2-large-xlsr-53",
"base_model:finetune:facebook/wav2vec2-large-xlsr-53",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
automatic-speech-recognition
| 2023-10-15T03:16:54Z |
---
license: apache-2.0
base_model: facebook/wav2vec2-large-xlsr-53
tags:
- automatic-speech-recognition
- ./sample_speech.py
- generated_from_trainer
model-index:
- name: zh-xlsr
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# zh-xlsr
This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the ./SAMPLE_SPEECH.PY - NA dataset.
It achieves the following results on the evaluation set:
- Loss: 1.8449
- Cer: 0.4954
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0003
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- total_eval_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 150
- num_epochs: 15
### Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 6.0153 | 0.5 | 330 | 5.3438 | 0.9522 |
| 5.3776 | 1.0 | 660 | 5.1534 | 0.9409 |
| 5.2604 | 1.5 | 990 | 5.0832 | 0.9108 |
| 5.2393 | 2.01 | 1320 | 5.0655 | 0.9073 |
| 5.1721 | 2.51 | 1650 | 5.0464 | 0.9000 |
| 5.1619 | 3.01 | 1980 | 5.0244 | 0.9045 |
| 5.1308 | 3.51 | 2310 | 5.0216 | 0.9020 |
| 5.0971 | 4.01 | 2640 | 4.9341 | 0.9040 |
| 5.0137 | 4.51 | 2970 | 4.8795 | 0.9144 |
| 4.9341 | 5.02 | 3300 | 4.7250 | 0.9039 |
| 4.6832 | 5.52 | 3630 | 4.2140 | 0.8367 |
| 4.1627 | 6.02 | 3960 | 3.4010 | 0.7318 |
| 3.5448 | 6.52 | 4290 | 2.8830 | 0.6480 |
| 3.2576 | 7.02 | 4620 | 2.6253 | 0.6266 |
| 2.8561 | 7.52 | 4950 | 2.4300 | 0.5866 |
| 2.7894 | 8.02 | 5280 | 2.2998 | 0.5750 |
| 2.6018 | 8.53 | 5610 | 2.1878 | 0.5549 |
| 2.546 | 9.03 | 5940 | 2.1450 | 0.5351 |
| 2.3787 | 9.53 | 6270 | 2.1027 | 0.5340 |
| 2.335 | 10.03 | 6600 | 2.0304 | 0.5166 |
| 2.2138 | 10.53 | 6930 | 2.0100 | 0.5165 |
| 2.2381 | 11.03 | 7260 | 1.9651 | 0.5031 |
| 2.1108 | 11.53 | 7590 | 1.9666 | 0.5035 |
| 2.0916 | 12.04 | 7920 | 1.9136 | 0.4998 |
| 2.0229 | 12.54 | 8250 | 1.8988 | 0.5028 |
| 2.0056 | 13.04 | 8580 | 1.8769 | 0.4996 |
| 1.9245 | 13.54 | 8910 | 1.8716 | 0.4955 |
| 1.9378 | 14.04 | 9240 | 1.8561 | 0.4946 |
| 1.9003 | 14.54 | 9570 | 1.8485 | 0.4936 |
### Framework versions
- Transformers 4.34.0
- Pytorch 2.1.0+cu121
- Datasets 2.14.5
- Tokenizers 0.14.1
|
OckerGui/videomae-base-finetuned-SSBD_Old
|
OckerGui
| 2023-10-15T03:15:11Z | 4 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"videomae",
"video-classification",
"generated_from_trainer",
"license:cc-by-nc-4.0",
"endpoints_compatible",
"region:us"
] |
video-classification
| 2023-10-15T02:59:39Z |
---
license: cc-by-nc-4.0
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: videomae-base-finetuned-SSBD
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# videomae-base-finetuned-SSBD
This model is a fine-tuned version of [MCG-NJU/videomae-base](https://huggingface.co/MCG-NJU/videomae-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.9015
- Accuracy: 0.5714
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 12
- eval_batch_size: 12
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- training_steps: 150
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 1.1764 | 0.14 | 21 | 0.9983 | 0.44 |
| 1.2156 | 1.14 | 42 | 1.1047 | 0.4 |
| 1.0214 | 2.14 | 63 | 1.2948 | 0.2 |
| 0.5585 | 3.14 | 84 | 2.0400 | 0.44 |
| 0.3809 | 4.14 | 105 | 2.2227 | 0.4 |
| 0.1665 | 5.14 | 126 | 2.2653 | 0.12 |
| 0.0736 | 6.14 | 147 | 2.8244 | 0.24 |
| 0.0501 | 7.02 | 150 | 2.8418 | 0.2 |
### Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
|
cys/ppo-LunarLander-v2
|
cys
| 2023-10-15T02:58:25Z | 1 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-10-15T02:58:04Z |
---
library_name: stable-baselines3
tags:
- LunarLander-v2
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: PPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: LunarLander-v2
type: LunarLander-v2
metrics:
- type: mean_reward
value: 265.30 +/- 17.46
name: mean_reward
verified: false
---
# **PPO** Agent playing **LunarLander-v2**
This is a trained model of a **PPO** agent playing **LunarLander-v2**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
## Usage (with Stable-baselines3)
TODO: Add your code
```python
from stable_baselines3 import ...
from huggingface_sb3 import load_from_hub
...
```
|
OckerGui/videomae-base-finetuned-ASBD
|
OckerGui
| 2023-10-15T02:54:14Z | 1 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"videomae",
"video-classification",
"generated_from_trainer",
"license:cc-by-nc-4.0",
"endpoints_compatible",
"region:us"
] |
video-classification
| 2023-10-15T01:52:55Z |
---
license: cc-by-nc-4.0
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: videomae-base-finetuned-ASBD
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# videomae-base-finetuned-ASBD
This model is a fine-tuned version of [MCG-NJU/videomae-base](https://huggingface.co/MCG-NJU/videomae-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7908
- Accuracy: 0.6912
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 12
- eval_batch_size: 12
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- training_steps: 500
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 1.274 | 0.1 | 49 | 1.3780 | 0.1892 |
| 1.2578 | 1.1 | 98 | 1.4805 | 0.3378 |
| 0.8274 | 2.1 | 147 | 1.0223 | 0.5270 |
| 0.6943 | 3.1 | 196 | 1.1050 | 0.6486 |
| 0.4192 | 4.1 | 245 | 1.3384 | 0.6081 |
| 0.3951 | 5.1 | 294 | 1.6994 | 0.5541 |
| 0.2655 | 6.1 | 343 | 1.7021 | 0.5946 |
| 0.0256 | 7.1 | 392 | 1.5357 | 0.6216 |
| 0.0368 | 8.1 | 441 | 1.6924 | 0.6892 |
| 0.0275 | 9.1 | 490 | 1.6663 | 0.6892 |
| 0.0364 | 10.02 | 500 | 1.6649 | 0.6757 |
### Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
|
lauraparra28/Roberta-base-finetuned-SQuAD2.0
|
lauraparra28
| 2023-10-15T02:52:14Z | 31 | 0 |
transformers
|
[
"transformers",
"pytorch",
"roberta",
"question-answering",
"generated_from_trainer",
"en",
"dataset:squad_v2",
"base_model:FacebookAI/roberta-base",
"base_model:finetune:FacebookAI/roberta-base",
"license:mit",
"model-index",
"endpoints_compatible",
"region:us"
] |
question-answering
| 2023-10-13T19:06:08Z |
---
license: mit
base_model: roberta-base
tags:
- generated_from_trainer
datasets:
- squad_v2
model-index:
- name: roberta-base-finetuned-squad
results:
- task:
type: question-answering
name: Question Answering
dataset:
name: squad_v2
type: squad_v2
config: squad_v2
split: validation
metrics:
- type: exact_match
value: 83.159
name: Exact Match
- type: f1
value: 79.684
name: F1
language:
- en
metrics:
- exact_match
- f1
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# roberta-base-finetuned-squad_v2
This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the [SQuAD2.0](https://huggingface.co/datasets/squad_v2).
It achieves the following results on the evaluation set:
- Loss: 1.2340
- Exact Match: 79.684
- F1-score: 83.159
## Overview
**Language model:** roberta-base
**Language:** English
**Downstream-task:** Extractive QA
**Training data:** SQuAD 2.0
**Eval data:** SQuAD 2.0
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:-----:|:---------------:|
| 0.8978 | 1.0 | 8239 | 0.8532 |
| 0.6621 | 2.0 | 16478 | 0.9733 |
| 0.5045 | 3.0 | 24717 | 0.9010 |
| 0.3837 | 4.0 | 32956 | 1.0523 |
| 0.3069 | 5.0 | 41195 | 1.2340 |
### Framework versions
- Transformers 4.34.0
- Pytorch 1.12.1
- Datasets 2.14.5
- Tokenizers 0.14.1
|
TheBloke/tora-code-7B-v1.0-GGUF
|
TheBloke
| 2023-10-15T02:07:17Z | 30 | 3 |
transformers
|
[
"transformers",
"gguf",
"llama",
"code",
"math",
"text-generation",
"en",
"dataset:gsm8k",
"dataset:competition_math",
"arxiv:2309.17452",
"base_model:llm-agents/tora-code-7b-v1.0",
"base_model:quantized:llm-agents/tora-code-7b-v1.0",
"license:llama2",
"region:us"
] |
text-generation
| 2023-10-15T02:03:17Z |
---
base_model: llm-agents/tora-code-7b-v1.0
datasets:
- gsm8k
- competition_math
inference: false
language:
- en
library_name: transformers
license: llama2
metrics:
- exact_match
model_creator: LLM-Agents
model_name: ToRA Code 7B v1.0
model_type: llama
pipeline_tag: text-generation
prompt_template: '<|user|>
{prompt}
<|assistant|>
'
quantized_by: TheBloke
tags:
- code
- math
---
<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->
# ToRA Code 7B v1.0 - GGUF
- Model creator: [LLM-Agents](https://huggingface.co/llm-agents)
- Original model: [ToRA Code 7B v1.0](https://huggingface.co/llm-agents/tora-code-7b-v1.0)
<!-- description start -->
## Description
This repo contains GGUF format model files for [LLM-Agents's ToRA Code 7B v1.0](https://huggingface.co/llm-agents/tora-code-7b-v1.0).
<!-- description end -->
<!-- README_GGUF.md-about-gguf start -->
### About GGUF
GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp.
Here is an incomplate list of clients and libraries that are known to support GGUF:
* [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option.
* [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.
* [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.
* [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration.
* [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection.
* [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.
* [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server.
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
* [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use.
<!-- README_GGUF.md-about-gguf end -->
<!-- repositories-available start -->
## Repositories available
* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/tora-code-7B-v1.0-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/tora-code-7B-v1.0-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/tora-code-7B-v1.0-GGUF)
* [LLM-Agents's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/llm-agents/tora-code-7b-v1.0)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: ToRA
```
<|user|>
{prompt}
<|assistant|>
```
<!-- prompt-template end -->
<!-- compatibility_gguf start -->
## Compatibility
These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221)
They are also compatible with many third party UIs and libraries - please see the list at the top of this README.
## Explanation of quantisation methods
<details>
<summary>Click to see details</summary>
The new methods available are:
* GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
* GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
* GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
* GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
* GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
Refer to the Provided Files table below to see what files use which methods, and how.
</details>
<!-- compatibility_gguf end -->
<!-- README_GGUF.md-provided-files start -->
## Provided files
| Name | Quant method | Bits | Size | Max RAM required | Use case |
| ---- | ---- | ---- | ---- | ---- | ----- |
| [tora-code-7b-v1.0.Q2_K.gguf](https://huggingface.co/TheBloke/tora-code-7B-v1.0-GGUF/blob/main/tora-code-7b-v1.0.Q2_K.gguf) | Q2_K | 2 | 2.83 GB| 5.33 GB | smallest, significant quality loss - not recommended for most purposes |
| [tora-code-7b-v1.0.Q3_K_S.gguf](https://huggingface.co/TheBloke/tora-code-7B-v1.0-GGUF/blob/main/tora-code-7b-v1.0.Q3_K_S.gguf) | Q3_K_S | 3 | 2.95 GB| 5.45 GB | very small, high quality loss |
| [tora-code-7b-v1.0.Q3_K_M.gguf](https://huggingface.co/TheBloke/tora-code-7B-v1.0-GGUF/blob/main/tora-code-7b-v1.0.Q3_K_M.gguf) | Q3_K_M | 3 | 3.30 GB| 5.80 GB | very small, high quality loss |
| [tora-code-7b-v1.0.Q3_K_L.gguf](https://huggingface.co/TheBloke/tora-code-7B-v1.0-GGUF/blob/main/tora-code-7b-v1.0.Q3_K_L.gguf) | Q3_K_L | 3 | 3.60 GB| 6.10 GB | small, substantial quality loss |
| [tora-code-7b-v1.0.Q4_0.gguf](https://huggingface.co/TheBloke/tora-code-7B-v1.0-GGUF/blob/main/tora-code-7b-v1.0.Q4_0.gguf) | Q4_0 | 4 | 3.83 GB| 6.33 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [tora-code-7b-v1.0.Q4_K_S.gguf](https://huggingface.co/TheBloke/tora-code-7B-v1.0-GGUF/blob/main/tora-code-7b-v1.0.Q4_K_S.gguf) | Q4_K_S | 4 | 3.86 GB| 6.36 GB | small, greater quality loss |
| [tora-code-7b-v1.0.Q4_K_M.gguf](https://huggingface.co/TheBloke/tora-code-7B-v1.0-GGUF/blob/main/tora-code-7b-v1.0.Q4_K_M.gguf) | Q4_K_M | 4 | 4.08 GB| 6.58 GB | medium, balanced quality - recommended |
| [tora-code-7b-v1.0.Q5_0.gguf](https://huggingface.co/TheBloke/tora-code-7B-v1.0-GGUF/blob/main/tora-code-7b-v1.0.Q5_0.gguf) | Q5_0 | 5 | 4.65 GB| 7.15 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [tora-code-7b-v1.0.Q5_K_S.gguf](https://huggingface.co/TheBloke/tora-code-7B-v1.0-GGUF/blob/main/tora-code-7b-v1.0.Q5_K_S.gguf) | Q5_K_S | 5 | 4.65 GB| 7.15 GB | large, low quality loss - recommended |
| [tora-code-7b-v1.0.Q5_K_M.gguf](https://huggingface.co/TheBloke/tora-code-7B-v1.0-GGUF/blob/main/tora-code-7b-v1.0.Q5_K_M.gguf) | Q5_K_M | 5 | 4.78 GB| 7.28 GB | large, very low quality loss - recommended |
| [tora-code-7b-v1.0.Q6_K.gguf](https://huggingface.co/TheBloke/tora-code-7B-v1.0-GGUF/blob/main/tora-code-7b-v1.0.Q6_K.gguf) | Q6_K | 6 | 5.53 GB| 8.03 GB | very large, extremely low quality loss |
| [tora-code-7b-v1.0.Q8_0.gguf](https://huggingface.co/TheBloke/tora-code-7B-v1.0-GGUF/blob/main/tora-code-7b-v1.0.Q8_0.gguf) | Q8_0 | 8 | 7.16 GB| 9.66 GB | very large, extremely low quality loss - not recommended |
**Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
<!-- README_GGUF.md-provided-files end -->
<!-- README_GGUF.md-how-to-download start -->
## How to download GGUF files
**Note for manual downloaders:** You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.
The following clients/libraries will automatically download models for you, providing a list of available models to choose from:
- LM Studio
- LoLLMS Web UI
- Faraday.dev
### In `text-generation-webui`
Under Download Model, you can enter the model repo: TheBloke/tora-code-7B-v1.0-GGUF and below it, a specific filename to download, such as: tora-code-7b-v1.0.Q4_K_M.gguf.
Then click Download.
### On the command line, including multiple files at once
I recommend using the `huggingface-hub` Python library:
```shell
pip3 install huggingface-hub
```
Then you can download any individual model file to the current directory, at high speed, with a command like this:
```shell
huggingface-cli download TheBloke/tora-code-7B-v1.0-GGUF tora-code-7b-v1.0.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
<details>
<summary>More advanced huggingface-cli download usage</summary>
You can also download multiple files at once with a pattern:
```shell
huggingface-cli download TheBloke/tora-code-7B-v1.0-GGUF --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'
```
For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
```shell
pip3 install hf_transfer
```
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
```shell
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/tora-code-7B-v1.0-GGUF tora-code-7b-v1.0.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
</details>
<!-- README_GGUF.md-how-to-download end -->
<!-- README_GGUF.md-how-to-run start -->
## Example `llama.cpp` command
Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
```shell
./main -ngl 32 -m tora-code-7b-v1.0.Q4_K_M.gguf --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "<|user|>\n{prompt}\n<|assistant|>"
```
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
Change `-c 4096` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically.
If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)
## How to run in `text-generation-webui`
Further instructions here: [text-generation-webui/docs/llama.cpp.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/llama.cpp.md).
## How to run from Python code
You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries.
### How to load this model in Python code, using ctransformers
#### First install the package
Run one of the following commands, according to your system:
```shell
# Base ctransformers with no GPU acceleration
pip install ctransformers
# Or with CUDA GPU acceleration
pip install ctransformers[cuda]
# Or with AMD ROCm GPU acceleration (Linux only)
CT_HIPBLAS=1 pip install ctransformers --no-binary ctransformers
# Or with Metal GPU acceleration for macOS systems only
CT_METAL=1 pip install ctransformers --no-binary ctransformers
```
#### Simple ctransformers example code
```python
from ctransformers import AutoModelForCausalLM
# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
llm = AutoModelForCausalLM.from_pretrained("TheBloke/tora-code-7B-v1.0-GGUF", model_file="tora-code-7b-v1.0.Q4_K_M.gguf", model_type="llama", gpu_layers=50)
print(llm("AI is going to"))
```
## How to use with LangChain
Here are guides on using llama-cpp-python and ctransformers with LangChain:
* [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp)
* [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers)
<!-- README_GGUF.md-how-to-run end -->
<!-- footer start -->
<!-- 200823 -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute
Thanks to the [chirper.ai](https://chirper.ai) team!
Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Aemon Algiz.
**Patreon special mentions**: Pierre Kircher, Stanislav Ovsiannikov, Michael Levine, Eugene Pentland, Andrey, 준교 김, Randy H, Fred von Graf, Artur Olbinski, Caitlyn Gatomon, terasurfer, Jeff Scroggin, James Bentley, Vadim, Gabriel Puliatti, Harry Royden McLaughlin, Sean Connelly, Dan Guido, Edmond Seymore, Alicia Loh, subjectnull, AzureBlack, Manuel Alberto Morcote, Thomas Belote, Lone Striker, Chris Smitley, Vitor Caleffi, Johann-Peter Hartmann, Clay Pascal, biorpg, Brandon Frisco, sidney chen, transmissions 11, Pedro Madruga, jinyuan sun, Ajan Kanaga, Emad Mostaque, Trenton Dambrowitz, Jonathan Leane, Iucharbius, usrbinkat, vamX, George Stoitzev, Luke Pendergrass, theTransient, Olakabola, Swaroop Kallakuri, Cap'n Zoog, Brandon Phillips, Michael Dempsey, Nikolai Manek, danny, Matthew Berman, Gabriel Tamborski, alfie_i, Raymond Fosdick, Tom X Nguyen, Raven Klaugh, LangChain4j, Magnesian, Illia Dulskyi, David Ziegler, Mano Prime, Luis Javier Navarrete Lozano, Erik Bjäreholt, 阿明, Nathan Dryer, Alex, Rainer Wilmers, zynix, TL, Joseph William Delisle, John Villwock, Nathan LeClaire, Willem Michiel, Joguhyik, GodLy, OG, Alps Aficionado, Jeffrey Morgan, ReadyPlayerEmma, Tiffany J. Kim, Sebastain Graf, Spencer Kim, Michael Davis, webtim, Talal Aujan, knownsqashed, John Detwiler, Imad Khwaja, Deo Leter, Jerry Meng, Elijah Stavena, Rooh Singh, Pieter, SuperWojo, Alexandros Triantafyllidis, Stephen Murray, Ai Maven, ya boyyy, Enrico Ros, Ken Nordquist, Deep Realms, Nicholas, Spiking Neurons AB, Elle, Will Dee, Jack West, RoA, Luke @flexchar, Viktor Bowallius, Derek Yates, Subspace Studios, jjj, Toran Billups, Asp the Wyvern, Fen Risland, Ilya, NimbleBox.ai, Chadd, Nitin Borwankar, Emre, Mandus, Leonard Tan, Kalila, K, Trailburnt, S_X, Cory Kujawski
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
<!-- footer end -->
<!-- original-model-card start -->
# Original model card: LLM-Agents's ToRA Code 7B v1.0
<h1 align="center">
ToRA: A Tool-Integrated Reasoning Agent <br> for Mathematical Problem Solving
</h1>
<p align="center">
<a href="https://microsoft.github.io/ToRA/"><b>[🌐 Website]</b></a> •
<a href="https://arxiv.org/pdf/2309.17452.pdf"><b>[📜 Paper]</b></a> •
<a href="https://huggingface.co/llm-agents"><b>[🤗 HF Models]</b></a> •
<a href="https://github.com/microsoft/ToRA"><b>[🐱 GitHub]</b></a>
<br>
<a href="https://twitter.com/zhs05232838/status/1708860992631763092"><b>[🐦 Twitter]</b></a> •
<a href="https://www.reddit.com/r/LocalLLaMA/comments/1703k6d/tora_a_toolintegrated_reasoning_agent_for/"><b>[💬 Reddit]</b></a> •
<a href="https://notes.aimodels.fyi/researchers-announce-tora-training-language-models-to-better-understand-math-using-external-tools/">[🍀 Unofficial Blog]</a>
<!-- <a href="#-quick-start">Quick Start</a> • -->
<!-- <a href="#%EF%B8%8F-citation">Citation</a> -->
</p>
<p align="center">
Repo for "<a href="https://arxiv.org/pdf/2309.17452.pdf" target="_blank">ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving</a>"
</p>
## 🔥 News
- [2023/10/08] 🔥🔥🔥 All ToRA models released at [HuggingFace](https://huggingface.co/llm-agents)!!!
- [2023/09/29] ToRA paper, repo, and website released.
## 💡 Introduction
ToRA is a series of Tool-integrated Reasoning Agents designed to solve challenging mathematical reasoning problems by interacting with tools, e.g., computation libraries and symbolic solvers. ToRA series seamlessly integrate natural language reasoning with the utilization of external tools, thereby amalgamating the analytical prowess of language and the computational efficiency of external tools.
| Model | Size | GSM8k | MATH | AVG@10 math tasks<sup>†</sup> |
|---|---|---|---|---|
| GPT-4 | - | 92.0 | 42.5 | 78.3 |
| GPT-4 (PAL) | - | 94.2 | 51.8 | 86.4 |
| [ToRA-7B](https://huggingface.co/llm-agents/tora-7b-v1.0) | 7B | 68.8 | 40.1 | 62.4|
| [ToRA-Code-7B](https://huggingface.co/llm-agents/tora-code-7b-v1.0) | 7B | 72.6 | 44.6 | 66.5|
| [ToRA-13B](https://huggingface.co/llm-agents/tora-13b-v1.0) | 13B | 72.7 | 43.0 | 65.9|
| [ToRA-Code-13B](https://huggingface.co/llm-agents/tora-code-13b-v1.0) | 13B | 75.8 | 48.1 | 71.3 |
| [ToRA-Code-34B<sup>*</sup>](https://huggingface.co/llm-agents/tora-code-34b-v1.0) | 34B | 80.7 | **51.0** | 74.8 |
| [ToRA-70B](https://huggingface.co/llm-agents/tora-70b-v1.0) | 70B | **84.3** | 49.7 | **76.9** |
- <sup>*</sup>ToRA-Code-34B is currently the first and only open-source model to achieve over 50% accuracy (pass@1) on the MATH dataset, which significantly outperforms GPT-4’s CoT result (51.0 vs. 42.5), and is competitive with GPT-4 solving problems with programs. By open-sourcing our codes and models, we hope more breakthroughs will come!
- <sup>†</sup>10 math tasks include GSM8k, MATH, GSM-Hard, SVAMP, TabMWP, ASDiv, SingleEQ, SingleOP, AddSub, and MultiArith.
## ⚡️ Training
The models are trained on ToRA-Corpus 16k, which contains tool-integrated reasoning trajectories of MATH and GSM8k from GPT-4.
We use imitation learning (i.e., SFT) to fine-tune the models, and then apply our proposed *output space shaping* to improve tool-integrated reasoning behaviors. Please refer to the [paper](https://arxiv.org/pdf/2309.17452.pdf) for more details.
## 🪁 Inference & Evaluation
Please refer to ToRA's [GitHub repo](https://github.com/microsoft/ToRA) for inference, evaluation, and training code.
## ☕️ Citation
If you find this repository helpful, please consider citing our paper:
```
@misc{gou2023tora,
title={ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving},
author={Zhibin Gou and Zhihong Shao and Yeyun Gong and yelong shen and Yujiu Yang and Minlie Huang and Nan Duan and Weizhu Chen},
year={2023},
eprint={2309.17452},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
<!-- original-model-card end -->
|
petegordon/my_awesome_model
|
petegordon
| 2023-10-15T02:04:17Z | 3 | 0 |
transformers
|
[
"transformers",
"pytorch",
"distilbert",
"text-classification",
"generated_from_trainer",
"dataset:imdb",
"base_model:distilbert/distilbert-base-uncased",
"base_model:finetune:distilbert/distilbert-base-uncased",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-10-15T01:31:15Z |
---
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
datasets:
- imdb
metrics:
- accuracy
model-index:
- name: my_awesome_model
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: imdb
type: imdb
config: plain_text
split: test
args: plain_text
metrics:
- name: Accuracy
type: accuracy
value: 0.93152
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# my_awesome_model
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the imdb dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2264
- Accuracy: 0.9315
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.2239 | 1.0 | 1563 | 0.2534 | 0.9130 |
| 0.1521 | 2.0 | 3126 | 0.2264 | 0.9315 |
### Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
|
TheBloke/Xwin-LM-13B-v0.2-GPTQ
|
TheBloke
| 2023-10-15T01:34:45Z | 24 | 5 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"base_model:Xwin-LM/Xwin-LM-13B-V0.2",
"base_model:quantized:Xwin-LM/Xwin-LM-13B-V0.2",
"license:llama2",
"autotrain_compatible",
"text-generation-inference",
"4-bit",
"gptq",
"region:us"
] |
text-generation
| 2023-10-15T00:54:13Z |
---
base_model: Xwin-LM/Xwin-LM-13B-V0.2
inference: false
license: llama2
model_creator: Xwin-LM
model_name: Xwin LM 13B v0.2
model_type: llama
prompt_template: 'A chat between a curious user and an artificial intelligence assistant.
The assistant gives helpful, detailed, and polite answers to the user''s questions.
USER: {prompt} ASSISTANT:
'
quantized_by: TheBloke
---
<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->
# Xwin LM 13B v0.2 - GPTQ
- Model creator: [Xwin-LM](https://huggingface.co/Xwin-LM)
- Original model: [Xwin LM 13B v0.2](https://huggingface.co/Xwin-LM/Xwin-LM-13B-V0.2)
<!-- description start -->
## Description
This repo contains GPTQ model files for [Xwin-LM's Xwin LM 13B v0.2](https://huggingface.co/Xwin-LM/Xwin-LM-13B-V0.2).
Multiple GPTQ parameter permutations are provided; see Provided Files below for details of the options provided, their parameters, and the software used to create them.
<!-- description end -->
<!-- repositories-available start -->
## Repositories available
* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/Xwin-LM-13B-v0.2-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Xwin-LM-13B-v0.2-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/Xwin-LM-13B-v0.2-GGUF)
* [Xwin-LM's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/Xwin-LM/Xwin-LM-13B-V0.2)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: Vicuna
```
A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: {prompt} ASSISTANT:
```
<!-- prompt-template end -->
<!-- README_GPTQ.md-provided-files start -->
## Provided files, and GPTQ parameters
Multiple quantisation parameters are provided, to allow you to choose the best one for your hardware and requirements.
Each separate quant is in a different branch. See below for instructions on fetching from different branches.
Most GPTQ files are made with AutoGPTQ. Mistral models are currently made with Transformers.
<details>
<summary>Explanation of GPTQ parameters</summary>
- Bits: The bit size of the quantised model.
- GS: GPTQ group size. Higher numbers use less VRAM, but have lower quantisation accuracy. "None" is the lowest possible value.
- Act Order: True or False. Also known as `desc_act`. True results in better quantisation accuracy. Some GPTQ clients have had issues with models that use Act Order plus Group Size, but this is generally resolved now.
- Damp %: A GPTQ parameter that affects how samples are processed for quantisation. 0.01 is default, but 0.1 results in slightly better accuracy.
- GPTQ dataset: The calibration dataset used during quantisation. Using a dataset more appropriate to the model's training can improve quantisation accuracy. Note that the GPTQ calibration dataset is not the same as the dataset used to train the model - please refer to the original model repo for details of the training dataset(s).
- Sequence Length: The length of the dataset sequences used for quantisation. Ideally this is the same as the model sequence length. For some very long sequence models (16+K), a lower sequence length may have to be used. Note that a lower sequence length does not limit the sequence length of the quantised model. It only impacts the quantisation accuracy on longer inference sequences.
- ExLlama Compatibility: Whether this file can be loaded with ExLlama, which currently only supports Llama models in 4-bit.
</details>
| Branch | Bits | GS | Act Order | Damp % | GPTQ Dataset | Seq Len | Size | ExLlama | Desc |
| ------ | ---- | -- | --------- | ------ | ------------ | ------- | ---- | ------- | ---- |
| [main](https://huggingface.co/TheBloke/Xwin-LM-13B-v0.2-GPTQ/tree/main) | 4 | 128 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 7.26 GB | Yes | 4-bit, with Act Order and group size 128g. Uses even less VRAM than 64g, but with slightly lower accuracy. |
| [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/Xwin-LM-13B-v0.2-GPTQ/tree/gptq-4bit-32g-actorder_True) | 4 | 32 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 8.00 GB | Yes | 4-bit, with Act Order and group size 32g. Gives highest possible inference quality, with maximum VRAM usage. |
| [gptq-8bit--1g-actorder_True](https://huggingface.co/TheBloke/Xwin-LM-13B-v0.2-GPTQ/tree/gptq-8bit--1g-actorder_True) | 8 | None | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 13.36 GB | No | 8-bit, with Act Order. No group size, to lower VRAM requirements. |
| [gptq-8bit-128g-actorder_True](https://huggingface.co/TheBloke/Xwin-LM-13B-v0.2-GPTQ/tree/gptq-8bit-128g-actorder_True) | 8 | 128 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 13.65 GB | No | 8-bit, with group size 128g for higher inference quality and with Act Order for even higher accuracy. |
| [gptq-8bit-32g-actorder_True](https://huggingface.co/TheBloke/Xwin-LM-13B-v0.2-GPTQ/tree/gptq-8bit-32g-actorder_True) | 8 | 32 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 14.55 GB | No | 8-bit, with group size 32g and Act Order for maximum inference quality. |
| [gptq-4bit-64g-actorder_True](https://huggingface.co/TheBloke/Xwin-LM-13B-v0.2-GPTQ/tree/gptq-4bit-64g-actorder_True) | 4 | 64 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 7.51 GB | Yes | 4-bit, with Act Order and group size 64g. Uses less VRAM than 32g, but with slightly lower accuracy. |
<!-- README_GPTQ.md-provided-files end -->
<!-- README_GPTQ.md-download-from-branches start -->
## How to download, including from branches
### In text-generation-webui
To download from the `main` branch, enter `TheBloke/Xwin-LM-13B-v0.2-GPTQ` in the "Download model" box.
To download from another branch, add `:branchname` to the end of the download name, eg `TheBloke/Xwin-LM-13B-v0.2-GPTQ:gptq-4bit-32g-actorder_True`
### From the command line
I recommend using the `huggingface-hub` Python library:
```shell
pip3 install huggingface-hub
```
To download the `main` branch to a folder called `Xwin-LM-13B-v0.2-GPTQ`:
```shell
mkdir Xwin-LM-13B-v0.2-GPTQ
huggingface-cli download TheBloke/Xwin-LM-13B-v0.2-GPTQ --local-dir Xwin-LM-13B-v0.2-GPTQ --local-dir-use-symlinks False
```
To download from a different branch, add the `--revision` parameter:
```shell
mkdir Xwin-LM-13B-v0.2-GPTQ
huggingface-cli download TheBloke/Xwin-LM-13B-v0.2-GPTQ --revision gptq-4bit-32g-actorder_True --local-dir Xwin-LM-13B-v0.2-GPTQ --local-dir-use-symlinks False
```
<details>
<summary>More advanced huggingface-cli download usage</summary>
If you remove the `--local-dir-use-symlinks False` parameter, the files will instead be stored in the central Huggingface cache directory (default location on Linux is: `~/.cache/huggingface`), and symlinks will be added to the specified `--local-dir`, pointing to their real location in the cache. This allows for interrupted downloads to be resumed, and allows you to quickly clone the repo to multiple places on disk without triggering a download again. The downside, and the reason why I don't list that as the default option, is that the files are then hidden away in a cache folder and it's harder to know where your disk space is being used, and to clear it up if/when you want to remove a download model.
The cache location can be changed with the `HF_HOME` environment variable, and/or the `--cache-dir` parameter to `huggingface-cli`.
For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
```shell
pip3 install hf_transfer
```
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
```shell
mkdir Xwin-LM-13B-v0.2-GPTQ
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/Xwin-LM-13B-v0.2-GPTQ --local-dir Xwin-LM-13B-v0.2-GPTQ --local-dir-use-symlinks False
```
Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
</details>
### With `git` (**not** recommended)
To clone a specific branch with `git`, use a command like this:
```shell
git clone --single-branch --branch gptq-4bit-32g-actorder_True https://huggingface.co/TheBloke/Xwin-LM-13B-v0.2-GPTQ
```
Note that using Git with HF repos is strongly discouraged. It will be much slower than using `huggingface-hub`, and will use twice as much disk space as it has to store the model files twice (it stores every byte both in the intended target folder, and again in the `.git` folder as a blob.)
<!-- README_GPTQ.md-download-from-branches end -->
<!-- README_GPTQ.md-text-generation-webui start -->
## How to easily download and use this model in [text-generation-webui](https://github.com/oobabooga/text-generation-webui).
Please make sure you're using the latest version of [text-generation-webui](https://github.com/oobabooga/text-generation-webui).
It is strongly recommended to use the text-generation-webui one-click-installers unless you're sure you know how to make a manual install.
1. Click the **Model tab**.
2. Under **Download custom model or LoRA**, enter `TheBloke/Xwin-LM-13B-v0.2-GPTQ`.
- To download from a specific branch, enter for example `TheBloke/Xwin-LM-13B-v0.2-GPTQ:gptq-4bit-32g-actorder_True`
- see Provided Files above for the list of branches for each option.
3. Click **Download**.
4. The model will start downloading. Once it's finished it will say "Done".
5. In the top left, click the refresh icon next to **Model**.
6. In the **Model** dropdown, choose the model you just downloaded: `Xwin-LM-13B-v0.2-GPTQ`
7. The model will automatically load, and is now ready for use!
8. If you want any custom settings, set them and then click **Save settings for this model** followed by **Reload the Model** in the top right.
* Note that you do not need to and should not set manual GPTQ parameters any more. These are set automatically from the file `quantize_config.json`.
9. Once you're ready, click the **Text Generation tab** and enter a prompt to get started!
<!-- README_GPTQ.md-text-generation-webui end -->
<!-- README_GPTQ.md-use-from-tgi start -->
## Serving this model from Text Generation Inference (TGI)
It's recommended to use TGI version 1.1.0 or later. The official Docker container is: `ghcr.io/huggingface/text-generation-inference:1.1.0`
Example Docker parameters:
```shell
--model-id TheBloke/Xwin-LM-13B-v0.2-GPTQ --port 3000 --quantize awq --max-input-length 3696 --max-total-tokens 4096 --max-batch-prefill-tokens 4096
```
Example Python code for interfacing with TGI (requires huggingface-hub 0.17.0 or later):
```shell
pip3 install huggingface-hub
```
```python
from huggingface_hub import InferenceClient
endpoint_url = "https://your-endpoint-url-here"
prompt = "Tell me about AI"
prompt_template=f'''A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: {prompt} ASSISTANT:
'''
client = InferenceClient(endpoint_url)
response = client.text_generation(prompt,
max_new_tokens=128,
do_sample=True,
temperature=0.7,
top_p=0.95,
top_k=40,
repetition_penalty=1.1)
print(f"Model output: {response}")
```
<!-- README_GPTQ.md-use-from-tgi end -->
<!-- README_GPTQ.md-use-from-python start -->
## How to use this GPTQ model from Python code
### Install the necessary packages
Requires: Transformers 4.33.0 or later, Optimum 1.12.0 or later, and AutoGPTQ 0.4.2 or later.
```shell
pip3 install transformers optimum
pip3 install auto-gptq --extra-index-url https://huggingface.github.io/autogptq-index/whl/cu118/ # Use cu117 if on CUDA 11.7
```
If you have problems installing AutoGPTQ using the pre-built wheels, install it from source instead:
```shell
pip3 uninstall -y auto-gptq
git clone https://github.com/PanQiWei/AutoGPTQ
cd AutoGPTQ
git checkout v0.4.2
pip3 install .
```
### You can then use the following code
```python
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
model_name_or_path = "TheBloke/Xwin-LM-13B-v0.2-GPTQ"
# To use a different branch, change revision
# For example: revision="gptq-4bit-32g-actorder_True"
model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
device_map="auto",
trust_remote_code=False,
revision="main")
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
prompt = "Tell me about AI"
prompt_template=f'''A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: {prompt} ASSISTANT:
'''
print("\n\n*** Generate:")
input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda()
output = model.generate(inputs=input_ids, temperature=0.7, do_sample=True, top_p=0.95, top_k=40, max_new_tokens=512)
print(tokenizer.decode(output[0]))
# Inference can also be done using transformers' pipeline
print("*** Pipeline:")
pipe = pipeline(
"text-generation",
model=model,
tokenizer=tokenizer,
max_new_tokens=512,
do_sample=True,
temperature=0.7,
top_p=0.95,
top_k=40,
repetition_penalty=1.1
)
print(pipe(prompt_template)[0]['generated_text'])
```
<!-- README_GPTQ.md-use-from-python end -->
<!-- README_GPTQ.md-compatibility start -->
## Compatibility
The files provided are tested to work with AutoGPTQ, both via Transformers and using AutoGPTQ directly. They should also work with [Occ4m's GPTQ-for-LLaMa fork](https://github.com/0cc4m/KoboldAI).
[ExLlama](https://github.com/turboderp/exllama) is compatible with Llama and Mistral models in 4-bit. Please see the Provided Files table above for per-file compatibility.
[Huggingface Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference) is compatible with all GPTQ models.
<!-- README_GPTQ.md-compatibility end -->
<!-- footer start -->
<!-- 200823 -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute
Thanks to the [chirper.ai](https://chirper.ai) team!
Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Aemon Algiz.
**Patreon special mentions**: Pierre Kircher, Stanislav Ovsiannikov, Michael Levine, Eugene Pentland, Andrey, 준교 김, Randy H, Fred von Graf, Artur Olbinski, Caitlyn Gatomon, terasurfer, Jeff Scroggin, James Bentley, Vadim, Gabriel Puliatti, Harry Royden McLaughlin, Sean Connelly, Dan Guido, Edmond Seymore, Alicia Loh, subjectnull, AzureBlack, Manuel Alberto Morcote, Thomas Belote, Lone Striker, Chris Smitley, Vitor Caleffi, Johann-Peter Hartmann, Clay Pascal, biorpg, Brandon Frisco, sidney chen, transmissions 11, Pedro Madruga, jinyuan sun, Ajan Kanaga, Emad Mostaque, Trenton Dambrowitz, Jonathan Leane, Iucharbius, usrbinkat, vamX, George Stoitzev, Luke Pendergrass, theTransient, Olakabola, Swaroop Kallakuri, Cap'n Zoog, Brandon Phillips, Michael Dempsey, Nikolai Manek, danny, Matthew Berman, Gabriel Tamborski, alfie_i, Raymond Fosdick, Tom X Nguyen, Raven Klaugh, LangChain4j, Magnesian, Illia Dulskyi, David Ziegler, Mano Prime, Luis Javier Navarrete Lozano, Erik Bjäreholt, 阿明, Nathan Dryer, Alex, Rainer Wilmers, zynix, TL, Joseph William Delisle, John Villwock, Nathan LeClaire, Willem Michiel, Joguhyik, GodLy, OG, Alps Aficionado, Jeffrey Morgan, ReadyPlayerEmma, Tiffany J. Kim, Sebastain Graf, Spencer Kim, Michael Davis, webtim, Talal Aujan, knownsqashed, John Detwiler, Imad Khwaja, Deo Leter, Jerry Meng, Elijah Stavena, Rooh Singh, Pieter, SuperWojo, Alexandros Triantafyllidis, Stephen Murray, Ai Maven, ya boyyy, Enrico Ros, Ken Nordquist, Deep Realms, Nicholas, Spiking Neurons AB, Elle, Will Dee, Jack West, RoA, Luke @flexchar, Viktor Bowallius, Derek Yates, Subspace Studios, jjj, Toran Billups, Asp the Wyvern, Fen Risland, Ilya, NimbleBox.ai, Chadd, Nitin Borwankar, Emre, Mandus, Leonard Tan, Kalila, K, Trailburnt, S_X, Cory Kujawski
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
<!-- footer end -->
# Original model card: Xwin-LM's Xwin LM 13B v0.2
<h3 align="center">
Xwin-LM: Powerful, Stable, and Reproducible LLM Alignment
</h3>
<p align="center">
<a href="https://github.com/Xwin-LM/Xwin-LM"><img src="https://img.shields.io/badge/GitHub-yellow.svg?style=social&logo=github"></a><a href="https://huggingface.co/Xwin-LM"><img src="https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Models-blue"></a>
</p>
**Step up your LLM alignment with Xwin-LM!**
Xwin-LM aims to develop and open-source alignment technologies for large language models, including supervised fine-tuning (SFT), reward models (RM), reject sampling, reinforcement learning from human feedback (RLHF), etc. Our first release, built-upon on the Llama2 base models, ranked **TOP-1** on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/). Notably, it's **the first to surpass GPT-4** on this benchmark. The project will be continuously updated.
## News
- 💥 [Oct 12, 2023] [Xwin-LM-7B-V0.2](https://huggingface.co/Xwin-LM/Xwin-LM-7B-V0.2) and [Xwin-LM-13B-V0.2](https://huggingface.co/Xwin-LM/Xwin-LM-13B-V0.2) have been released, with improved comparison data and RL training (i.e., PPO). Their winrates v.s. GPT-4 have increased significantly, reaching **59.83%** (7B model) and **70.36%** (13B model) respectively. The 70B model will be released soon.
- 💥 [Sep, 2023] We released [Xwin-LM-70B-V0.1](https://huggingface.co/Xwin-LM/Xwin-LM-70B-V0.1), which has achieved a win-rate against Davinci-003 of **95.57%** on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/) benchmark, ranking as **TOP-1** on AlpacaEval. **It was the FIRST model surpassing GPT-4** on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/). Also note its winrate v.s. GPT-4 is **60.61**.
- 🔍 [Sep, 2023] RLHF plays crucial role in the strong performance of Xwin-LM-V0.1 release!
- 💥 [Sep, 2023] We released [Xwin-LM-13B-V0.1](https://huggingface.co/Xwin-LM/Xwin-LM-13B-V0.1), which has achieved **91.76%** win-rate on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/), ranking as **top-1** among all 13B models.
- 💥 [Sep, 2023] We released [Xwin-LM-7B-V0.1](https://huggingface.co/Xwin-LM/Xwin-LM-7B-V0.1), which has achieved **87.82%** win-rate on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/), ranking as **top-1** among all 7B models.
## Model Card
| Model | Checkpoint | Report | License |
|------------|------------|-------------|------------------|
|Xwin-LM-7B-V0.2| 🤗 <a href="https://huggingface.co/Xwin-LM/Xwin-LM-7B-V0.2" target="_blank">HF Link</a> | 📃**Coming soon (Stay tuned)** | <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama 2 License|
|Xwin-LM-13B-V0.2| 🤗 <a href="https://huggingface.co/Xwin-LM/Xwin-LM-13B-V0.2" target="_blank">HF Link</a> | | <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama 2 License|
|Xwin-LM-7B-V0.1| 🤗 <a href="https://huggingface.co/Xwin-LM/Xwin-LM-7B-V0.1" target="_blank">HF Link</a> | | <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama 2 License|
|Xwin-LM-13B-V0.1| 🤗 <a href="https://huggingface.co/Xwin-LM/Xwin-LM-13B-V0.1" target="_blank">HF Link</a> | | <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama 2 License|
|Xwin-LM-70B-V0.1| 🤗 <a href="https://huggingface.co/Xwin-LM/Xwin-LM-70B-V0.1" target="_blank">HF Link</a> | | <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama 2 License|
## Benchmarks
### Xwin-LM performance on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/).
The table below displays the performance of Xwin-LM on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/), where evaluates its win-rate against Text-Davinci-003 across 805 questions. To provide a comprehensive evaluation, we present, for the first time, the win-rate against ChatGPT and GPT-4 as well. Our Xwin-LM model family establish a new state-of-the-art performance across all metrics. Notably, Xwin-LM-70B-V0.1 has eclipsed GPT-4 for the first time, achieving an impressive win-rate of **95.57%** to Text-Davinci-003 and **60.61%** to GPT-4.
| **Model** | **AlpacaEval (winrate %)** | **AlpacaEval (winrate %)** |**AlpacaEval (winrate %)** |
|----------------------------------|------------|----------|-------------|
| | **v.s. Text-Davinci-003** | **v.s. ChatGPT** | **v.s. GPT4**|
| **Xwin-LM-70B-V0.1** | **95.57** | **87.50** | **60.61** |
| GPT-4 | 95.28 | 84.66 | 50.00 |
| **Xwin-LM-13B-V0.2** | **93.22** | **87.14** | **70.36** |
| WizardLM-70B-V1.0 | 92.91 | 80.19 | 46.70 |
| Llama-2-70B-Chat | 92.66 | 81.97 | 51.19 |
| **Xwin-LM-13B-V0.1** | **91.76** | **81.79** | **55.30** |
| ChatGPT | 89.37 | 50.00 | 16.60 |
| **Xwin-LM-7B-V0.2** | **89.31** | **79.60** | **59.83** |
| WizardLM-13B-V1.2 | 89.17 | 75.75 | 41.91 |
| **Xwin-LM-7B-V0.1** | **87.35** | **76.40** | **47.57** |
| Llama-2-13B-Chat | 81.09 | 64.22 | 30.92 |
### Case study on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/)
| Prompts | GPT4 response | Xwin-LM response |
|----------------|------------|--------|
|I've put a plate on top of an apple, and take the plate from kitchen to dinning room. Where is the apple now|The apple is now in the dining room, as it was underneath the plate when you moved the plate from the kitchen to the dining room.|The apple is still in the kitchen, as you have only moved the plate. The apple is under the plate, so if you want to bring the apple to the dining room, you should either move the apple directly or put the apple on the plate and then move the plate to the dining room.|
| Answer the following question.<br> How do you say "good evening" in French. | In French, "good evening" is said as "bonsoir." | In French, "good evening" is translated to "bonsoir." This greeting is used in the evening and nighttime hours, typically after 6 p.m. It is a combination of "bon," which means "good," and "soir," which means "evening." To pronounce it, say "bone-swahr." |
### Xwin-LM performance on NLP foundation tasks.
The following table provides a comparison of Xwin-LMs with other LLMs on NLP foundation tasks in [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard).
| Model | MMLU 5-shot | ARC 25-shot | TruthfulQA 0-shot | HellaSwag 10-shot | Average |
|------------------|-------------|-------------|-------------------|-------------------|------------|
| Text-davinci-003 | 56.9 | **85.2** | 59.3 | 82.2 | 70.9 |
|Vicuna-13b 1.1 | 51.3 | 53.0 | 51.8 | 80.1 | 59.1 |
|Guanaco 30B | 57.6 | 63.7 | 50.7 | 85.1 | 64.3 |
| WizardLM-7B 1.0 | 42.7 | 51.6 | 44.7 | 77.7 | 54.2 |
| WizardLM-13B 1.0 | 52.3 | 57.2 | 50.5 | 81.0 | 60.2 |
| WizardLM-30B 1.0 | 58.8 | 62.5 | 52.4 | 83.3 | 64.2|
| Llama-2-7B-Chat | 48.3 | 52.9 | 45.6 | 78.6 | 56.4 |
| Llama-2-13B-Chat | 54.6 | 59.0 | 44.1 | 81.9 | 59.9 |
| Llama-2-70B-Chat | 63.9 | 64.6 | 52.8 | 85.9 | 66.8 |
| **Xwin-LM-7B-V0.1** | 49.7 | 56.2 | 48.1 | 79.5 | 58.4 |
| **Xwin-LM-13B-V0.1** | 56.6 | 62.4 | 45.5 | 83.0 | 61.9 |
| **Xwin-LM-70B-V0.1** | **69.6** | 70.5 | **60.1** | **87.1** | **71.8** |
| **Xwin-LM-7B-V0.2** | 50.0 | 56.4 | 49.5 | 78.9 | 58.7 |
| **Xwin-LM-13B-V0.2** | 56.6 | 61.5 | 43.8 | 82.9 | 61.2 |
## Inference
### Conversation Template
To obtain desired results, please strictly follow the conversation templates when utilizing our model for inference. Our model adopts the prompt format established by [Vicuna](https://github.com/lm-sys/FastChat) and is equipped to support **multi-turn** conversations.
```
A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: Hi! ASSISTANT: Hello.</s>USER: Who are you? ASSISTANT: I am Xwin-LM.</s>......
```
### HuggingFace Example
```python
from transformers import AutoTokenizer, AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("Xwin-LM/Xwin-LM-7B-V0.1")
tokenizer = AutoTokenizer.from_pretrained("Xwin-LM/Xwin-LM-7B-V0.1")
(
prompt := "A chat between a curious user and an artificial intelligence assistant. "
"The assistant gives helpful, detailed, and polite answers to the user's questions. "
"USER: Hello, can you help me? "
"ASSISTANT:"
)
inputs = tokenizer(prompt, return_tensors="pt")
samples = model.generate(**inputs, max_new_tokens=4096, temperature=0.7)
output = tokenizer.decode(samples[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True)
print(output)
# Of course! I'm here to help. Please feel free to ask your question or describe the issue you're having, and I'll do my best to assist you.
```
### vLLM Example
Because Xwin-LM is based on Llama2, it also offers support for rapid inference using [vLLM](https://github.com/vllm-project/vllm). Please refer to [vLLM](https://github.com/vllm-project/vllm) for detailed installation instructions.
```python
from vllm import LLM, SamplingParams
(
prompt := "A chat between a curious user and an artificial intelligence assistant. "
"The assistant gives helpful, detailed, and polite answers to the user's questions. "
"USER: Hello, can you help me? "
"ASSISTANT:"
)
sampling_params = SamplingParams(temperature=0.7, max_tokens=4096)
llm = LLM(model="Xwin-LM/Xwin-LM-7B-V0.1")
outputs = llm.generate([prompt,], sampling_params)
for output in outputs:
prompt = output.prompt
generated_text = output.outputs[0].text
print(generated_text)
```
## TODO
- [ ] Release the source code
- [ ] Release more capabilities, such as math, reasoning, and etc.
## Citation
Please consider citing our work if you use the data or code in this repo.
```
@software{xwin-lm,
title = {Xwin-LM},
author = {Xwin-LM Team},
url = {https://github.com/Xwin-LM/Xwin-LM},
version = {pre-release},
year = {2023},
month = {9},
}
```
## Acknowledgements
Thanks to [Llama 2](https://ai.meta.com/llama/), [FastChat](https://github.com/lm-sys/FastChat), [AlpacaFarm](https://github.com/tatsu-lab/alpaca_farm), and [vLLM](https://github.com/vllm-project/vllm).
|
Undi95/Xwin-LM-13B-V0.2-GGUF
|
Undi95
| 2023-10-15T01:05:58Z | 26 | 2 | null |
[
"gguf",
"endpoints_compatible",
"region:us"
] | null | 2023-10-14T21:11:41Z |
Link to the original model : [Xwin-LM/Xwin-LM-13B-V0.2](https://huggingface.co/Xwin-LM/Xwin-LM-13B-V0.2)
In waiting for TheBloke quant.
Edit: The king done it!
https://huggingface.co/TheBloke/Xwin-LM-13B-v0.2-GGUF
https://huggingface.co/TheBloke/Xwin-LM-13B-v0.2-AWQ
https://huggingface.co/TheBloke/Xwin-LM-13B-v0.2-GPTQ
|
zeerakwyne/SD-Dog-Test5
|
zeerakwyne
| 2023-10-15T01:00:26Z | 0 | 0 |
diffusers
|
[
"diffusers",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"lora",
"base_model:runwayml/stable-diffusion-v1-5",
"base_model:adapter:runwayml/stable-diffusion-v1-5",
"license:creativeml-openrail-m",
"region:us"
] |
text-to-image
| 2023-10-15T00:08:47Z |
---
license: creativeml-openrail-m
base_model: runwayml/stable-diffusion-v1-5
instance_prompt: a photo of sks dog
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- lora
inference: true
---
# LoRA DreamBooth - zeerakwyne/SD-Dog-Test5
These are LoRA adaption weights for runwayml/stable-diffusion-v1-5. The weights were trained on a photo of sks dog using [DreamBooth](https://dreambooth.github.io/). You can find some example images in the following.
LoRA for the text encoder was enabled: False.
|
alphahg/CodeLllama-7b-rust-finetune-qlora
|
alphahg
| 2023-10-15T00:50:22Z | 0 | 0 | null |
[
"generated_from_trainer",
"base_model:codellama/CodeLlama-7b-hf",
"base_model:finetune:codellama/CodeLlama-7b-hf",
"license:llama2",
"region:us"
] | null | 2023-10-15T00:10:00Z |
---
license: llama2
base_model: codellama/CodeLlama-7b-hf
tags:
- generated_from_trainer
model-index:
- name: llama2-7b-rust-finetune
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# llama2-7b-rust-finetune
This model is a fine-tuned version of [codellama/CodeLlama-7b-hf](https://huggingface.co/codellama/CodeLlama-7b-hf) on the-stack-rust-clean dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5347
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2.5e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1
- training_steps: 500
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| No log | 0.0 | 100 | 0.5443 |
| No log | 0.01 | 200 | 0.5385 |
| No log | 0.01 | 300 | 0.5362 |
| No log | 0.01 | 400 | 0.5351 |
| 0.5389 | 0.02 | 500 | 0.5347 |
### Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
|
jrick6/sks_dog
|
jrick6
| 2023-10-15T00:47:43Z | 1 | 0 |
diffusers
|
[
"diffusers",
"tensorboard",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"lora",
"base_model:runwayml/stable-diffusion-v1-5",
"base_model:adapter:runwayml/stable-diffusion-v1-5",
"license:creativeml-openrail-m",
"region:us"
] |
text-to-image
| 2023-10-15T00:45:14Z |
---
license: creativeml-openrail-m
base_model: runwayml/stable-diffusion-v1-5
instance_prompt: a photo of sks dog
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- lora
inference: true
---
# LoRA DreamBooth - jrick6/sks_dog
These are LoRA adaption weights for runwayml/stable-diffusion-v1-5. The weights were trained on a photo of sks dog using [DreamBooth](https://dreambooth.github.io/). You can find some example images in the following.
LoRA for the text encoder was enabled: True.
|
KiranKvs/codeGenie
|
KiranKvs
| 2023-10-15T00:33:01Z | 0 | 0 | null |
[
"region:us"
] | null | 2023-10-15T00:31:26Z |
# Code-Llama-GGUF-Demo
Code Llama GGUF Demo
|
bleugreen/mistral_urlmatch
|
bleugreen
| 2023-10-15T00:30:18Z | 6 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-10-14T07:09:24Z |
---
library_name: peft
---
## Prompt
```
[INST] Choose the link that is most relevant to the provided company name and topic.
Consider a link relevant if it is either from the company and relates to the topic, or if it is from a reputable source discussing both the company and the topic.
Respond with either 'A' or 'B', representing the more relevant link.
Name = {name}
Topic = {topic}
A = {link1.url}
B = {link2.url}
[/INST]
```
### Framework versions
- PEFT 0.5.0
|
bleugreen/mistral_relevant
|
bleugreen
| 2023-10-15T00:29:22Z | 0 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-10-12T23:11:52Z |
---
library_name: peft
---
## Training procedure
### Prompt
```
[INST] With no explanation, is the following text chunk relevant & useful, reply 'True' or 'False'
'''
{text}
'''
[/INST]
{correct}
```
### Framework versions
- PEFT 0.5.0
|
tkell/tracklist-artist-to-vec
|
tkell
| 2023-10-15T00:16:02Z | 0 | 0 |
pytorch
|
[
"pytorch",
"music",
"dj-sets",
"word2vec",
"license:cc-by-nc-nd-4.0",
"region:us"
] | null | 2023-10-13T18:15:02Z |
---
license: "cc-by-nc-nd-4.0"
library_name: "pytorch"
tags:
- music
- dj-sets
- word2vec
---
# Tracklist To Vec Model Card
A tiny experiment to make a "music recommender", from my own DJ set tracklists.
|
zeerakwyne/SD-Dog-Test4
|
zeerakwyne
| 2023-10-15T00:03:23Z | 0 | 0 | null |
[
"region:us"
] | null | 2023-10-15T00:01:15Z |
---
license: creativeml-openrail-m
base_model: runwayml/stable-diffusion-v1-5
instance_prompt: a photo of sks dog
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- lora
inference: true
---
# LoRA DreamBooth - zeerakwyne/SD-Dog-Test4
These are LoRA adaption weights for runwayml/stable-diffusion-v1-5. The weights were trained on a photo of sks dog using [DreamBooth](https://dreambooth.github.io/). You can find some example images in the following.
LoRA for the text encoder was enabled: False.
|
buskingsue/distilbert-base-uncased-finetuned-emotion
|
buskingsue
| 2023-10-14T23:45:41Z | 5 | 0 |
transformers
|
[
"transformers",
"pytorch",
"distilbert",
"text-classification",
"generated_from_trainer",
"dataset:emotion",
"base_model:distilbert/distilbert-base-uncased",
"base_model:finetune:distilbert/distilbert-base-uncased",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-10-14T23:34:00Z |
---
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
datasets:
- emotion
metrics:
- accuracy
- f1
model-index:
- name: distilbert-base-uncased-finetuned-emotion
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: emotion
type: emotion
config: split
split: validation
args: split
metrics:
- name: Accuracy
type: accuracy
value: 0.92
- name: F1
type: f1
value: 0.9199406554171253
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# distilbert-base-uncased-finetuned-emotion
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the emotion dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2221
- Accuracy: 0.92
- F1: 0.9199
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| 0.8424 | 1.0 | 250 | 0.3382 | 0.9015 | 0.8994 |
| 0.2553 | 2.0 | 500 | 0.2221 | 0.92 | 0.9199 |
### Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
|
adityarra07/whisper-medium-ft-GPT
|
adityarra07
| 2023-10-14T23:31:41Z | 4 | 0 |
transformers
|
[
"transformers",
"pytorch",
"whisper",
"automatic-speech-recognition",
"generated_from_trainer",
"base_model:openai/whisper-medium",
"base_model:finetune:openai/whisper-medium",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
automatic-speech-recognition
| 2023-10-14T22:39:23Z |
---
license: apache-2.0
base_model: openai/whisper-medium
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: whisper-medium-ft-GPT
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# whisper-medium-ft-GPT
This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4126
- Wer: 16.1319
- Gpt: 8.1573
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 6
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer | Gpt |
|:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|
| 1.4571 | 1.0 | 63 | 0.4337 | 33.9572 | 8.0230 |
| 0.176 | 2.0 | 126 | 0.3830 | 31.2834 | 7.9877 |
| 0.0563 | 3.0 | 189 | 0.3942 | 16.5775 | 8.1149 |
| 0.0192 | 4.0 | 252 | 0.4223 | 15.6863 | 7.9620 |
| 0.0079 | 5.0 | 315 | 0.4049 | 15.5080 | 7.6897 |
| 0.0023 | 6.0 | 378 | 0.4126 | 16.1319 | 8.1573 |
### Framework versions
- Transformers 4.33.1
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3
|
pdich2085/new-blip
|
pdich2085
| 2023-10-14T23:27:04Z | 9 | 0 |
generic
|
[
"generic",
"pytorch",
"tf",
"blip",
"image-to-text",
"image-captioning",
"endpoints-template",
"license:bsd-3-clause",
"endpoints_compatible",
"region:us"
] |
image-to-text
| 2023-10-14T17:20:05Z |
---
tags:
- image-to-text
- image-captioning
- endpoints-template
license: bsd-3-clause
library_name: generic
---
# Fork of [Salesforce/blip-image-captioning-large](https://huggingface.co/Salesforce/blip-image-captioning-large) for a `image-captioning` task on 🤗Inference endpoint.
This repository implements a `custom` task for `image-captioning` for 🤗 Inference Endpoints. The code for the customized pipeline is in the [pipeline.py](https://huggingface.co/florentgbelidji/blip_captioning/blob/main/pipeline.py).
To use deploy this model a an Inference Endpoint you have to select `Custom` as task to use the `pipeline.py` file. -> _double check if it is selected_
### expected Request payload
```json
{
"image": "/9j/4AAQSkZJRgA.....", #encoded image
"text": "a photography of a"
}
```
below is an example on how to run a request using Python and `requests`.
## Run Request
1. Use any online image.
```bash
!wget https://storage.googleapis.com/sfr-vision-language-research/BLIP/demo.jpg
```
2.run request
```python
import json
from typing import List
import requests as r
import base64
with open("/content/demo.jpg", "rb") as image_file:
encoded_string = base64.b64encode(image_file.read()).decode()
ENDPOINT_URL = ""
HF_TOKEN = ""
def query(payload):
response = requests.post(API_URL, headers=headers, json=payload)
return response.json()
output = query({
"inputs": {
"images": [encoded_string], # using the base64 encoded string
"texts": ["a photography of"] # Optional, based on your current class logic
}
})
print(output)
```
Example parameters depending on the decoding strategy:
1. Beam search
```
"parameters": {
"num_beams":5,
"max_length":20
}
```
2. Nucleus sampling
```
"parameters": {
"num_beams":1,
"max_length":20,
"do_sample": True,
"top_k":50,
"top_p":0.95
}
```
3. Contrastive search
```
"parameters": {
"penalty_alpha":0.6,
"top_k":4
"max_length":512
}
```
See [generate()](https://huggingface.co/docs/transformers/v4.25.1/en/main_classes/text_generation#transformers.GenerationMixin.generate) doc for additional detail
expected output
```python
{'captions': ['a photography of a woman and her dog on the beach']}
```
|
theminji/search
|
theminji
| 2023-10-14T22:53:43Z | 5 | 0 |
transformers
|
[
"transformers",
"tf",
"distilbert",
"text-classification",
"generated_from_keras_callback",
"base_model:distilbert/distilbert-base-uncased",
"base_model:finetune:distilbert/distilbert-base-uncased",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-10-14T22:50:14Z |
---
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_keras_callback
model-index:
- name: TheBossLevel123/searchmodel
results: []
---
<!-- This model card has been generated automatically according to the information Keras had access to. You should
probably proofread and complete it, then remove this comment. -->
# TheBossLevel123/searchmodel
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 0.5002
- Validation Loss: 0.5589
- Train Accuracy: 0.6842
- Epoch: 0
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 45, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
- training_precision: float32
### Training results
| Train Loss | Validation Loss | Train Accuracy | Epoch |
|:----------:|:---------------:|:--------------:|:-----:|
| 0.5002 | 0.5589 | 0.6842 | 0 |
### Framework versions
- Transformers 4.34.0
- TensorFlow 2.13.0
- Datasets 2.14.5
- Tokenizers 0.14.1
|
TheBloke/SauerkrautLM-7B-v1-mistral-GPTQ
|
TheBloke
| 2023-10-14T22:51:30Z | 8 | 3 |
transformers
|
[
"transformers",
"safetensors",
"mistral",
"text-generation",
"de",
"en",
"base_model:VAGOsolutions/SauerkrautLM-7b-v1-mistral",
"base_model:quantized:VAGOsolutions/SauerkrautLM-7b-v1-mistral",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"4-bit",
"gptq",
"region:us"
] |
text-generation
| 2023-10-14T22:05:50Z |
---
base_model: VAGOsolutions/SauerkrautLM-7b-v1-mistral
inference: false
language:
- de
- en
library_name: transformers
license: apache-2.0
model_creator: VAGO solutions
model_name: SauerkrautLM 7B v1 Mistral
model_type: mistral
pipeline_tag: text-generation
prompt_template: "Ein Chat zwischen einem Benutzer und einem KI-Assistenten. Der KI-Assistent\
\ gibt hilfreiche, detaillierte und h\xF6fliche Antworten. \nUser: {prompt} \nAssistant:\n"
quantized_by: TheBloke
---
<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->
# SauerkrautLM 7B v1 Mistral - GPTQ
- Model creator: [VAGO solutions](https://huggingface.co/VAGOsolutions)
- Original model: [SauerkrautLM 7B v1 Mistral](https://huggingface.co/VAGOsolutions/SauerkrautLM-7b-v1-mistral)
<!-- description start -->
## Description
This repo contains GPTQ model files for [VAGO solutions's SauerkrautLM 7B v1 Mistral](https://huggingface.co/VAGOsolutions/SauerkrautLM-7b-v1-mistral).
Multiple GPTQ parameter permutations are provided; see Provided Files below for details of the options provided, their parameters, and the software used to create them.
<!-- description end -->
<!-- repositories-available start -->
## Repositories available
* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/SauerkrautLM-7B-v1-mistral-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/SauerkrautLM-7B-v1-mistral-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/SauerkrautLM-7B-v1-mistral-GGUF)
* [VAGO solutions's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/VAGOsolutions/SauerkrautLM-7b-v1-mistral)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: Sauerkraut
```
Ein Chat zwischen einem Benutzer und einem KI-Assistenten. Der KI-Assistent gibt hilfreiche, detaillierte und höfliche Antworten.
User: {prompt}
Assistant:
```
<!-- prompt-template end -->
<!-- README_GPTQ.md-provided-files start -->
## Provided files, and GPTQ parameters
Multiple quantisation parameters are provided, to allow you to choose the best one for your hardware and requirements.
Each separate quant is in a different branch. See below for instructions on fetching from different branches.
Most GPTQ files are made with AutoGPTQ. Mistral models are currently made with Transformers.
<details>
<summary>Explanation of GPTQ parameters</summary>
- Bits: The bit size of the quantised model.
- GS: GPTQ group size. Higher numbers use less VRAM, but have lower quantisation accuracy. "None" is the lowest possible value.
- Act Order: True or False. Also known as `desc_act`. True results in better quantisation accuracy. Some GPTQ clients have had issues with models that use Act Order plus Group Size, but this is generally resolved now.
- Damp %: A GPTQ parameter that affects how samples are processed for quantisation. 0.01 is default, but 0.1 results in slightly better accuracy.
- GPTQ dataset: The calibration dataset used during quantisation. Using a dataset more appropriate to the model's training can improve quantisation accuracy. Note that the GPTQ calibration dataset is not the same as the dataset used to train the model - please refer to the original model repo for details of the training dataset(s).
- Sequence Length: The length of the dataset sequences used for quantisation. Ideally this is the same as the model sequence length. For some very long sequence models (16+K), a lower sequence length may have to be used. Note that a lower sequence length does not limit the sequence length of the quantised model. It only impacts the quantisation accuracy on longer inference sequences.
- ExLlama Compatibility: Whether this file can be loaded with ExLlama, which currently only supports Llama models in 4-bit.
</details>
| Branch | Bits | GS | Act Order | Damp % | GPTQ Dataset | Seq Len | Size | ExLlama | Desc |
| ------ | ---- | -- | --------- | ------ | ------------ | ------- | ---- | ------- | ---- |
| [main](https://huggingface.co/TheBloke/SauerkrautLM-7B-v1-mistral-GPTQ/tree/main) | 4 | 128 | Yes | 0.1 | [German Quad](https://huggingface.co/datasets/deepset/germanquad) | 4096 | 4.16 GB | Yes | 4-bit, with Act Order and group size 128g. Uses even less VRAM than 64g, but with slightly lower accuracy. |
| [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/SauerkrautLM-7B-v1-mistral-GPTQ/tree/gptq-4bit-32g-actorder_True) | 4 | 32 | Yes | 0.1 | [German Quad](https://huggingface.co/datasets/deepset/germanquad) | 4096 | 4.57 GB | Yes | 4-bit, with Act Order and group size 32g. Gives highest possible inference quality, with maximum VRAM usage. |
| [gptq-8bit--1g-actorder_True](https://huggingface.co/TheBloke/SauerkrautLM-7B-v1-mistral-GPTQ/tree/gptq-8bit--1g-actorder_True) | 8 | None | Yes | 0.1 | [German Quad](https://huggingface.co/datasets/deepset/germanquad) | 4096 | 7.52 GB | No | 8-bit, with Act Order. No group size, to lower VRAM requirements. |
| [gptq-8bit-128g-actorder_True](https://huggingface.co/TheBloke/SauerkrautLM-7B-v1-mistral-GPTQ/tree/gptq-8bit-128g-actorder_True) | 8 | 128 | Yes | 0.1 | [German Quad](https://huggingface.co/datasets/deepset/germanquad) | 4096 | 7.68 GB | No | 8-bit, with group size 128g for higher inference quality and with Act Order for even higher accuracy. |
| [gptq-8bit-32g-actorder_True](https://huggingface.co/TheBloke/SauerkrautLM-7B-v1-mistral-GPTQ/tree/gptq-8bit-32g-actorder_True) | 8 | 32 | Yes | 0.1 | [German Quad](https://huggingface.co/datasets/deepset/germanquad) | 4096 | 8.17 GB | No | 8-bit, with group size 32g and Act Order for maximum inference quality. |
| [gptq-4bit-64g-actorder_True](https://huggingface.co/TheBloke/SauerkrautLM-7B-v1-mistral-GPTQ/tree/gptq-4bit-64g-actorder_True) | 4 | 64 | Yes | 0.1 | [German Quad](https://huggingface.co/datasets/deepset/germanquad) | 4096 | 4.29 GB | Yes | 4-bit, with Act Order and group size 64g. Uses less VRAM than 32g, but with slightly lower accuracy. |
<!-- README_GPTQ.md-provided-files end -->
<!-- README_GPTQ.md-download-from-branches start -->
## How to download, including from branches
### In text-generation-webui
To download from the `main` branch, enter `TheBloke/SauerkrautLM-7B-v1-mistral-GPTQ` in the "Download model" box.
To download from another branch, add `:branchname` to the end of the download name, eg `TheBloke/SauerkrautLM-7B-v1-mistral-GPTQ:gptq-4bit-32g-actorder_True`
### From the command line
I recommend using the `huggingface-hub` Python library:
```shell
pip3 install huggingface-hub
```
To download the `main` branch to a folder called `SauerkrautLM-7B-v1-mistral-GPTQ`:
```shell
mkdir SauerkrautLM-7B-v1-mistral-GPTQ
huggingface-cli download TheBloke/SauerkrautLM-7B-v1-mistral-GPTQ --local-dir SauerkrautLM-7B-v1-mistral-GPTQ --local-dir-use-symlinks False
```
To download from a different branch, add the `--revision` parameter:
```shell
mkdir SauerkrautLM-7B-v1-mistral-GPTQ
huggingface-cli download TheBloke/SauerkrautLM-7B-v1-mistral-GPTQ --revision gptq-4bit-32g-actorder_True --local-dir SauerkrautLM-7B-v1-mistral-GPTQ --local-dir-use-symlinks False
```
<details>
<summary>More advanced huggingface-cli download usage</summary>
If you remove the `--local-dir-use-symlinks False` parameter, the files will instead be stored in the central Huggingface cache directory (default location on Linux is: `~/.cache/huggingface`), and symlinks will be added to the specified `--local-dir`, pointing to their real location in the cache. This allows for interrupted downloads to be resumed, and allows you to quickly clone the repo to multiple places on disk without triggering a download again. The downside, and the reason why I don't list that as the default option, is that the files are then hidden away in a cache folder and it's harder to know where your disk space is being used, and to clear it up if/when you want to remove a download model.
The cache location can be changed with the `HF_HOME` environment variable, and/or the `--cache-dir` parameter to `huggingface-cli`.
For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
```shell
pip3 install hf_transfer
```
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
```shell
mkdir SauerkrautLM-7B-v1-mistral-GPTQ
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/SauerkrautLM-7B-v1-mistral-GPTQ --local-dir SauerkrautLM-7B-v1-mistral-GPTQ --local-dir-use-symlinks False
```
Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
</details>
### With `git` (**not** recommended)
To clone a specific branch with `git`, use a command like this:
```shell
git clone --single-branch --branch gptq-4bit-32g-actorder_True https://huggingface.co/TheBloke/SauerkrautLM-7B-v1-mistral-GPTQ
```
Note that using Git with HF repos is strongly discouraged. It will be much slower than using `huggingface-hub`, and will use twice as much disk space as it has to store the model files twice (it stores every byte both in the intended target folder, and again in the `.git` folder as a blob.)
<!-- README_GPTQ.md-download-from-branches end -->
<!-- README_GPTQ.md-text-generation-webui start -->
## How to easily download and use this model in [text-generation-webui](https://github.com/oobabooga/text-generation-webui).
Please make sure you're using the latest version of [text-generation-webui](https://github.com/oobabooga/text-generation-webui).
It is strongly recommended to use the text-generation-webui one-click-installers unless you're sure you know how to make a manual install.
1. Click the **Model tab**.
2. Under **Download custom model or LoRA**, enter `TheBloke/SauerkrautLM-7B-v1-mistral-GPTQ`.
- To download from a specific branch, enter for example `TheBloke/SauerkrautLM-7B-v1-mistral-GPTQ:gptq-4bit-32g-actorder_True`
- see Provided Files above for the list of branches for each option.
3. Click **Download**.
4. The model will start downloading. Once it's finished it will say "Done".
5. In the top left, click the refresh icon next to **Model**.
6. In the **Model** dropdown, choose the model you just downloaded: `SauerkrautLM-7B-v1-mistral-GPTQ`
7. The model will automatically load, and is now ready for use!
8. If you want any custom settings, set them and then click **Save settings for this model** followed by **Reload the Model** in the top right.
* Note that you do not need to and should not set manual GPTQ parameters any more. These are set automatically from the file `quantize_config.json`.
9. Once you're ready, click the **Text Generation tab** and enter a prompt to get started!
<!-- README_GPTQ.md-text-generation-webui end -->
<!-- README_GPTQ.md-use-from-tgi start -->
## Serving this model from Text Generation Inference (TGI)
It's recommended to use TGI version 1.1.0 or later. The official Docker container is: `ghcr.io/huggingface/text-generation-inference:1.1.0`
Example Docker parameters:
```shell
--model-id TheBloke/SauerkrautLM-7B-v1-mistral-GPTQ --port 3000 --quantize awq --max-input-length 3696 --max-total-tokens 4096 --max-batch-prefill-tokens 4096
```
Example Python code for interfacing with TGI (requires huggingface-hub 0.17.0 or later):
```shell
pip3 install huggingface-hub
```
```python
from huggingface_hub import InferenceClient
endpoint_url = "https://your-endpoint-url-here"
prompt = "Tell me about AI"
prompt_template=f'''Ein Chat zwischen einem Benutzer und einem KI-Assistenten. Der KI-Assistent gibt hilfreiche, detaillierte und höfliche Antworten.
User: {prompt}
Assistant:
'''
client = InferenceClient(endpoint_url)
response = client.text_generation(prompt,
max_new_tokens=128,
do_sample=True,
temperature=0.7,
top_p=0.95,
top_k=40,
repetition_penalty=1.1)
print(f"Model output: {response}")
```
<!-- README_GPTQ.md-use-from-tgi end -->
<!-- README_GPTQ.md-use-from-python start -->
## How to use this GPTQ model from Python code
### Install the necessary packages
Requires: Transformers 4.33.0 or later, Optimum 1.12.0 or later, and AutoGPTQ 0.4.2 or later.
```shell
pip3 install transformers optimum
pip3 install auto-gptq --extra-index-url https://huggingface.github.io/autogptq-index/whl/cu118/ # Use cu117 if on CUDA 11.7
```
If you have problems installing AutoGPTQ using the pre-built wheels, install it from source instead:
```shell
pip3 uninstall -y auto-gptq
git clone https://github.com/PanQiWei/AutoGPTQ
cd AutoGPTQ
git checkout v0.4.2
pip3 install .
```
### You can then use the following code
```python
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
model_name_or_path = "TheBloke/SauerkrautLM-7B-v1-mistral-GPTQ"
# To use a different branch, change revision
# For example: revision="gptq-4bit-32g-actorder_True"
model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
device_map="auto",
trust_remote_code=False,
revision="main")
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
prompt = "Tell me about AI"
prompt_template=f'''Ein Chat zwischen einem Benutzer und einem KI-Assistenten. Der KI-Assistent gibt hilfreiche, detaillierte und höfliche Antworten.
User: {prompt}
Assistant:
'''
print("\n\n*** Generate:")
input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda()
output = model.generate(inputs=input_ids, temperature=0.7, do_sample=True, top_p=0.95, top_k=40, max_new_tokens=512)
print(tokenizer.decode(output[0]))
# Inference can also be done using transformers' pipeline
print("*** Pipeline:")
pipe = pipeline(
"text-generation",
model=model,
tokenizer=tokenizer,
max_new_tokens=512,
do_sample=True,
temperature=0.7,
top_p=0.95,
top_k=40,
repetition_penalty=1.1
)
print(pipe(prompt_template)[0]['generated_text'])
```
<!-- README_GPTQ.md-use-from-python end -->
<!-- README_GPTQ.md-compatibility start -->
## Compatibility
The files provided are tested to work with AutoGPTQ, both via Transformers and using AutoGPTQ directly. They should also work with [Occ4m's GPTQ-for-LLaMa fork](https://github.com/0cc4m/KoboldAI).
[ExLlama](https://github.com/turboderp/exllama) is compatible with Llama and Mistral models in 4-bit. Please see the Provided Files table above for per-file compatibility.
[Huggingface Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference) is compatible with all GPTQ models.
<!-- README_GPTQ.md-compatibility end -->
<!-- footer start -->
<!-- 200823 -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute
Thanks to the [chirper.ai](https://chirper.ai) team!
Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Aemon Algiz.
**Patreon special mentions**: Pierre Kircher, Stanislav Ovsiannikov, Michael Levine, Eugene Pentland, Andrey, 준교 김, Randy H, Fred von Graf, Artur Olbinski, Caitlyn Gatomon, terasurfer, Jeff Scroggin, James Bentley, Vadim, Gabriel Puliatti, Harry Royden McLaughlin, Sean Connelly, Dan Guido, Edmond Seymore, Alicia Loh, subjectnull, AzureBlack, Manuel Alberto Morcote, Thomas Belote, Lone Striker, Chris Smitley, Vitor Caleffi, Johann-Peter Hartmann, Clay Pascal, biorpg, Brandon Frisco, sidney chen, transmissions 11, Pedro Madruga, jinyuan sun, Ajan Kanaga, Emad Mostaque, Trenton Dambrowitz, Jonathan Leane, Iucharbius, usrbinkat, vamX, George Stoitzev, Luke Pendergrass, theTransient, Olakabola, Swaroop Kallakuri, Cap'n Zoog, Brandon Phillips, Michael Dempsey, Nikolai Manek, danny, Matthew Berman, Gabriel Tamborski, alfie_i, Raymond Fosdick, Tom X Nguyen, Raven Klaugh, LangChain4j, Magnesian, Illia Dulskyi, David Ziegler, Mano Prime, Luis Javier Navarrete Lozano, Erik Bjäreholt, 阿明, Nathan Dryer, Alex, Rainer Wilmers, zynix, TL, Joseph William Delisle, John Villwock, Nathan LeClaire, Willem Michiel, Joguhyik, GodLy, OG, Alps Aficionado, Jeffrey Morgan, ReadyPlayerEmma, Tiffany J. Kim, Sebastain Graf, Spencer Kim, Michael Davis, webtim, Talal Aujan, knownsqashed, John Detwiler, Imad Khwaja, Deo Leter, Jerry Meng, Elijah Stavena, Rooh Singh, Pieter, SuperWojo, Alexandros Triantafyllidis, Stephen Murray, Ai Maven, ya boyyy, Enrico Ros, Ken Nordquist, Deep Realms, Nicholas, Spiking Neurons AB, Elle, Will Dee, Jack West, RoA, Luke @flexchar, Viktor Bowallius, Derek Yates, Subspace Studios, jjj, Toran Billups, Asp the Wyvern, Fen Risland, Ilya, NimbleBox.ai, Chadd, Nitin Borwankar, Emre, Mandus, Leonard Tan, Kalila, K, Trailburnt, S_X, Cory Kujawski
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
<!-- footer end -->
# Original model card: VAGO solutions's SauerkrautLM 7B v1 Mistral
## VAGO solutions SauerkrautLM
Introducing SauerkrautLM-v1 - Your German Language Powerhouse!
We are thrilled to unveil our **very first release**, **SauerkrautLM-v1**. This remarkable creation marks a significant milestone as it is specifically **tailored for the German-speaking community**. In a landscape where German language models are scarce, we are proud to offer a solution that fills this void.
What sets SauerkrautLM-v1 apart is its versatility. Whether you are an individual looking to harness its capabilities for personal use or a business seeking to integrate it into your projects, our model is designed to accommodate all. It operates under the Apache 2.0 License, providing you with the freedom to explore its potential in both private and commercial applications.
Performance is at the heart of SauerkrautLM-v1. We put it to the **test using a customized version of MT-Bench for the German language**, and the results speak volumes. It currently stands as the most robust German Language Model on Hugging Face (based on german mt-bench results), showcasing its exceptional capabilities. Rest assured, this model is here to shine and set new standards. And the best thing is it comes in three different sizes (3B, 7B, 13B) to address your individual needs.
Our model's journey began with meticulous training using an **augmented dataset within the QLoRA approach**. This is just the beginning of our model series, promising even more innovative and powerful solutions in the future.
Join us on this exciting adventure as we redefine the possibilities of language modeling for the German-speaking world.
SauerkrautLM-v1 is here to empower your language-related endeavors like never before.
## All Models
| Model | HF | GPTQ | GGUF |
|-------|-------|-------|-------|
| SauerkrautLM-3b-v1 | [Link](https://huggingface.co/VAGOsolutions/SauerkrautLM-3b-v1) | soon | soon |
| SauerkrautLM-7b-v1 | [Link](https://huggingface.co/VAGOsolutions/SauerkrautLM-7b-v1) | soon | soon |
| SauerkrautLM-7b-v1-mistral | [Link](https://huggingface.co/VAGOsolutions/SauerkrautLM-7b-v1-mistral) | soon | soon |
| SauerkrautLM-13b-v1 | [Link](https://huggingface.co/VAGOsolutions/SauerkrautLM-13b-v1) | soon | soon |
## Model Details
**SauerkrautLM-7b-v1-mistral**
**Training Dataset:**
SauerkrautLM was trained with mix of German data augmentation and translated data.
We found, that only a simple translation of training data can lead to unnatural German phrasings.
Data augmentation techniques were used to grant grammatical, syntactical correctness and a more natural German wording in our training data.
**Training Procedure:**
SauerkrautLM-7b-v1-mistral was fine-tuned using QLoRA on 1 A100 80GB with Axolotl.
- **Trained by:** SauerkrautLM-v1 trained by VAGO solutions
- **Model Type:** SauerkrautLM-v1 is an auto-regressive language model based on the transformer architecture
- **Language(s):** German, English
- **License:** APACHE 2.0
- **Contact:** [Website](https://vago-solutions.de/#Kontakt) [David Golchinfar](mailto:golchinfar@vago-solutions.de)
**Prompt Template:**
```
Ein Chat zwischen einem Benutzer und einem KI-Assistenten. Der KI-Assistent gibt hilfreiche, detaillierte und höfliche Antworten.
User: {prompt}
Assistant:
```
## Evaluation
**[MT-Bench-TrueGerman](https://huggingface.co/datasets/VAGOsolutions/MT-Bench-TrueGerman)**
## MT-Bench-TrueGerman Response Example
**SauerkrautLM-7b-v1-mistral**
**Prompt**
> Stellen Sie sich vor, Sie verfassen einen Blogbeitrag, in dem Sie zwei beliebte Smartphone-Modelle vergleichen. Entwickeln Sie eine Gliederung für den Blogbeitrag, einschließlich der Hauptpunkte und Unterkapitel, um die Merkmale, die Leistung und die Benutzererfahrung der beiden Modelle effektiv zu vergleichen und gegenüberzustellen. Bitte antworten Sie in weniger als 200 Wörtern.", "Nehmen Sie Ihre vorherige Antwort und formulieren Sie sie als Limerick um.
**Antwort SauerkrautLM-7b-v1-mistral:**
```
Titel: Vergleich von Smartphones: iPhone 13 Pro Max vs. Galaxy S22 Ultra\n\nEinleitung\nIn diesem Blogbeitrag werden wir zwei beliebte Smartphone-Modelle, das iPhone 13 Pro Max und die Galaxy S22 Ultra, vergleichen. Diese beiden Geräte zeichnen sich durch innovative Merkmale, beeindruckende Leistung und eine überlegene Benutzererfahrung aus.\n\nTeil 1: Design\n- Das iPhone 13 Pro Max bietet ein modernes und elegantes Design mit einem Glas-Metallrahmen, während die Galaxy S22 Ultra ein minimalistischerer Ansatz mit einem Glas-Maske-Design verwendet.\n- Beide Geräte verfügen über eine hohe Bildschirmdichte, jedoch ist das AMOLED-Display der Galaxy S22 Ultra für eine bessere Farbtiefe und Helligkeit bekannt.\n- Die Größe der Bildschirme variiert zwischen den beiden Modellen, mit dem iPhone 13 Pro Max eine etwas kleinere 6,7 Zoll und der Galaxy S22 Ultra eine leistungsfähigere 6,5 Zoll.\n\nTeil 2: Leistung\n- Beide Geräte verfügen über hohe Leistungsmerkmale und bieten eine schnelle Leistung, aber die Entscheidungsfindung hängt von persönlichen Vorlieben und Anwendungsbereich ab.\n- Der neue A15 Bionic Chip im iPhone 13 Pro Max ist leistungsstärker als der Snapdragon 888 in der Galaxy S22 Ultra.\n- Die Akkulebenszeit variiert je nach Nutzung und Verbrauch, aber das iPhone 13 Pro Max hat im Vergleich zu seiner Vorgängerversion einen größeren Akku.\n\nTeil 3: Kamera\n- Beide Geräte bieten hochwertige Kameraeinstellungen und hochauflösende Bildqualität.\n- Der iPhone 13 Pro Max verfügt über eine 12-MP-Sucher und eine 12-MP-Ultraweitwinkelkamera, während die Galaxy S22 Ultra eine 50-MP-Primärkamera und eine 10-MP-Ultraweitwinkelkamera bietet.\n- Der Nachverfolgungsmodus der Galaxy S22 Ultra ist zudem für sich allein schneller und einfacher zu bedienen.\n\nTeil 4: Benutzererfahrung\n- Die Benutzeroberfläche des iPhone 13 Pro Max ist intuitiver und einfach zu bedienen, während die Galaxy S22 Ultra je nach Vorlieben der Nutzer eine individuelle Anpassung erfordern kann.\n- Die Nutzung von Apple-Diensten wie FaceTime und iCloud ist auf den iPhone 13 Pro Max bequemer, während die Nutzung von Samsung-Diensten auf der Galaxy S22 Ultra ein wenig komplexer sein kann.\n\nFazit\nOb du ein Fan von Apple- oder Samsung-Geräten bist, gibt es für beide Modelle in dieser Vergleichsrunde etwas, was dich begeistert. Der iPhone 13 Pro Max überzeugt mit seiner besseren Bildschirmdichte, der Galaxy S22 Ultra mit ihrer schnelleren Kamera und dem einfacheren Bedienungserlebnis. Letztendlich hängt die Wahl vom persönlichen Vorlieben und Anwendungsbereich ab.","In einer Welt, in der Smartphones wachsen und gedeihen,\nLiegt das Vergleichsspiel, wo zwei Herrschaften kämpfen.\nEin iPhone mit einem Max,\nUnd eine Galaxy, so scharf,\nMit einer Kamera, die alle fesseln wird!
```
**Prompt**
> Sie sehen ein schönes rotes Haus auf Ihrer linken Seite und ein faszinierendes Gewächshaus auf Ihrer rechten Seite, einen attraktiven beheizten rosa Ort vor sich. Also, wo ist das Weiße Haus?", "Enthält die ursprüngliche Frage Hinweise, um den Standort des Weißen Hauses eindeutig zu bestimmen?"],"reference": ["Die Antwort ist \"Washington, DC\".", "Nein.
**Antwort SauerkrautLM-7b-v1-mistral:**
```
Das Weiße Haus ist direkt in der Mitte zwischen dem roten und dem beheizten roten Ort.","Nein, die ursprüngliche Frage enthält keine direkten Hinweise, um den Standort des Weißen Hauses eindeutig zu bestimmen.
```
**Prompt**
> Betrachten Sie einen Satelliten, der sich in einer kreisförmigen Umlaufbahn um die Erde befindet. Die Geschwindigkeit des Satelliten nimmt ab. Was wird mit dem orbitalen Radius des Satelliten und seiner Umlaufdauer passieren? Bitte rechtfertigen Sie Ihre Antwort unter Verwendung physikalischer Prinzipien.", "Was sind einige Sonderfälle oder Randfälle in Ihrer Lösung? Wie gehen Sie mit ihnen um?"] ,"reference": ["Der orbitale Radius wird zunehmen und die Umlaufdauer wird zunehmen
**Antwort SauerkrautLM-7b-v1-mistral:**
```
Wenn ein Satellit sich in einer kreisförmigen Umlaufbahn um die Erde befindet, bewegt er sich mit einer konstanten Geschwindigkeit. Allerdings wird diese Geschwindigkeit im Laufe der Zeit aufgrund von Faktoren wie der Entfernung des Satelliten vom Erdmittelpunkt und der Gravitationskraft abnehmen.\n\nDurch die Abnahme der Geschwindigkeit des Satelliten verringert sich auch die Orbitalgeschwindigkeit. Gemäß dem sogenannten Kepler'schen Gesetz ändert sich die Geschwindigkeit eines Satelliten proportional zur Entfernung vom Zentrum der umlaufenden Umlaufbahn. Dadurch ändert sich auch die Umlaufdauer, da die Zeit, die der Satellit benötigt, um eine bestimmte Strecke zurückzulegen, proportional zur Geschwindigkeit und der Entfernung ist.\n\nDaher wird die Orbitalgeschwindigkeit des Satelliten aufgrund der Abnahme der Geschwindigkeit langsamer, und somit wird auch seine Umlaufdauer länger.","In meiner Lösung der Veränderung des Orbitalradius und der Umlaufdauer eines Satelliten müssen wir einige Sonderfälle und Randfälle berücksichtigen.\n\nEin Sonderfall ist zum Beispiel, wenn der Satellit in eine geostationäre Umlaufbahn um die Erde gelangen kann. In dieser Umlaufbahn befindet sich der Satellit in einer konstanten Höhenlage und scheint den Menschen aus der Erdatmosphäre ausgesetzt zu sein. Der Satellit dreht sich dabei jedoch nur um die Erde und betrachtet die Erde von der Brennkammer aus.\n\nIn diesem Fall bleibt der Orbitalradius des Satelliten konstant, da er immer eine höhere Position einnimmt und somit immer die gleiche Höhe beibehalten muss, um die Erde aufzubewahren. Die Umlaufdauer wird jedoch durch die Entfernung vom Erdmittelpunkt beeinflusst, da die Erde sich während der Umlaufzeit durch ihre Rotation weiterdreht. Da der Satellit sich immer in derselben Höhe befindet, ändert sich jedoch das Verhältnis von Umlaufzeit zu Umlaufdauer nur geringfügig.\n\nEin weiterer Sonderfall ist, wenn der Satellit in eine Polarumlaufbahn gelangen kann. In einer Polarumlaufbahn umkreist der Satellit die Erde in einer Höhe von etwa 500 Kilometern über dem Polarkreis. In dieser Umlaufbahn bleibt der Orbitalradius des Satelliten konstant, da er immer eine höhere Position einnimmt und somit immer die gleiche Höhe beibehalten muss, um die Erde aufzubewahren. Die Umlaufzeit wird jedoch je nach Abstand vom Erdmittelpunkt variieren, da die Gravitationskraft mit der Entfernung abnimmt.\n\nIm Falle der Polarumlaufbahn ändern sich die Umlaufzeit und der Orbitalradius des Satelliten aufgrund der Abnahme der Gravitationskraft. Je weiter der Satellit von der Erde entfernt ist, desto langsamer dreht er sich und desto weniger Gravitation wirkt sich auf ihn aus. Dadurch ändert sich das Verhältnis von Umlaufzeit zu Umlaufdauer und somit auch die Größe des Orbitalradii.\n\nIn den genannten Sonderfällen bleibt die Umgebung des Satelliten und seine Bewegung im Grunde unverändert. Allerdings ändert sich aufgrund der Variation von Gravitationskraft, Entfernung und Umlaufhöhe der Satellit seine Umlaufzeit und sein Orbitalradius.
```
## Disclaimer
Our models have been meticulously trained on extensive datasets. While we have made diligent efforts to thoroughly screen and eliminate any instances of coarse or inappropriate language from our data, we must inform users that despite our best efforts in data cleansing, the possibility of some such content slipping through cannot be entirely ruled out.
Furthermore, it is important to note that we have implemented filters within our models; however, we cannot always guarantee consistently appropriate behavior. Therefore, if you encounter any issues or come across inappropriate content, we kindly request that you inform us through the contact information provided.
Additionally, it is essential to understand that the licensing of these models does not constitute legal advice. We are not held responsible for the actions of third parties who utilize our models. These models may be employed for commercial purposes, and the Apache 2.0 remains applicable and is included with the model files.
## Contact
If you are interested in customized LLMs for business applications, please get in contact with us via our website or contact us at [Dr. Daryoush Vaziri](mailto:vaziri@vago-solutions.de). We are also grateful for your feedback and suggestions.
## Collaborations
We are also keenly seeking support and investment for our startup, VAGO solutions, where we continuously advance the development of robust language models designed to address a diverse range of purposes and requirements. If the prospect of collaboratively navigating future challenges excites you, we warmly invite you to reach out to us.
|
kwwww/bert-base-uncased-test_16_8551
|
kwwww
| 2023-10-14T22:47:48Z | 0 | 0 |
peft
|
[
"peft",
"pytorch",
"region:us"
] | null | 2023-10-14T05:56:46Z |
---
library_name: peft
---
## Training procedure
### Framework versions
- PEFT 0.6.0.dev0
|
pkhanna2/my_awesome_qa_model
|
pkhanna2
| 2023-10-14T22:27:50Z | 3 | 0 |
transformers
|
[
"transformers",
"pytorch",
"distilbert",
"question-answering",
"generated_from_trainer",
"base_model:distilbert/distilbert-base-uncased",
"base_model:finetune:distilbert/distilbert-base-uncased",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
question-answering
| 2023-10-14T22:25:52Z |
---
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
model-index:
- name: my_awesome_qa_model
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# my_awesome_qa_model
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 3.7909
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| No log | 1.0 | 38 | 4.4095 |
| No log | 2.0 | 76 | 3.8866 |
| No log | 3.0 | 114 | 3.7909 |
### Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
|
TheBloke/SauerkrautLM-3B-v1-GGUF
|
TheBloke
| 2023-10-14T22:03:25Z | 85 | 5 |
transformers
|
[
"transformers",
"gguf",
"llama",
"text-generation",
"de",
"en",
"base_model:VAGOsolutions/SauerkrautLM-3b-v1",
"base_model:quantized:VAGOsolutions/SauerkrautLM-3b-v1",
"license:other",
"region:us"
] |
text-generation
| 2023-10-14T21:01:32Z |
---
base_model: VAGOsolutions/SauerkrautLM-3b-v1
inference: false
language:
- de
- en
library_name: transformers
license: other
model_creator: VAGO solutions
model_name: SauerkrautLM 3B v1
model_type: llama
pipeline_tag: text-generation
prompt_template: "Ein Chat zwischen einem Benutzer und einem KI-Assistenten. Der KI-Assistent\
\ gibt hilfreiche, detaillierte und h\xF6fliche Antworten. \nUser: {prompt} \nAssistant:\n"
quantized_by: TheBloke
---
<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->
# SauerkrautLM 3B v1 - GGUF
- Model creator: [VAGO solutions](https://huggingface.co/VAGOsolutions)
- Original model: [SauerkrautLM 3B v1](https://huggingface.co/VAGOsolutions/SauerkrautLM-3b-v1)
<!-- description start -->
## Description
This repo contains GGUF format model files for [VAGO solutions's SauerkrautLM 3B v1](https://huggingface.co/VAGOsolutions/SauerkrautLM-3b-v1).
<!-- description end -->
<!-- README_GGUF.md-about-gguf start -->
### About GGUF
GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp.
Here is an incomplate list of clients and libraries that are known to support GGUF:
* [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option.
* [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.
* [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.
* [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration.
* [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection.
* [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.
* [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server.
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
* [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use.
<!-- README_GGUF.md-about-gguf end -->
<!-- repositories-available start -->
## Repositories available
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/SauerkrautLM-3B-v1-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/SauerkrautLM-3B-v1-GGUF)
* [VAGO solutions's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/VAGOsolutions/SauerkrautLM-3b-v1)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: Sauerkraut
```
Ein Chat zwischen einem Benutzer und einem KI-Assistenten. Der KI-Assistent gibt hilfreiche, detaillierte und höfliche Antworten.
User: {prompt}
Assistant:
```
<!-- prompt-template end -->
<!-- compatibility_gguf start -->
## Compatibility
These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221)
They are also compatible with many third party UIs and libraries - please see the list at the top of this README.
## Explanation of quantisation methods
<details>
<summary>Click to see details</summary>
The new methods available are:
* GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
* GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
* GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
* GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
* GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
Refer to the Provided Files table below to see what files use which methods, and how.
</details>
<!-- compatibility_gguf end -->
<!-- README_GGUF.md-provided-files start -->
## Provided files
| Name | Quant method | Bits | Size | Max RAM required | Use case |
| ---- | ---- | ---- | ---- | ---- | ----- |
| [sauerkrautlm-3b-v1.Q4_0.gguf](https://huggingface.co/TheBloke/SauerkrautLM-3B-v1-GGUF/blob/main/sauerkrautlm-3b-v1.Q4_0.gguf) | Q4_0 | 4 | 1.98 GB| 4.48 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [sauerkrautlm-3b-v1.Q4_1.gguf](https://huggingface.co/TheBloke/SauerkrautLM-3B-v1-GGUF/blob/main/sauerkrautlm-3b-v1.Q4_1.gguf) | Q4_1 | 4 | 2.19 GB| 4.69 GB | legacy; small, substantial quality loss - lprefer using Q3_K_L |
| [sauerkrautlm-3b-v1.Q5_0.gguf](https://huggingface.co/TheBloke/SauerkrautLM-3B-v1-GGUF/blob/main/sauerkrautlm-3b-v1.Q5_0.gguf) | Q5_0 | 5 | 2.40 GB| 4.90 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [sauerkrautlm-3b-v1.Q5_1.gguf](https://huggingface.co/TheBloke/SauerkrautLM-3B-v1-GGUF/blob/main/sauerkrautlm-3b-v1.Q5_1.gguf) | Q5_1 | 5 | 2.60 GB| 5.10 GB | legacy; medium, low quality loss - prefer using Q5_K_M |
| [sauerkrautlm-3b-v1.Q8_0.gguf](https://huggingface.co/TheBloke/SauerkrautLM-3B-v1-GGUF/blob/main/sauerkrautlm-3b-v1.Q8_0.gguf) | Q8_0 | 8 | 3.64 GB| 6.14 GB | very large, extremely low quality loss - not recommended |
**Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
<!-- README_GGUF.md-provided-files end -->
<!-- README_GGUF.md-how-to-download start -->
## How to download GGUF files
**Note for manual downloaders:** You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.
The following clients/libraries will automatically download models for you, providing a list of available models to choose from:
- LM Studio
- LoLLMS Web UI
- Faraday.dev
### In `text-generation-webui`
Under Download Model, you can enter the model repo: TheBloke/SauerkrautLM-3B-v1-GGUF and below it, a specific filename to download, such as: sauerkrautlm-3b-v1.Q4_K_M.gguf.
Then click Download.
### On the command line, including multiple files at once
I recommend using the `huggingface-hub` Python library:
```shell
pip3 install huggingface-hub
```
Then you can download any individual model file to the current directory, at high speed, with a command like this:
```shell
huggingface-cli download TheBloke/SauerkrautLM-3B-v1-GGUF sauerkrautlm-3b-v1.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
<details>
<summary>More advanced huggingface-cli download usage</summary>
You can also download multiple files at once with a pattern:
```shell
huggingface-cli download TheBloke/SauerkrautLM-3B-v1-GGUF --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'
```
For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
```shell
pip3 install hf_transfer
```
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
```shell
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/SauerkrautLM-3B-v1-GGUF sauerkrautlm-3b-v1.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
</details>
<!-- README_GGUF.md-how-to-download end -->
<!-- README_GGUF.md-how-to-run start -->
## Example `llama.cpp` command
Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
```shell
./main -ngl 32 -m sauerkrautlm-3b-v1.Q4_K_M.gguf --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "Ein Chat zwischen einem Benutzer und einem KI-Assistenten. Der KI-Assistent gibt hilfreiche, detaillierte und höfliche Antworten. \nUser: {prompt} \nAssistant:"
```
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
Change `-c 2048` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically.
If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)
## How to run in `text-generation-webui`
Further instructions here: [text-generation-webui/docs/llama.cpp.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/llama.cpp.md).
## How to run from Python code
You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries.
### How to load this model in Python code, using ctransformers
#### First install the package
Run one of the following commands, according to your system:
```shell
# Base ctransformers with no GPU acceleration
pip install ctransformers
# Or with CUDA GPU acceleration
pip install ctransformers[cuda]
# Or with AMD ROCm GPU acceleration (Linux only)
CT_HIPBLAS=1 pip install ctransformers --no-binary ctransformers
# Or with Metal GPU acceleration for macOS systems only
CT_METAL=1 pip install ctransformers --no-binary ctransformers
```
#### Simple ctransformers example code
```python
from ctransformers import AutoModelForCausalLM
# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
llm = AutoModelForCausalLM.from_pretrained("TheBloke/SauerkrautLM-3B-v1-GGUF", model_file="sauerkrautlm-3b-v1.Q4_K_M.gguf", model_type="llama", gpu_layers=50)
print(llm("AI is going to"))
```
## How to use with LangChain
Here are guides on using llama-cpp-python and ctransformers with LangChain:
* [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp)
* [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers)
<!-- README_GGUF.md-how-to-run end -->
<!-- footer start -->
<!-- 200823 -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute
Thanks to the [chirper.ai](https://chirper.ai) team!
Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Aemon Algiz.
**Patreon special mentions**: Pierre Kircher, Stanislav Ovsiannikov, Michael Levine, Eugene Pentland, Andrey, 준교 김, Randy H, Fred von Graf, Artur Olbinski, Caitlyn Gatomon, terasurfer, Jeff Scroggin, James Bentley, Vadim, Gabriel Puliatti, Harry Royden McLaughlin, Sean Connelly, Dan Guido, Edmond Seymore, Alicia Loh, subjectnull, AzureBlack, Manuel Alberto Morcote, Thomas Belote, Lone Striker, Chris Smitley, Vitor Caleffi, Johann-Peter Hartmann, Clay Pascal, biorpg, Brandon Frisco, sidney chen, transmissions 11, Pedro Madruga, jinyuan sun, Ajan Kanaga, Emad Mostaque, Trenton Dambrowitz, Jonathan Leane, Iucharbius, usrbinkat, vamX, George Stoitzev, Luke Pendergrass, theTransient, Olakabola, Swaroop Kallakuri, Cap'n Zoog, Brandon Phillips, Michael Dempsey, Nikolai Manek, danny, Matthew Berman, Gabriel Tamborski, alfie_i, Raymond Fosdick, Tom X Nguyen, Raven Klaugh, LangChain4j, Magnesian, Illia Dulskyi, David Ziegler, Mano Prime, Luis Javier Navarrete Lozano, Erik Bjäreholt, 阿明, Nathan Dryer, Alex, Rainer Wilmers, zynix, TL, Joseph William Delisle, John Villwock, Nathan LeClaire, Willem Michiel, Joguhyik, GodLy, OG, Alps Aficionado, Jeffrey Morgan, ReadyPlayerEmma, Tiffany J. Kim, Sebastain Graf, Spencer Kim, Michael Davis, webtim, Talal Aujan, knownsqashed, John Detwiler, Imad Khwaja, Deo Leter, Jerry Meng, Elijah Stavena, Rooh Singh, Pieter, SuperWojo, Alexandros Triantafyllidis, Stephen Murray, Ai Maven, ya boyyy, Enrico Ros, Ken Nordquist, Deep Realms, Nicholas, Spiking Neurons AB, Elle, Will Dee, Jack West, RoA, Luke @flexchar, Viktor Bowallius, Derek Yates, Subspace Studios, jjj, Toran Billups, Asp the Wyvern, Fen Risland, Ilya, NimbleBox.ai, Chadd, Nitin Borwankar, Emre, Mandus, Leonard Tan, Kalila, K, Trailburnt, S_X, Cory Kujawski
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
<!-- footer end -->
<!-- original-model-card start -->
# Original model card: VAGO solutions's SauerkrautLM 3B v1
## VAGO solutions SauerkrautLM
Introducing SauerkrautLM-v1 - Your German Language Powerhouse!
We are thrilled to unveil our **very first release**, **SauerkrautLM-v1**. This remarkable creation marks a significant milestone as it is specifically **tailored for the German-speaking community**. In a landscape where German language models are scarce, we are proud to offer a solution that fills this void.
What sets SauerkrautLM-v1 apart is its versatility. Whether you are an individual looking to harness its capabilities for personal use or a business seeking to integrate it into your projects, our model is designed to accommodate all. It operates under the LLAMA 2 License, providing you with the freedom to explore its potential in both private and commercial applications.
Performance is at the heart of SauerkrautLM-v1. We put it to the **test using a customized version of MT-Bench for the German language**, and the results speak volumes. It currently stands as the most robust German Language Model on Hugging Face (based on german mt-bench results), showcasing its exceptional capabilities. Rest assured, this model is here to shine and set new standards. And the best thing is it comes in three different sizes (3B, 7B, 13B) to address your individual needs.
Our model's journey began with meticulous training using an **augmented dataset within the QLoRA approach**. This is just the beginning of our model series, promising even more innovative and powerful solutions in the future.
Join us on this exciting adventure as we redefine the possibilities of language modeling for the German-speaking world.
SauerkrautLM-v1 is here to empower your language-related endeavors like never before.
## All Models
| Model | HF | GPTQ | GGUF |
|-------|-------|-------|-------|
| SauerkrautLM-3b-v1 | [Link](https://huggingface.co/VAGOsolutions/SauerkrautLM-3b-v1) | soon | soon |
| SauerkrautLM-7b-v1 | [Link](https://huggingface.co/VAGOsolutions/SauerkrautLM-7b-v1) | soon | soon |
| SauerkrautLM-7b-v1-mistral | [Link](https://huggingface.co/VAGOsolutions/SauerkrautLM-7b-v1-mistral) | soon | soon |
| SauerkrautLM-13b-v1 | [Link](https://huggingface.co/VAGOsolutions/SauerkrautLM-13b-v1) | soon | soon |
## Model Details
**SauerkrautLM-3b-v1**
**Training Dataset:**
SauerkrautLM was trained with mix of German data augmentation and translated data.
We found, that only a simple translation of training data can lead to unnatural German phrasings.
Data augmentation techniques were used to grant grammatical, syntactical correctness and a more natural German wording in our training data.
**Training Procedure:**
SauerkrautLM-3b-v1 was fine-tuned using QLoRA on 1 RTX 4090 24GB with Axolotl.
- **Trained by:** SauerkrautLM-v1 trained by VAGO solutions
- **Model Type:** SauerkrautLM-v1 is an auto-regressive language model based on the transformer architecture
- **Language(s):** German, English
- **License:** [LLAMA 2 COMMUNITY LICENSE AGREEMENT](https://huggingface.co/meta-llama/Llama-2-70b/raw/main/LICENSE.txt)
- **Contact:** [Website](https://vago-solutions.de/#Kontakt) [David Golchinfar](mailto:golchinfar@vago-solutions.de)
**Prompt Template:**
```
Ein Chat zwischen einem Benutzer und einem KI-Assistenten. Der KI-Assistent gibt hilfreiche, detaillierte und höfliche Antworten.
User: {prompt}
Assistant:
```
## Evaluation
**[MT-Bench-TrueGerman](https://huggingface.co/datasets/VAGOsolutions/MT-Bench-TrueGerman)**
## MT-Bench-TrueGerman Response Example
**SauertkrautLM-3b-v1**
**Prompt**
> Stellen Sie sich vor, Sie verfassen einen Blogbeitrag, in dem Sie zwei beliebte Smartphone-Modelle vergleichen. Entwickeln Sie eine Gliederung für den Blogbeitrag, einschließlich der Hauptpunkte und Unterkapitel, um die Merkmale, die Leistung und die Benutzererfahrung der beiden Modelle effektiv zu vergleichen und gegenüberzustellen. Bitte antworten Sie in weniger als 200 Wörtern.", "Nehmen Sie Ihre vorherige Antwort und formulieren Sie sie als Limerick um.
**Antwort SauerkrautLM-3b-v1:**
```
Klar, ich kann Ihnen gerne helfen! Hier sind die Hauptpunkte und Unterkapitel für Ihren Blogbeitrag zu den beiden beliebten Smartphone-Modellen:\n1. Hauptpunkte:\n- Untersuchen Sie die Leistung unterschiedlicher Smartphone-Modelle und erklären, welche sie überlegen machen.\n- Betrachten Sie die Benutzererfahrung: Welche Funktionen und App-Erweiterungen verwendet der Benutzer des jeweiligen Smartphones?\n- Überprüfen Sie die Batterieleistung: Welches Smartphone Model sorgfältig auf Batterieleistung achten kann?\n- Betrachten Sie die Verfügbarkeit für zusätzliche Ladegeräte: Welches Smartphone Model die schnellere Ladezeit ermöglicht?\n2. Unterkapitel:\n- Leistungsfaktor: Untersuchen Sie die Leistungsfähigkeit der Smartphones, indem Sie verschiedene Tests durchführen, um festzustellen, welche Modelle überlegen.\n- Benutzererfahrung: Betrachten Sie die Leistungsfähigkeit der Smartphones, indem Sie mit Benutzern aus verschiedenen Hintergrund-Nutzungsszenarien interagieren.\n- Batterielaufzeit: Untersuchen Sie die Batterielaufzeit der Smartphones, um herauszufinden, welches Modell die längere Lebensdauer bietet.\n- Zusätzliche Ladegeräte: Untersuchen Sie die Verfügbarkeit für zusätzliche Ladegeräte, indem Sie verschiedene Modelle testen, um festzustellen, welches Smartphone Modell die schnellere Ladezeit bietet.","Über den kühlen, weichen, süßen Gefühl, der während des Morgens herrscht, mögen wir uns nicht verwirren, während wir uns für den Tag entscheiden.
```
**Prompt**
> Sie sehen ein schönes rotes Haus auf Ihrer linken Seite und ein faszinierendes Gewächshaus auf Ihrer rechten Seite, einen attraktiven beheizten rosa Ort vor sich. Also, wo ist das Weiße Haus?", "Enthält die ursprüngliche Frage Hinweise, um den Standort des Weißen Hauses eindeutig zu bestimmen?"],"reference": ["Die Antwort ist \"Washington, DC\".", "Nein.
**Antwort SauerkrautLM-3b-v1:**
```
Das Weiße Haus ist auf der linken Seite des rechten Häuschens, wo sich der Gewächshaus befindet.\n\nHinweis: Der Gewächshaus ist nicht beheizt.","Ja, die ursprüngliche Frage vermittelt den Standort des Weißen Hauses eindeutig.
```
**Prompt**
> Betrachten Sie einen Satelliten, der sich in einer kreisförmigen Umlaufbahn um die Erde befindet. Die Geschwindigkeit des Satelliten nimmt ab. Was wird mit dem orbitalen Radius des Satelliten und seiner Umlaufdauer passieren? Bitte rechtfertigen Sie Ihre Antwort unter Verwendung physikalischer Prinzipien.", "Was sind einige Sonderfälle oder Randfälle in Ihrer Lösung? Wie gehen Sie mit ihnen um?"] ,"reference": ["Der orbitale Radius wird zunehmen und die Umlaufdauer wird zunehmen
**Antwort SauerkrautLM-3b-v1:**
```
Wenn der Satellit sich in einer kreisförmigen Umlaufbahn um die Erde befindet, wird sein orbitaler Radius abnehmen. Die Umlaufdauer des Satelliten kann je nach seiner Geschwindigkeit und der Schwerkraft konstant bleiben, wenn er sich nicht dauerhaft in einer kreisförmigen Umlaufbahn befindet. Wenn der Satellit sich in einer kreisförmigen Umlaufbahn befindet, wird sein orbitaler Radius nach dem Start unterschiedlich lang dauern, da er sich mit der Schwerkraft anzieht. Je nach seiner Geschwindigkeit und der Schwerkraft wird der Satellit sein orbitaler Radius ungefähr 1,5-2,2 Mal seiner Geschwindigkeit abnehmen, wenn er sich in einer kreisförmigen Umlaufbahn befindet.","Einige Sonderfälle in Ihrer Lösung sind:\n1. Zwischen zwei Schwerkraftwellen gibt es ein Schwerkraftschwank.\n2. Ein Kernschaltungskern könnte ein Kernschaltungskern sein, der sich mit einer anderen Kernschaltung kreuzt.\n3. Wenn der Kernschaltungskern sich in einem Kernschaltungskern befindet, könnte er seine eigenen Kernschaltungskern entstehen.\n4. Zwei Kernschaltungskern könnten sich in einem Kernschaltungskern befinden und die Schwerkraft auf sich verteilen, was zu einer Schwerkraftwellen führt.\n5. Ein Kernschaltungskern könnte aus mehreren Kernschaltungskernn bestehen.\n6. Wenn ein Kernschaltungskern sich in einer anderen Kernschaltungskern befindet, könnte er die Schwerkraft auf sich verteilen, was zu einer Schwerkraftwellen führt.\n7. Ein Kernschaltungskern könnte eine Schwerkraftwellen aus einer anderen Schwerkraftwellen befreien.\n8. Ein Kernschaltungskern könnte eine Schwerkraftwellen von einer anderen Schwerkraftwellen verursachen.\n\nDie Sonderfälle und Randfälle in Ihrer Lösung können je nach den spezifischen Konzepten und der Frage gelöst werden. Ebenso können Sie Sonderfälle oder Randfälle in Ihrer Lösung mit Ihren wissenschaftlichen Kenntnissen und Erfahrungen angehen
```
## Disclaimer
Our models have been meticulously trained on extensive datasets. While we have made diligent efforts to thoroughly screen and eliminate any instances of coarse or inappropriate language from our data, we must inform users that despite our best efforts in data cleansing, the possibility of some such content slipping through cannot be entirely ruled out.
Furthermore, it is important to note that we have implemented filters within our models; however, we cannot always guarantee consistently appropriate behavior. Therefore, if you encounter any issues or come across inappropriate content, we kindly request that you inform us through the contact information provided.
Additionally, it is essential to understand that the licensing of these models does not constitute legal advice. We are not held responsible for the actions of third parties who utilize our models. These models may be employed for commercial purposes, and the original Llama2 license remains applicable and is included with the model files.
## Contact
If you are interested in customized LLMs for business applications, please get in contact with us via our website or contact us at [Dr. Daryoush Vaziri](mailto:vaziri@vago-solutions.de). We are also grateful for your feedback and suggestions.
## Collaborations
We are also keenly seeking support and investment for our startup, VAGO solutions, where we continuously advance the development of robust language models designed to address a diverse range of purposes and requirements. If the prospect of collaboratively navigating future challenges excites you, we warmly invite you to reach out to us.
<!-- original-model-card end -->
|
OckerGui/videomae-base-finetuned-ASBD_Tests2
|
OckerGui
| 2023-10-14T21:51:09Z | 4 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"videomae",
"video-classification",
"generated_from_trainer",
"license:cc-by-nc-4.0",
"endpoints_compatible",
"region:us"
] |
video-classification
| 2023-10-14T20:14:17Z |
---
license: cc-by-nc-4.0
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: videomae-base-finetuned-ASBD
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# videomae-base-finetuned-ASBD
This model is a fine-tuned version of [MCG-NJU/videomae-base](https://huggingface.co/MCG-NJU/videomae-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.4053
- Accuracy: 0.0882
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 12
- eval_batch_size: 12
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- training_steps: 50
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 1.2408 | 0.98 | 49 | 1.2719 | 0.3108 |
| 1.2896 | 1.02 | 50 | 1.2724 | 0.3108 |
### Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
|
SyedAunZaidi/llama-2-7B-finetuned-dolly-lora
|
SyedAunZaidi
| 2023-10-14T21:42:20Z | 3 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-10-14T21:42:19Z |
---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: True
- load_in_4bit: False
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: fp4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float32
### Framework versions
- PEFT 0.5.0
|
galbitang/autotrain-sofa_1015-95167146296
|
galbitang
| 2023-10-14T21:38:26Z | 6 | 0 |
transformers
|
[
"transformers",
"pytorch",
"safetensors",
"vit",
"image-classification",
"autotrain",
"vision",
"dataset:galbitang/autotrain-data-sofa_1015",
"co2_eq_emissions",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
image-classification
| 2023-10-14T21:30:09Z |
---
tags:
- autotrain
- vision
- image-classification
datasets:
- galbitang/autotrain-data-sofa_1015
widget:
- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/tiger.jpg
example_title: Tiger
- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/teapot.jpg
example_title: Teapot
- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/palace.jpg
example_title: Palace
co2_eq_emissions:
emissions: 3.24838604709472
---
# Model Trained Using AutoTrain
- Problem type: Multi-class Classification
- Model ID: 95167146296
- CO2 Emissions (in grams): 3.2484
## Validation Metrics
- Loss: 0.860
- Accuracy: 0.698
- Macro F1: 0.628
- Micro F1: 0.698
- Weighted F1: 0.694
- Macro Precision: 0.646
- Micro Precision: 0.698
- Weighted Precision: 0.699
- Macro Recall: 0.625
- Micro Recall: 0.698
- Weighted Recall: 0.698
|
Amaboh/finetuning-risk-evluation-model-wc
|
Amaboh
| 2023-10-14T21:33:04Z | 3 | 0 |
transformers
|
[
"transformers",
"pytorch",
"distilbert",
"text-classification",
"generated_from_trainer",
"base_model:distilbert/distilbert-base-uncased",
"base_model:finetune:distilbert/distilbert-base-uncased",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-10-14T06:53:39Z |
---
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
model-index:
- name: finetuning-risk-evluation-model-wc
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# finetuning-risk-evluation-model-wc
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
### Training results
### Framework versions
- Transformers 4.33.0
- Pytorch 2.0.0+cpu
- Datasets 2.1.0
- Tokenizers 0.13.3
|
SalmonAI123/bert-finetuned-squad
|
SalmonAI123
| 2023-10-14T20:59:08Z | 10 | 0 |
transformers
|
[
"transformers",
"pytorch",
"bert",
"question-answering",
"generated_from_trainer",
"dataset:squad",
"base_model:google-bert/bert-base-cased",
"base_model:finetune:google-bert/bert-base-cased",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
question-answering
| 2023-10-14T18:46:49Z |
---
license: apache-2.0
base_model: bert-base-cased
tags:
- generated_from_trainer
datasets:
- squad
model-index:
- name: bert-finetuned-squad
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# bert-finetuned-squad
This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the squad dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
### Framework versions
- Transformers 4.33.0
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3
|
Lucas66Zhang/sd-class-butterflies-32
|
Lucas66Zhang
| 2023-10-14T20:53:34Z | 1 | 0 |
diffusers
|
[
"diffusers",
"safetensors",
"pytorch",
"unconditional-image-generation",
"diffusion-models-class",
"license:mit",
"diffusers:DDPMPipeline",
"region:us"
] |
unconditional-image-generation
| 2023-10-14T20:53:27Z |
---
license: mit
tags:
- pytorch
- diffusers
- unconditional-image-generation
- diffusion-models-class
---
# Model Card for Unit 1 of the [Diffusion Models Class 🧨](https://github.com/huggingface/diffusion-models-class)
This model is a diffusion model for unconditional image generation of cute 🦋.
## Usage
```python
from diffusers import DDPMPipeline
pipeline = DDPMPipeline.from_pretrained('Lucas66Zhang/sd-class-butterflies-32')
image = pipeline().images[0]
image
```
|
TheBloke/tora-70B-v1.0-GGUF
|
TheBloke
| 2023-10-14T20:36:25Z | 73 | 2 |
transformers
|
[
"transformers",
"gguf",
"llama",
"code",
"math",
"text-generation",
"en",
"dataset:gsm8k",
"dataset:competition_math",
"arxiv:2309.17452",
"base_model:llm-agents/tora-70b-v1.0",
"base_model:quantized:llm-agents/tora-70b-v1.0",
"license:llama2",
"region:us"
] |
text-generation
| 2023-10-14T20:11:17Z |
---
base_model: llm-agents/tora-70b-v1.0
datasets:
- gsm8k
- competition_math
inference: false
language:
- en
library_name: transformers
license: llama2
metrics:
- exact_match
model_creator: LLM-Agents
model_name: ToRA 70B v1.0
model_type: llama
pipeline_tag: text-generation
prompt_template: '<|user|>
{prompt}
<|assistant|>
'
quantized_by: TheBloke
tags:
- code
- math
---
<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->
# ToRA 70B v1.0 - GGUF
- Model creator: [LLM-Agents](https://huggingface.co/llm-agents)
- Original model: [ToRA 70B v1.0](https://huggingface.co/llm-agents/tora-70b-v1.0)
<!-- description start -->
## Description
This repo contains GGUF format model files for [LLM-Agents's ToRA 70B v1.0](https://huggingface.co/llm-agents/tora-70b-v1.0).
<!-- description end -->
<!-- README_GGUF.md-about-gguf start -->
### About GGUF
GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp.
Here is an incomplate list of clients and libraries that are known to support GGUF:
* [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option.
* [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.
* [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.
* [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration.
* [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection.
* [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.
* [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server.
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
* [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use.
<!-- README_GGUF.md-about-gguf end -->
<!-- repositories-available start -->
## Repositories available
* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/tora-70B-v1.0-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/tora-70B-v1.0-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/tora-70B-v1.0-GGUF)
* [LLM-Agents's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/llm-agents/tora-70b-v1.0)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: ToRA
```
<|user|>
{prompt}
<|assistant|>
```
<!-- prompt-template end -->
<!-- compatibility_gguf start -->
## Compatibility
These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221)
They are also compatible with many third party UIs and libraries - please see the list at the top of this README.
## Explanation of quantisation methods
<details>
<summary>Click to see details</summary>
The new methods available are:
* GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
* GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
* GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
* GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
* GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
Refer to the Provided Files table below to see what files use which methods, and how.
</details>
<!-- compatibility_gguf end -->
<!-- README_GGUF.md-provided-files start -->
## Provided files
| Name | Quant method | Bits | Size | Max RAM required | Use case |
| ---- | ---- | ---- | ---- | ---- | ----- |
| [tora-70b-v1.0.Q2_K.gguf](https://huggingface.co/TheBloke/tora-70B-v1.0-GGUF/blob/main/tora-70b-v1.0.Q2_K.gguf) | Q2_K | 2 | 29.28 GB| 31.78 GB | smallest, significant quality loss - not recommended for most purposes |
| [tora-70b-v1.0.Q3_K_S.gguf](https://huggingface.co/TheBloke/tora-70B-v1.0-GGUF/blob/main/tora-70b-v1.0.Q3_K_S.gguf) | Q3_K_S | 3 | 29.92 GB| 32.42 GB | very small, high quality loss |
| [tora-70b-v1.0.Q3_K_M.gguf](https://huggingface.co/TheBloke/tora-70B-v1.0-GGUF/blob/main/tora-70b-v1.0.Q3_K_M.gguf) | Q3_K_M | 3 | 33.19 GB| 35.69 GB | very small, high quality loss |
| [tora-70b-v1.0.Q3_K_L.gguf](https://huggingface.co/TheBloke/tora-70B-v1.0-GGUF/blob/main/tora-70b-v1.0.Q3_K_L.gguf) | Q3_K_L | 3 | 36.15 GB| 38.65 GB | small, substantial quality loss |
| [tora-70b-v1.0.Q4_0.gguf](https://huggingface.co/TheBloke/tora-70B-v1.0-GGUF/blob/main/tora-70b-v1.0.Q4_0.gguf) | Q4_0 | 4 | 38.87 GB| 41.37 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [tora-70b-v1.0.Q4_K_S.gguf](https://huggingface.co/TheBloke/tora-70B-v1.0-GGUF/blob/main/tora-70b-v1.0.Q4_K_S.gguf) | Q4_K_S | 4 | 39.07 GB| 41.57 GB | small, greater quality loss |
| [tora-70b-v1.0.Q4_K_M.gguf](https://huggingface.co/TheBloke/tora-70B-v1.0-GGUF/blob/main/tora-70b-v1.0.Q4_K_M.gguf) | Q4_K_M | 4 | 41.42 GB| 43.92 GB | medium, balanced quality - recommended |
| [tora-70b-v1.0.Q5_0.gguf](https://huggingface.co/TheBloke/tora-70B-v1.0-GGUF/blob/main/tora-70b-v1.0.Q5_0.gguf) | Q5_0 | 5 | 47.46 GB| 49.96 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [tora-70b-v1.0.Q5_K_S.gguf](https://huggingface.co/TheBloke/tora-70B-v1.0-GGUF/blob/main/tora-70b-v1.0.Q5_K_S.gguf) | Q5_K_S | 5 | 47.46 GB| 49.96 GB | large, low quality loss - recommended |
| [tora-70b-v1.0.Q5_K_M.gguf](https://huggingface.co/TheBloke/tora-70B-v1.0-GGUF/blob/main/tora-70b-v1.0.Q5_K_M.gguf) | Q5_K_M | 5 | 48.75 GB| 51.25 GB | large, very low quality loss - recommended |
| tora-70b-v1.0.Q6_K.gguf | Q6_K | 6 | 56.59 GB| 59.09 GB | very large, extremely low quality loss |
| tora-70b-v1.0.Q8_0.gguf | Q8_0 | 8 | 73.29 GB| 75.79 GB | very large, extremely low quality loss - not recommended |
**Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
### Q6_K and Q8_0 files are split and require joining
**Note:** HF does not support uploading files larger than 50GB. Therefore I have uploaded the Q6_K and Q8_0 files as split files.
<details>
<summary>Click for instructions regarding Q6_K and Q8_0 files</summary>
### q6_K
Please download:
* `tora-70b-v1.0.Q6_K.gguf-split-a`
* `tora-70b-v1.0.Q6_K.gguf-split-b`
### q8_0
Please download:
* `tora-70b-v1.0.Q8_0.gguf-split-a`
* `tora-70b-v1.0.Q8_0.gguf-split-b`
To join the files, do the following:
Linux and macOS:
```
cat tora-70b-v1.0.Q6_K.gguf-split-* > tora-70b-v1.0.Q6_K.gguf && rm tora-70b-v1.0.Q6_K.gguf-split-*
cat tora-70b-v1.0.Q8_0.gguf-split-* > tora-70b-v1.0.Q8_0.gguf && rm tora-70b-v1.0.Q8_0.gguf-split-*
```
Windows command line:
```
COPY /B tora-70b-v1.0.Q6_K.gguf-split-a + tora-70b-v1.0.Q6_K.gguf-split-b tora-70b-v1.0.Q6_K.gguf
del tora-70b-v1.0.Q6_K.gguf-split-a tora-70b-v1.0.Q6_K.gguf-split-b
COPY /B tora-70b-v1.0.Q8_0.gguf-split-a + tora-70b-v1.0.Q8_0.gguf-split-b tora-70b-v1.0.Q8_0.gguf
del tora-70b-v1.0.Q8_0.gguf-split-a tora-70b-v1.0.Q8_0.gguf-split-b
```
</details>
<!-- README_GGUF.md-provided-files end -->
<!-- README_GGUF.md-how-to-download start -->
## How to download GGUF files
**Note for manual downloaders:** You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.
The following clients/libraries will automatically download models for you, providing a list of available models to choose from:
- LM Studio
- LoLLMS Web UI
- Faraday.dev
### In `text-generation-webui`
Under Download Model, you can enter the model repo: TheBloke/tora-70B-v1.0-GGUF and below it, a specific filename to download, such as: tora-70b-v1.0.Q4_K_M.gguf.
Then click Download.
### On the command line, including multiple files at once
I recommend using the `huggingface-hub` Python library:
```shell
pip3 install huggingface-hub
```
Then you can download any individual model file to the current directory, at high speed, with a command like this:
```shell
huggingface-cli download TheBloke/tora-70B-v1.0-GGUF tora-70b-v1.0.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
<details>
<summary>More advanced huggingface-cli download usage</summary>
You can also download multiple files at once with a pattern:
```shell
huggingface-cli download TheBloke/tora-70B-v1.0-GGUF --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'
```
For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
```shell
pip3 install hf_transfer
```
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
```shell
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/tora-70B-v1.0-GGUF tora-70b-v1.0.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
</details>
<!-- README_GGUF.md-how-to-download end -->
<!-- README_GGUF.md-how-to-run start -->
## Example `llama.cpp` command
Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
```shell
./main -ngl 32 -m tora-70b-v1.0.Q4_K_M.gguf --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "<|user|>\n{prompt}\n<|assistant|>"
```
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
Change `-c 4096` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically.
If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)
## How to run in `text-generation-webui`
Further instructions here: [text-generation-webui/docs/llama.cpp.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/llama.cpp.md).
## How to run from Python code
You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries.
### How to load this model in Python code, using ctransformers
#### First install the package
Run one of the following commands, according to your system:
```shell
# Base ctransformers with no GPU acceleration
pip install ctransformers
# Or with CUDA GPU acceleration
pip install ctransformers[cuda]
# Or with AMD ROCm GPU acceleration (Linux only)
CT_HIPBLAS=1 pip install ctransformers --no-binary ctransformers
# Or with Metal GPU acceleration for macOS systems only
CT_METAL=1 pip install ctransformers --no-binary ctransformers
```
#### Simple ctransformers example code
```python
from ctransformers import AutoModelForCausalLM
# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
llm = AutoModelForCausalLM.from_pretrained("TheBloke/tora-70B-v1.0-GGUF", model_file="tora-70b-v1.0.Q4_K_M.gguf", model_type="llama", gpu_layers=50)
print(llm("AI is going to"))
```
## How to use with LangChain
Here are guides on using llama-cpp-python and ctransformers with LangChain:
* [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp)
* [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers)
<!-- README_GGUF.md-how-to-run end -->
<!-- footer start -->
<!-- 200823 -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute
Thanks to the [chirper.ai](https://chirper.ai) team!
Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Aemon Algiz.
**Patreon special mentions**: Pierre Kircher, Stanislav Ovsiannikov, Michael Levine, Eugene Pentland, Andrey, 준교 김, Randy H, Fred von Graf, Artur Olbinski, Caitlyn Gatomon, terasurfer, Jeff Scroggin, James Bentley, Vadim, Gabriel Puliatti, Harry Royden McLaughlin, Sean Connelly, Dan Guido, Edmond Seymore, Alicia Loh, subjectnull, AzureBlack, Manuel Alberto Morcote, Thomas Belote, Lone Striker, Chris Smitley, Vitor Caleffi, Johann-Peter Hartmann, Clay Pascal, biorpg, Brandon Frisco, sidney chen, transmissions 11, Pedro Madruga, jinyuan sun, Ajan Kanaga, Emad Mostaque, Trenton Dambrowitz, Jonathan Leane, Iucharbius, usrbinkat, vamX, George Stoitzev, Luke Pendergrass, theTransient, Olakabola, Swaroop Kallakuri, Cap'n Zoog, Brandon Phillips, Michael Dempsey, Nikolai Manek, danny, Matthew Berman, Gabriel Tamborski, alfie_i, Raymond Fosdick, Tom X Nguyen, Raven Klaugh, LangChain4j, Magnesian, Illia Dulskyi, David Ziegler, Mano Prime, Luis Javier Navarrete Lozano, Erik Bjäreholt, 阿明, Nathan Dryer, Alex, Rainer Wilmers, zynix, TL, Joseph William Delisle, John Villwock, Nathan LeClaire, Willem Michiel, Joguhyik, GodLy, OG, Alps Aficionado, Jeffrey Morgan, ReadyPlayerEmma, Tiffany J. Kim, Sebastain Graf, Spencer Kim, Michael Davis, webtim, Talal Aujan, knownsqashed, John Detwiler, Imad Khwaja, Deo Leter, Jerry Meng, Elijah Stavena, Rooh Singh, Pieter, SuperWojo, Alexandros Triantafyllidis, Stephen Murray, Ai Maven, ya boyyy, Enrico Ros, Ken Nordquist, Deep Realms, Nicholas, Spiking Neurons AB, Elle, Will Dee, Jack West, RoA, Luke @flexchar, Viktor Bowallius, Derek Yates, Subspace Studios, jjj, Toran Billups, Asp the Wyvern, Fen Risland, Ilya, NimbleBox.ai, Chadd, Nitin Borwankar, Emre, Mandus, Leonard Tan, Kalila, K, Trailburnt, S_X, Cory Kujawski
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
<!-- footer end -->
<!-- original-model-card start -->
# Original model card: LLM-Agents's ToRA 70B v1.0
<h1 align="center">
ToRA: A Tool-Integrated Reasoning Agent <br> for Mathematical Problem Solving
</h1>
<p align="center">
<a href="https://microsoft.github.io/ToRA/"><b>[🌐 Website]</b></a> •
<a href="https://arxiv.org/abs/2309.17452"><b>[📜 Paper]</b></a> •
<a href="https://huggingface.co/llm-agents"><b>[🤗 HF Models]</b></a> •
<a href="https://github.com/microsoft/ToRA"><b>[🐱 GitHub]</b></a>
<br>
<a href="https://twitter.com/zhs05232838/status/1708860992631763092"><b>[🐦 Twitter]</b></a> •
<a href="https://www.reddit.com/r/LocalLLaMA/comments/1703k6d/tora_a_toolintegrated_reasoning_agent_for/"><b>[💬 Reddit]</b></a> •
<a href="https://notes.aimodels.fyi/researchers-announce-tora-training-language-models-to-better-understand-math-using-external-tools/">[🍀 Unofficial Blog]</a>
<!-- <a href="#-quick-start">Quick Start</a> • -->
<!-- <a href="#%EF%B8%8F-citation">Citation</a> -->
</p>
<p align="center">
Repo for "<a href="https://arxiv.org/abs/2309.17452" target="_blank">ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving</a>"
</p>
## 🔥 News
- [2023/10/08] 🔥🔥🔥 All ToRA models released at [HuggingFace](https://huggingface.co/llm-agents)!!!
- [2023/09/29] ToRA paper, repo, and website released.
## 💡 Introduction
ToRA is a series of Tool-integrated Reasoning Agents designed to solve challenging mathematical reasoning problems by interacting with tools, e.g., computation libraries and symbolic solvers. ToRA series seamlessly integrate natural language reasoning with the utilization of external tools, thereby amalgamating the analytical prowess of language and the computational efficiency of external tools.
| Model | Size | GSM8k | MATH | AVG@10 math tasks<sup>†</sup> |
|---|---|---|---|---|
| GPT-4 | - | 92.0 | 42.5 | 78.3 |
| GPT-4 (PAL) | - | 94.2 | 51.8 | 86.4 |
| [ToRA-7B](https://huggingface.co/llm-agents/tora-7b-v1.0) | 7B | 68.8 | 40.1 | 62.4|
| [ToRA-Code-7B](https://huggingface.co/llm-agents/tora-code-7b-v1.0) | 7B | 72.6 | 44.6 | 66.5|
| [ToRA-13B](https://huggingface.co/llm-agents/tora-13b-v1.0) | 13B | 72.7 | 43.0 | 65.9|
| [ToRA-Code-13B](https://huggingface.co/llm-agents/tora-code-13b-v1.0) | 13B | 75.8 | 48.1 | 71.3 |
| [ToRA-Code-34B<sup>*</sup>](https://huggingface.co/llm-agents/tora-code-34b-v1.0) | 34B | 80.7 | **51.0** | 74.8 |
| [ToRA-70B](https://huggingface.co/llm-agents/tora-70b-v1.0) | 70B | **84.3** | 49.7 | **76.9** |
- <sup>*</sup>ToRA-Code-34B is currently the first and only open-source model to achieve over 50% accuracy (pass@1) on the MATH dataset, which significantly outperforms GPT-4’s CoT result (51.0 vs. 42.5), and is competitive with GPT-4 solving problems with programs. By open-sourcing our codes and models, we hope more breakthroughs will come!
- <sup>†</sup>10 math tasks include GSM8k, MATH, GSM-Hard, SVAMP, TabMWP, ASDiv, SingleEQ, SingleOP, AddSub, and MultiArith.
## ⚡️ Training
The models are trained on ToRA-Corpus 16k, which contains tool-integrated reasoning trajectories of MATH and GSM8k from GPT-4.
We use imitation learning (i.e., SFT) to fine-tune the models, and then apply our proposed *output space shaping* to improve tool-integrated reasoning behaviors. Please refer to the [paper](https://arxiv.org/pdf/2309.17452.pdf) for more details.
## 🪁 Inference & Evaluation
Please refer to ToRA's [GitHub repo](https://github.com/microsoft/ToRA) for inference, evaluation, and training code.
## ☕️ Citation
If you find this repository helpful, please consider citing our paper:
```
@misc{gou2023tora,
title={ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving},
author={Zhibin Gou and Zhihong Shao and Yeyun Gong and yelong shen and Yujiu Yang and Minlie Huang and Nan Duan and Weizhu Chen},
year={2023},
eprint={2309.17452},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
<!-- original-model-card end -->
|
TheBloke/SauerkrautLM-7B-v1-GGUF
|
TheBloke
| 2023-10-14T20:35:47Z | 688 | 4 |
transformers
|
[
"transformers",
"gguf",
"llama",
"text-generation",
"de",
"en",
"base_model:VAGOsolutions/SauerkrautLM-7b-v1",
"base_model:quantized:VAGOsolutions/SauerkrautLM-7b-v1",
"license:llama2",
"region:us"
] |
text-generation
| 2023-10-14T20:27:45Z |
---
base_model: VAGOsolutions/SauerkrautLM-7b-v1
inference: false
language:
- de
- en
library_name: transformers
license: llama2
model_creator: VAGO solutions
model_name: SauerkrautLM 7B v1
model_type: llama
pipeline_tag: text-generation
prompt_template: "Ein Chat zwischen einem Benutzer und einem KI-Assistenten. Der KI-Assistent\
\ gibt hilfreiche, detaillierte und h\xF6fliche Antworten. \nUser: {prompt} \nAssistant:\n"
quantized_by: TheBloke
---
<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->
# SauerkrautLM 7B v1 - GGUF
- Model creator: [VAGO solutions](https://huggingface.co/VAGOsolutions)
- Original model: [SauerkrautLM 7B v1](https://huggingface.co/VAGOsolutions/SauerkrautLM-7b-v1)
<!-- description start -->
## Description
This repo contains GGUF format model files for [VAGO solutions's SauerkrautLM 7B v1](https://huggingface.co/VAGOsolutions/SauerkrautLM-7b-v1).
<!-- description end -->
<!-- README_GGUF.md-about-gguf start -->
### About GGUF
GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp.
Here is an incomplate list of clients and libraries that are known to support GGUF:
* [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option.
* [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.
* [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.
* [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration.
* [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection.
* [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.
* [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server.
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
* [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use.
<!-- README_GGUF.md-about-gguf end -->
<!-- repositories-available start -->
## Repositories available
* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/SauerkrautLM-7B-v1-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/SauerkrautLM-7B-v1-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/SauerkrautLM-7B-v1-GGUF)
* [VAGO solutions's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/VAGOsolutions/SauerkrautLM-7b-v1)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: Sauerkraut
```
Ein Chat zwischen einem Benutzer und einem KI-Assistenten. Der KI-Assistent gibt hilfreiche, detaillierte und höfliche Antworten.
User: {prompt}
Assistant:
```
<!-- prompt-template end -->
<!-- compatibility_gguf start -->
## Compatibility
These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221)
They are also compatible with many third party UIs and libraries - please see the list at the top of this README.
## Explanation of quantisation methods
<details>
<summary>Click to see details</summary>
The new methods available are:
* GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
* GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
* GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
* GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
* GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
Refer to the Provided Files table below to see what files use which methods, and how.
</details>
<!-- compatibility_gguf end -->
<!-- README_GGUF.md-provided-files start -->
## Provided files
| Name | Quant method | Bits | Size | Max RAM required | Use case |
| ---- | ---- | ---- | ---- | ---- | ----- |
| [sauerkrautlm-7b-v1.Q2_K.gguf](https://huggingface.co/TheBloke/SauerkrautLM-7B-v1-GGUF/blob/main/sauerkrautlm-7b-v1.Q2_K.gguf) | Q2_K | 2 | 2.83 GB| 5.33 GB | smallest, significant quality loss - not recommended for most purposes |
| [sauerkrautlm-7b-v1.Q3_K_S.gguf](https://huggingface.co/TheBloke/SauerkrautLM-7B-v1-GGUF/blob/main/sauerkrautlm-7b-v1.Q3_K_S.gguf) | Q3_K_S | 3 | 2.95 GB| 5.45 GB | very small, high quality loss |
| [sauerkrautlm-7b-v1.Q3_K_M.gguf](https://huggingface.co/TheBloke/SauerkrautLM-7B-v1-GGUF/blob/main/sauerkrautlm-7b-v1.Q3_K_M.gguf) | Q3_K_M | 3 | 3.30 GB| 5.80 GB | very small, high quality loss |
| [sauerkrautlm-7b-v1.Q3_K_L.gguf](https://huggingface.co/TheBloke/SauerkrautLM-7B-v1-GGUF/blob/main/sauerkrautlm-7b-v1.Q3_K_L.gguf) | Q3_K_L | 3 | 3.60 GB| 6.10 GB | small, substantial quality loss |
| [sauerkrautlm-7b-v1.Q4_0.gguf](https://huggingface.co/TheBloke/SauerkrautLM-7B-v1-GGUF/blob/main/sauerkrautlm-7b-v1.Q4_0.gguf) | Q4_0 | 4 | 3.83 GB| 6.33 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [sauerkrautlm-7b-v1.Q4_K_S.gguf](https://huggingface.co/TheBloke/SauerkrautLM-7B-v1-GGUF/blob/main/sauerkrautlm-7b-v1.Q4_K_S.gguf) | Q4_K_S | 4 | 3.86 GB| 6.36 GB | small, greater quality loss |
| [sauerkrautlm-7b-v1.Q4_K_M.gguf](https://huggingface.co/TheBloke/SauerkrautLM-7B-v1-GGUF/blob/main/sauerkrautlm-7b-v1.Q4_K_M.gguf) | Q4_K_M | 4 | 4.08 GB| 6.58 GB | medium, balanced quality - recommended |
| [sauerkrautlm-7b-v1.Q5_0.gguf](https://huggingface.co/TheBloke/SauerkrautLM-7B-v1-GGUF/blob/main/sauerkrautlm-7b-v1.Q5_0.gguf) | Q5_0 | 5 | 4.65 GB| 7.15 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [sauerkrautlm-7b-v1.Q5_K_S.gguf](https://huggingface.co/TheBloke/SauerkrautLM-7B-v1-GGUF/blob/main/sauerkrautlm-7b-v1.Q5_K_S.gguf) | Q5_K_S | 5 | 4.65 GB| 7.15 GB | large, low quality loss - recommended |
| [sauerkrautlm-7b-v1.Q5_K_M.gguf](https://huggingface.co/TheBloke/SauerkrautLM-7B-v1-GGUF/blob/main/sauerkrautlm-7b-v1.Q5_K_M.gguf) | Q5_K_M | 5 | 4.78 GB| 7.28 GB | large, very low quality loss - recommended |
| [sauerkrautlm-7b-v1.Q6_K.gguf](https://huggingface.co/TheBloke/SauerkrautLM-7B-v1-GGUF/blob/main/sauerkrautlm-7b-v1.Q6_K.gguf) | Q6_K | 6 | 5.53 GB| 8.03 GB | very large, extremely low quality loss |
| [sauerkrautlm-7b-v1.Q8_0.gguf](https://huggingface.co/TheBloke/SauerkrautLM-7B-v1-GGUF/blob/main/sauerkrautlm-7b-v1.Q8_0.gguf) | Q8_0 | 8 | 7.16 GB| 9.66 GB | very large, extremely low quality loss - not recommended |
**Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
<!-- README_GGUF.md-provided-files end -->
<!-- README_GGUF.md-how-to-download start -->
## How to download GGUF files
**Note for manual downloaders:** You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.
The following clients/libraries will automatically download models for you, providing a list of available models to choose from:
- LM Studio
- LoLLMS Web UI
- Faraday.dev
### In `text-generation-webui`
Under Download Model, you can enter the model repo: TheBloke/SauerkrautLM-7B-v1-GGUF and below it, a specific filename to download, such as: sauerkrautlm-7b-v1.Q4_K_M.gguf.
Then click Download.
### On the command line, including multiple files at once
I recommend using the `huggingface-hub` Python library:
```shell
pip3 install huggingface-hub
```
Then you can download any individual model file to the current directory, at high speed, with a command like this:
```shell
huggingface-cli download TheBloke/SauerkrautLM-7B-v1-GGUF sauerkrautlm-7b-v1.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
<details>
<summary>More advanced huggingface-cli download usage</summary>
You can also download multiple files at once with a pattern:
```shell
huggingface-cli download TheBloke/SauerkrautLM-7B-v1-GGUF --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'
```
For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
```shell
pip3 install hf_transfer
```
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
```shell
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/SauerkrautLM-7B-v1-GGUF sauerkrautlm-7b-v1.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
</details>
<!-- README_GGUF.md-how-to-download end -->
<!-- README_GGUF.md-how-to-run start -->
## Example `llama.cpp` command
Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
```shell
./main -ngl 32 -m sauerkrautlm-7b-v1.Q4_K_M.gguf --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "Ein Chat zwischen einem Benutzer und einem KI-Assistenten. Der KI-Assistent gibt hilfreiche, detaillierte und höfliche Antworten. \nUser: {prompt} \nAssistant:"
```
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
Change `-c 4096` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically.
If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)
## How to run in `text-generation-webui`
Further instructions here: [text-generation-webui/docs/llama.cpp.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/llama.cpp.md).
## How to run from Python code
You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries.
### How to load this model in Python code, using ctransformers
#### First install the package
Run one of the following commands, according to your system:
```shell
# Base ctransformers with no GPU acceleration
pip install ctransformers
# Or with CUDA GPU acceleration
pip install ctransformers[cuda]
# Or with AMD ROCm GPU acceleration (Linux only)
CT_HIPBLAS=1 pip install ctransformers --no-binary ctransformers
# Or with Metal GPU acceleration for macOS systems only
CT_METAL=1 pip install ctransformers --no-binary ctransformers
```
#### Simple ctransformers example code
```python
from ctransformers import AutoModelForCausalLM
# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
llm = AutoModelForCausalLM.from_pretrained("TheBloke/SauerkrautLM-7B-v1-GGUF", model_file="sauerkrautlm-7b-v1.Q4_K_M.gguf", model_type="llama", gpu_layers=50)
print(llm("AI is going to"))
```
## How to use with LangChain
Here are guides on using llama-cpp-python and ctransformers with LangChain:
* [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp)
* [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers)
<!-- README_GGUF.md-how-to-run end -->
<!-- footer start -->
<!-- 200823 -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute
Thanks to the [chirper.ai](https://chirper.ai) team!
Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Aemon Algiz.
**Patreon special mentions**: Pierre Kircher, Stanislav Ovsiannikov, Michael Levine, Eugene Pentland, Andrey, 준교 김, Randy H, Fred von Graf, Artur Olbinski, Caitlyn Gatomon, terasurfer, Jeff Scroggin, James Bentley, Vadim, Gabriel Puliatti, Harry Royden McLaughlin, Sean Connelly, Dan Guido, Edmond Seymore, Alicia Loh, subjectnull, AzureBlack, Manuel Alberto Morcote, Thomas Belote, Lone Striker, Chris Smitley, Vitor Caleffi, Johann-Peter Hartmann, Clay Pascal, biorpg, Brandon Frisco, sidney chen, transmissions 11, Pedro Madruga, jinyuan sun, Ajan Kanaga, Emad Mostaque, Trenton Dambrowitz, Jonathan Leane, Iucharbius, usrbinkat, vamX, George Stoitzev, Luke Pendergrass, theTransient, Olakabola, Swaroop Kallakuri, Cap'n Zoog, Brandon Phillips, Michael Dempsey, Nikolai Manek, danny, Matthew Berman, Gabriel Tamborski, alfie_i, Raymond Fosdick, Tom X Nguyen, Raven Klaugh, LangChain4j, Magnesian, Illia Dulskyi, David Ziegler, Mano Prime, Luis Javier Navarrete Lozano, Erik Bjäreholt, 阿明, Nathan Dryer, Alex, Rainer Wilmers, zynix, TL, Joseph William Delisle, John Villwock, Nathan LeClaire, Willem Michiel, Joguhyik, GodLy, OG, Alps Aficionado, Jeffrey Morgan, ReadyPlayerEmma, Tiffany J. Kim, Sebastain Graf, Spencer Kim, Michael Davis, webtim, Talal Aujan, knownsqashed, John Detwiler, Imad Khwaja, Deo Leter, Jerry Meng, Elijah Stavena, Rooh Singh, Pieter, SuperWojo, Alexandros Triantafyllidis, Stephen Murray, Ai Maven, ya boyyy, Enrico Ros, Ken Nordquist, Deep Realms, Nicholas, Spiking Neurons AB, Elle, Will Dee, Jack West, RoA, Luke @flexchar, Viktor Bowallius, Derek Yates, Subspace Studios, jjj, Toran Billups, Asp the Wyvern, Fen Risland, Ilya, NimbleBox.ai, Chadd, Nitin Borwankar, Emre, Mandus, Leonard Tan, Kalila, K, Trailburnt, S_X, Cory Kujawski
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
<!-- footer end -->
<!-- original-model-card start -->
# Original model card: VAGO solutions's SauerkrautLM 7B v1
## VAGO solutions SauerkrautLM
Introducing SauerkrautLM-v1 - Your German Language Powerhouse!
We are thrilled to unveil our **very first release**, **SauerkrautLM-v1**. This remarkable creation marks a significant milestone as it is specifically **tailored for the German-speaking community**. In a landscape where German language models are scarce, we are proud to offer a solution that fills this void.
What sets SauerkrautLM-v1 apart is its versatility. Whether you are an individual looking to harness its capabilities for personal use or a business seeking to integrate it into your projects, our model is designed to accommodate all. It operates under the LLAMA 2 License, providing you with the freedom to explore its potential in both private and commercial applications.
Performance is at the heart of SauerkrautLM-v1. We put it to the **test using a customized version of MT-Bench for the German language**, and the results speak volumes. It currently stands as the most robust German Language Model on Hugging Face (based on german mt-bench results), showcasing its exceptional capabilities. Rest assured, this model is here to shine and set new standards. And the best thing is it comes in three different sizes (3B, 7B, 13B) to address your individual needs.
Our model's journey began with meticulous training using an **augmented dataset within the QLoRA approach**. This is just the beginning of our model series, promising even more innovative and powerful solutions in the future.
Join us on this exciting adventure as we redefine the possibilities of language modeling for the German-speaking world.
SauerkrautLM-v1 is here to empower your language-related endeavors like never before.
## All Models
| Model | HF | GPTQ | GGUF |
|-------|-------|-------|-------|
| SauerkrautLM-3b-v1 | [Link](https://huggingface.co/VAGOsolutions/SauerkrautLM-3b-v1) | soon | soon |
| SauerkrautLM-7b-v1 | [Link](https://huggingface.co/VAGOsolutions/SauerkrautLM-7b-v1) | soon | soon |
| SauerkrautLM-7b-v1-mistral | [Link](https://huggingface.co/VAGOsolutions/SauerkrautLM-7b-v1-mistral) | soon | soon |
| SauerkrautLM-13b-v1 | [Link](https://huggingface.co/VAGOsolutions/SauerkrautLM-13b-v1) | soon | soon |
## Model Details
**SauerkrautLM-7b-v1**
**Training Dataset:**
SauerkrautLM was trained with mix of German data augmentation and translated data.
We found, that only a simple translation of training data can lead to unnatural German phrasings.
Data augmentation techniques were used to grant grammatical, syntactical correctness and a more natural German wording in our training data.
**Training Procedure:**
SauerkrautLM-7b-v1 was fine-tuned using QLoRA on 1 A100 80GB with Axolotl.
- **Trained by:** SauerkrautLM-v1 trained by VAGO solutions
- **Model Type:** SauerkrautLM-v1 is an auto-regressive language model based on the transformer architecture
- **Language(s):** German, English
- **License:** [LLAMA 2 COMMUNITY LICENSE AGREEMENT](https://huggingface.co/meta-llama/Llama-2-70b/raw/main/LICENSE.txt)
- **Contact:** [Website](https://vago-solutions.de/#Kontakt) [David Golchinfar](mailto:golchinfar@vago-solutions.de)
**Prompt Template:**
```
Ein Chat zwischen einem Benutzer und einem KI-Assistenten. Der KI-Assistent gibt hilfreiche, detaillierte und höfliche Antworten.
User: {prompt}
Assistant:
```
## Evaluation
**[MT-Bench-TrueGerman](https://huggingface.co/datasets/VAGOsolutions/MT-Bench-TrueGerman)**
## MT-Bench-TrueGerman Response Example
**SauerkrautLM-7b-v1**
**Prompt**
> Stellen Sie sich vor, Sie verfassen einen Blogbeitrag, in dem Sie zwei beliebte Smartphone-Modelle vergleichen. Entwickeln Sie eine Gliederung für den Blogbeitrag, einschließlich der Hauptpunkte und Unterkapitel, um die Merkmale, die Leistung und die Benutzererfahrung der beiden Modelle effektiv zu vergleichen und gegenüberzustellen. Bitte antworten Sie in weniger als 200 Wörtern.", "Nehmen Sie Ihre vorherige Antwort und formulieren Sie sie als Limerick um.
**Antwort SauerkrautLM-7b-v1:**
```
Titel: Vergleich von Smartphones: iPhone 13 Pro Max vs. Galaxy S22 Ultra\n\nEinleitung\nIn diesem Blogbeitrag werden wir zwei beliebte Smartphone-Modelle, das iPhone 13 Pro Max und die Galaxy S22 Ultra, vergleichen. Diese beiden Geräte zeichnen sich durch innovative Merkmale, beeindruckende Leistung und eine überlegene Benutzererfahrung aus.\n\nTeil 1: Design\n- Das iPhone 13 Pro Max bietet ein modernes und elegantes Design mit einem Glas-Metallrahmen, während die Galaxy S22 Ultra ein minimalistischerer Ansatz mit einem Glas-Maske-Design verwendet.\n- Beide Geräte verfügen über eine hohe Bildschirmdichte, jedoch ist das AMOLED-Display der Galaxy S22 Ultra für eine bessere Farbtiefe und Helligkeit bekannt.\n- Die Größe der Bildschirme variiert zwischen den beiden Modellen, mit dem iPhone 13 Pro Max eine etwas kleinere 6,7 Zoll und der Galaxy S22 Ultra eine leistungsfähigere 6,5 Zoll.\n\nTeil 2: Leistung\n- Beide Geräte verfügen über hohe Leistungsmerkmale und bieten eine schnelle Leistung, aber die Entscheidungsfindung hängt von persönlichen Vorlieben und Anwendungsbereich ab.\n- Der neue A15 Bionic Chip im iPhone 13 Pro Max ist leistungsstärker als der Snapdragon 888 in der Galaxy S22 Ultra.\n- Die Akkulebenszeit variiert je nach Nutzung und Verbrauch, aber das iPhone 13 Pro Max hat im Vergleich zu seiner Vorgängerversion einen größeren Akku.\n\nTeil 3: Kamera\n- Beide Geräte bieten hochwertige Kameraeinstellungen und hochauflösende Bildqualität.\n- Der iPhone 13 Pro Max verfügt über eine 12-MP-Sucher und eine 12-MP-Ultraweitwinkelkamera, während die Galaxy S22 Ultra eine 50-MP-Primärkamera und eine 10-MP-Ultraweitwinkelkamera bietet.\n- Der Nachverfolgungsmodus der Galaxy S22 Ultra ist zudem für sich allein schneller und einfacher zu bedienen.\n\nTeil 4: Benutzererfahrung\n- Die Benutzeroberfläche des iPhone 13 Pro Max ist intuitiver und einfach zu bedienen, während die Galaxy S22 Ultra je nach Vorlieben der Nutzer eine individuelle Anpassung erfordern kann.\n- Die Nutzung von Apple-Diensten wie FaceTime und iCloud ist auf den iPhone 13 Pro Max bequemer, während die Nutzung von Samsung-Diensten auf der Galaxy S22 Ultra ein wenig komplexer sein kann.\n\nFazit\nOb du ein Fan von Apple- oder Samsung-Geräten bist, gibt es für beide Modelle in dieser Vergleichsrunde etwas, was dich begeistert. Der iPhone 13 Pro Max überzeugt mit seiner besseren Bildschirmdichte, der Galaxy S22 Ultra mit ihrer schnelleren Kamera und dem einfacheren Bedienungserlebnis. Letztendlich hängt die Wahl vom persönlichen Vorlieben und Anwendungsbereich ab.","In einer Welt, in der Smartphones wachsen und gedeihen,\nLiegt das Vergleichsspiel, wo zwei Herrschaften kämpfen.\nEin iPhone mit einem Max,\nUnd eine Galaxy, so scharf,\nMit einer Kamera, die alle fesseln wird!
```
**Prompt**
> Sie sehen ein schönes rotes Haus auf Ihrer linken Seite und ein faszinierendes Gewächshaus auf Ihrer rechten Seite, einen attraktiven beheizten rosa Ort vor sich. Also, wo ist das Weiße Haus?", "Enthält die ursprüngliche Frage Hinweise, um den Standort des Weißen Hauses eindeutig zu bestimmen?"],"reference": ["Die Antwort ist \"Washington, DC\".", "Nein.
**Antwort SauerkrautLM-7b-v1:**
```
Das Weiße Haus ist direkt in der Mitte zwischen dem roten und dem beheizten roten Ort.","Nein, die ursprüngliche Frage enthält keine direkten Hinweise, um den Standort des Weißen Hauses eindeutig zu bestimmen.
```
**Prompt**
> Betrachten Sie einen Satelliten, der sich in einer kreisförmigen Umlaufbahn um die Erde befindet. Die Geschwindigkeit des Satelliten nimmt ab. Was wird mit dem orbitalen Radius des Satelliten und seiner Umlaufdauer passieren? Bitte rechtfertigen Sie Ihre Antwort unter Verwendung physikalischer Prinzipien.", "Was sind einige Sonderfälle oder Randfälle in Ihrer Lösung? Wie gehen Sie mit ihnen um?"] ,"reference": ["Der orbitale Radius wird zunehmen und die Umlaufdauer wird zunehmen
**Antwort SauerkrautLM-7b-v1:**
```
Wenn ein Satellit sich in einer kreisförmigen Umlaufbahn um die Erde befindet, bewegt er sich mit einer konstanten Geschwindigkeit. Allerdings wird diese Geschwindigkeit im Laufe der Zeit aufgrund von Faktoren wie der Entfernung des Satelliten vom Erdmittelpunkt und der Gravitationskraft abnehmen.\n\nDurch die Abnahme der Geschwindigkeit des Satelliten verringert sich auch die Orbitalgeschwindigkeit. Gemäß dem sogenannten Kepler'schen Gesetz ändert sich die Geschwindigkeit eines Satelliten proportional zur Entfernung vom Zentrum der umlaufenden Umlaufbahn. Dadurch ändert sich auch die Umlaufdauer, da die Zeit, die der Satellit benötigt, um eine bestimmte Strecke zurückzulegen, proportional zur Geschwindigkeit und der Entfernung ist.\n\nDaher wird die Orbitalgeschwindigkeit des Satelliten aufgrund der Abnahme der Geschwindigkeit langsamer, und somit wird auch seine Umlaufdauer länger.","In meiner Lösung der Veränderung des Orbitalradius und der Umlaufdauer eines Satelliten müssen wir einige Sonderfälle und Randfälle berücksichtigen.\n\nEin Sonderfall ist zum Beispiel, wenn der Satellit in eine geostationäre Umlaufbahn um die Erde gelangen kann. In dieser Umlaufbahn befindet sich der Satellit in einer konstanten Höhenlage und scheint den Menschen aus der Erdatmosphäre ausgesetzt zu sein. Der Satellit dreht sich dabei jedoch nur um die Erde und betrachtet die Erde von der Brennkammer aus.\n\nIn diesem Fall bleibt der Orbitalradius des Satelliten konstant, da er immer eine höhere Position einnimmt und somit immer die gleiche Höhe beibehalten muss, um die Erde aufzubewahren. Die Umlaufdauer wird jedoch durch die Entfernung vom Erdmittelpunkt beeinflusst, da die Erde sich während der Umlaufzeit durch ihre Rotation weiterdreht. Da der Satellit sich immer in derselben Höhe befindet, ändert sich jedoch das Verhältnis von Umlaufzeit zu Umlaufdauer nur geringfügig.\n\nEin weiterer Sonderfall ist, wenn der Satellit in eine Polarumlaufbahn gelangen kann. In einer Polarumlaufbahn umkreist der Satellit die Erde in einer Höhe von etwa 500 Kilometern über dem Polarkreis. In dieser Umlaufbahn bleibt der Orbitalradius des Satelliten konstant, da er immer eine höhere Position einnimmt und somit immer die gleiche Höhe beibehalten muss, um die Erde aufzubewahren. Die Umlaufzeit wird jedoch je nach Abstand vom Erdmittelpunkt variieren, da die Gravitationskraft mit der Entfernung abnimmt.\n\nIm Falle der Polarumlaufbahn ändern sich die Umlaufzeit und der Orbitalradius des Satelliten aufgrund der Abnahme der Gravitationskraft. Je weiter der Satellit von der Erde entfernt ist, desto langsamer dreht er sich und desto weniger Gravitation wirkt sich auf ihn aus. Dadurch ändert sich das Verhältnis von Umlaufzeit zu Umlaufdauer und somit auch die Größe des Orbitalradii.\n\nIn den genannten Sonderfällen bleibt die Umgebung des Satelliten und seine Bewegung im Grunde unverändert. Allerdings ändert sich aufgrund der Variation von Gravitationskraft, Entfernung und Umlaufhöhe der Satellit seine Umlaufzeit und sein Orbitalradius.
```
## Disclaimer
Our models have been meticulously trained on extensive datasets. While we have made diligent efforts to thoroughly screen and eliminate any instances of coarse or inappropriate language from our data, we must inform users that despite our best efforts in data cleansing, the possibility of some such content slipping through cannot be entirely ruled out.
Furthermore, it is important to note that we have implemented filters within our models; however, we cannot always guarantee consistently appropriate behavior. Therefore, if you encounter any issues or come across inappropriate content, we kindly request that you inform us through the contact information provided.
Additionally, it is essential to understand that the licensing of these models does not constitute legal advice. We are not held responsible for the actions of third parties who utilize our models. These models may be employed for commercial purposes, and the original Llama2 license remains applicable and is included with the model files.
## Contact
If you are interested in customized LLMs for business applications, please get in contact with us via our website or contact us at [Dr. Daryoush Vaziri](mailto:vaziri@vago-solutions.de). We are also grateful for your feedback and suggestions.
## Collaborations
We are also keenly seeking support and investment for our startup, VAGO solutions, where we continuously advance the development of robust language models designed to address a diverse range of purposes and requirements. If the prospect of collaboratively navigating future challenges excites you, we warmly invite you to reach out to us.
<!-- original-model-card end -->
|
sean-xl-y/results
|
sean-xl-y
| 2023-10-14T20:31:36Z | 0 | 0 | null |
[
"generated_from_trainer",
"base_model:Qwen/Qwen-14B-Chat",
"base_model:finetune:Qwen/Qwen-14B-Chat",
"region:us"
] | null | 2023-06-24T09:33:36Z |
---
base_model: Qwen/Qwen-14B-Chat
tags:
- generated_from_trainer
model-index:
- name: results
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# results
This model is a fine-tuned version of [Qwen/Qwen-14B-Chat](https://huggingface.co/Qwen/Qwen-14B-Chat) on an unknown dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 2
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_ratio: 0.03
- training_steps: 500
### Training results
### Framework versions
- Transformers 4.34.0
- Pytorch 2.1.0+cu121
- Datasets 2.14.5
- Tokenizers 0.14.1
|
victorlxh/iKG-v1.0
|
victorlxh
| 2023-10-14T20:31:16Z | 4 | 5 |
transformers
|
[
"transformers",
"pytorch",
"llama",
"text-generation",
"arxiv:2302.13971",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-08-28T00:36:08Z |
---
license: cc-by-nc-4.0
---
# ICKG Model Card
## Model Details
ICKG (Integrated Contextual Knowledge Graph Generator) is a knowledge graph construction (KGC) task-specific instruction-following language model fine-tuned from LMSYS's Vicuna-7B, which itself is derived from Meta's LLaMA LLM.
- **Developed by**: [Xiaohui Li](https://xiaohui-victor-li.github.io/)
- **Model type**: Auto-regressive language model based on the transformer architecture.
- **License**: Non-commercial
- **Finetuned from model**: [Vicuna-7B](https://huggingface.co/lmsys/vicuna-7b-v1.3) (originally from [LLaMA](https://arxiv.org/abs/2302.13971)).
## Model Sources
- **Repository**: [https://github.com/your-github-repo](https://github.com/your-github-repo)
- **Website**: [https://xiaohui-victor-li.github.io/FinDKG/](https://xiaohui-victor-li.github.io/FinDKG/)
- **Paper**: [https://arxiv.org/abs/your-paper-id](https://arxiv.org/abs/your-paper-id)
## Uses
The primary use of iKG LLM is for generating knowledge graphs (KG) based on instruction-following capability with specialized prompts. It's intended for researchers, data scientists, and developers interested in natural language processing, and knowledge graph construction.
## How to Get Started with the Model
- **Python Code**: [https://github.com/your-github-repo/tree/main#api](https://github.com/your-github-repo/tree/main#api)
- **Command line interface of FastChat**: [https://github.com/your-github-repo#ikg-weights](https://github.com/your-github-repo#ikg-weights)
## Training Details
iKG is fine-tuned from Vicuna-7B using ~3K instruction-following demonstrations including KG construction input document and extracted KG triplets as response output. iKG is thus learnt to extract list of KG triplets from given text document via prompt engineering. For more in-depth training details, refer to the "Generative Knowledge Graph Construction with Fine-tuned LLM" section of [the accompanying paper](https://arxiv.org/abs/your-paper-id).
- **Prompt Template**: The entities and relationship can be customized for specific tasks. `<input_text>` is the document text to replace.
```
From the provided document labeled as INPUT_TEXT, your task is to extract structured information from it in the form of triplet for constructing a knowledge graph. Each tuple should be in the form of ('h', 'type', 'r', 'o', 'type'), where 'h' stands for the head entity, 'r' for the relationship, and 'o' for the tail entity. The 'type' denotes the category of the corresponding entity. Do NOT include redundant triplets, NOT include triplets with relationship that occurs in the past.
Note that the entities should not be generic, numerical or temporal (like dates or percentages). Entities must be classified into the following categories:
ORG: Organizations other than government or regulatory bodies
ORG/GOV: Government bodies (e.g., "United States Government")
ORG/REG: Regulatory bodies (e.g., "Federal Reserve")
PERSON: Individuals (e.g., "Elon Musk")
GPE: Geopolitical entities such as countries, cities, etc. (e.g., "Germany")
COMP: Companies (e.g., "Google")
PRODUCT: Products or services (e.g., "iPhone")
EVENT: Specific and Material Events (e.g., "Olympic Games", "Covid-19")
SECTOR: Company sectors or industries (e.g., "Technology sector")
ECON_INDICATOR: Economic indicators (e.g., "Inflation rate"), numerical value like "10%" is not a ECON_INDICATOR;
FIN_INSTRUMENT: Financial and market instruments (e.g., "Stocks", "Global Markets")
CONCEPT: Abstract ideas or notions or themes (e.g., "Inflation", "AI", "Climate Change")
The relationships 'r' between these entities must be represented by one of the following relation verbs set: Has, Announce, Operate_In, Introduce, Produce, Control, Participates_In, Impact, Positive_Impact_On, Negative_Impact_On, Relate_To, Is_Member_Of, Invests_In, Raise, Decrease.
Remember to conduct entity disambiguation, consolidating different phrases or acronyms that refer to the same entity (for instance, "UK Central Bank", "BOE" and "Bank of England" should be unified as "Bank of England"). Simplify each entity of the triplet to be less than four words.
Your output should strictly be in a list format of triplets in the JSON list format of ('h', 'type', 'r', 'o', 'type'), where the relationship 'r' must be in the given relation verbs set above. Only output the list.
===========================================================
As an Example, consider the following news excerpt:
'Apple Inc. is set to introduce the new iPhone 14 in the technology sector this month. The product's release is likely to positively impact Apple's stock value.'
From this text, your output should be:
[('Apple Inc.', 'COMP', 'Introduce', 'iPhone 14', 'PRODUCT'),
('Apple Inc.', 'COMP', 'Operate_In', 'Technology Sector', 'SECTOR'),
('iPhone 14', 'PRODUCT', 'Positive_Impact_On', 'Apple's Stock Value', 'FIN_INSTRUMENT')]
INPUT_TEXT:
<input_text>
```
## Evaluation
iKG has undergone preliminary evaluation comparing its performance to GPT-3.5, GPT-4, and the original Vicuna-7B model. With respect to the KG construction task, it outperforms GPT-3.5 and Vicuna-7B while exhibiting comparative capability as GPT-4. iKG excels in generating instruction-based knowledge graphs with a particular emphasis on quality and adherence to format.
For a more detailed introduction, refer to [the accompanying paper](https://arxiv.org/abs/your-paper-id).
|
TheBloke/tora-13B-v1.0-GPTQ
|
TheBloke
| 2023-10-14T20:07:06Z | 21 | 0 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"code",
"math",
"en",
"dataset:gsm8k",
"dataset:competition_math",
"arxiv:2309.17452",
"base_model:llm-agents/tora-13b-v1.0",
"base_model:quantized:llm-agents/tora-13b-v1.0",
"license:llama2",
"autotrain_compatible",
"text-generation-inference",
"4-bit",
"gptq",
"region:us"
] |
text-generation
| 2023-10-14T19:30:30Z |
---
base_model: llm-agents/tora-13b-v1.0
datasets:
- gsm8k
- competition_math
inference: false
language:
- en
library_name: transformers
license: llama2
metrics:
- exact_match
model_creator: LLM-Agents
model_name: ToRA 13B v1.0
model_type: llama
pipeline_tag: text-generation
prompt_template: '<|user|>
{prompt}
<|assistant|>
'
quantized_by: TheBloke
tags:
- code
- math
---
<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->
# ToRA 13B v1.0 - GPTQ
- Model creator: [LLM-Agents](https://huggingface.co/llm-agents)
- Original model: [ToRA 13B v1.0](https://huggingface.co/llm-agents/tora-13b-v1.0)
<!-- description start -->
## Description
This repo contains GPTQ model files for [LLM-Agents's ToRA 13B v1.0](https://huggingface.co/llm-agents/tora-13b-v1.0).
Multiple GPTQ parameter permutations are provided; see Provided Files below for details of the options provided, their parameters, and the software used to create them.
<!-- description end -->
<!-- repositories-available start -->
## Repositories available
* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/tora-13B-v1.0-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/tora-13B-v1.0-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/tora-13B-v1.0-GGUF)
* [LLM-Agents's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/llm-agents/tora-13b-v1.0)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: ToRA
```
<|user|>
{prompt}
<|assistant|>
```
<!-- prompt-template end -->
<!-- README_GPTQ.md-provided-files start -->
## Provided files, and GPTQ parameters
Multiple quantisation parameters are provided, to allow you to choose the best one for your hardware and requirements.
Each separate quant is in a different branch. See below for instructions on fetching from different branches.
Most GPTQ files are made with AutoGPTQ. Mistral models are currently made with Transformers.
<details>
<summary>Explanation of GPTQ parameters</summary>
- Bits: The bit size of the quantised model.
- GS: GPTQ group size. Higher numbers use less VRAM, but have lower quantisation accuracy. "None" is the lowest possible value.
- Act Order: True or False. Also known as `desc_act`. True results in better quantisation accuracy. Some GPTQ clients have had issues with models that use Act Order plus Group Size, but this is generally resolved now.
- Damp %: A GPTQ parameter that affects how samples are processed for quantisation. 0.01 is default, but 0.1 results in slightly better accuracy.
- GPTQ dataset: The calibration dataset used during quantisation. Using a dataset more appropriate to the model's training can improve quantisation accuracy. Note that the GPTQ calibration dataset is not the same as the dataset used to train the model - please refer to the original model repo for details of the training dataset(s).
- Sequence Length: The length of the dataset sequences used for quantisation. Ideally this is the same as the model sequence length. For some very long sequence models (16+K), a lower sequence length may have to be used. Note that a lower sequence length does not limit the sequence length of the quantised model. It only impacts the quantisation accuracy on longer inference sequences.
- ExLlama Compatibility: Whether this file can be loaded with ExLlama, which currently only supports Llama models in 4-bit.
</details>
| Branch | Bits | GS | Act Order | Damp % | GPTQ Dataset | Seq Len | Size | ExLlama | Desc |
| ------ | ---- | -- | --------- | ------ | ------------ | ------- | ---- | ------- | ---- |
| [main](https://huggingface.co/TheBloke/tora-13B-v1.0-GPTQ/tree/main) | 4 | 128 | Yes | 0.1 | [CamelAI Math](https://huggingface.co/datasets/andersonbcdefg/math) | 4096 | 7.26 GB | Yes | 4-bit, with Act Order and group size 128g. Uses even less VRAM than 64g, but with slightly lower accuracy. |
| [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/tora-13B-v1.0-GPTQ/tree/gptq-4bit-32g-actorder_True) | 4 | 32 | Yes | 0.1 | [CamelAI Math](https://huggingface.co/datasets/andersonbcdefg/math) | 4096 | 8.00 GB | Yes | 4-bit, with Act Order and group size 32g. Gives highest possible inference quality, with maximum VRAM usage. |
| [gptq-8bit--1g-actorder_True](https://huggingface.co/TheBloke/tora-13B-v1.0-GPTQ/tree/gptq-8bit--1g-actorder_True) | 8 | None | Yes | 0.1 | [CamelAI Math](https://huggingface.co/datasets/andersonbcdefg/math) | 4096 | 13.36 GB | No | 8-bit, with Act Order. No group size, to lower VRAM requirements. |
| [gptq-8bit-128g-actorder_True](https://huggingface.co/TheBloke/tora-13B-v1.0-GPTQ/tree/gptq-8bit-128g-actorder_True) | 8 | 128 | Yes | 0.1 | [CamelAI Math](https://huggingface.co/datasets/andersonbcdefg/math) | 4096 | 13.65 GB | No | 8-bit, with group size 128g for higher inference quality and with Act Order for even higher accuracy. |
| [gptq-8bit-32g-actorder_True](https://huggingface.co/TheBloke/tora-13B-v1.0-GPTQ/tree/gptq-8bit-32g-actorder_True) | 8 | 32 | Yes | 0.1 | [CamelAI Math](https://huggingface.co/datasets/andersonbcdefg/math) | 4096 | 14.55 GB | No | 8-bit, with group size 32g and Act Order for maximum inference quality. |
| [gptq-4bit-64g-actorder_True](https://huggingface.co/TheBloke/tora-13B-v1.0-GPTQ/tree/gptq-4bit-64g-actorder_True) | 4 | 64 | Yes | 0.1 | [CamelAI Math](https://huggingface.co/datasets/andersonbcdefg/math) | 4096 | 7.51 GB | Yes | 4-bit, with Act Order and group size 64g. Uses less VRAM than 32g, but with slightly lower accuracy. |
<!-- README_GPTQ.md-provided-files end -->
<!-- README_GPTQ.md-download-from-branches start -->
## How to download, including from branches
### In text-generation-webui
To download from the `main` branch, enter `TheBloke/tora-13B-v1.0-GPTQ` in the "Download model" box.
To download from another branch, add `:branchname` to the end of the download name, eg `TheBloke/tora-13B-v1.0-GPTQ:gptq-4bit-32g-actorder_True`
### From the command line
I recommend using the `huggingface-hub` Python library:
```shell
pip3 install huggingface-hub
```
To download the `main` branch to a folder called `tora-13B-v1.0-GPTQ`:
```shell
mkdir tora-13B-v1.0-GPTQ
huggingface-cli download TheBloke/tora-13B-v1.0-GPTQ --local-dir tora-13B-v1.0-GPTQ --local-dir-use-symlinks False
```
To download from a different branch, add the `--revision` parameter:
```shell
mkdir tora-13B-v1.0-GPTQ
huggingface-cli download TheBloke/tora-13B-v1.0-GPTQ --revision gptq-4bit-32g-actorder_True --local-dir tora-13B-v1.0-GPTQ --local-dir-use-symlinks False
```
<details>
<summary>More advanced huggingface-cli download usage</summary>
If you remove the `--local-dir-use-symlinks False` parameter, the files will instead be stored in the central Huggingface cache directory (default location on Linux is: `~/.cache/huggingface`), and symlinks will be added to the specified `--local-dir`, pointing to their real location in the cache. This allows for interrupted downloads to be resumed, and allows you to quickly clone the repo to multiple places on disk without triggering a download again. The downside, and the reason why I don't list that as the default option, is that the files are then hidden away in a cache folder and it's harder to know where your disk space is being used, and to clear it up if/when you want to remove a download model.
The cache location can be changed with the `HF_HOME` environment variable, and/or the `--cache-dir` parameter to `huggingface-cli`.
For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
```shell
pip3 install hf_transfer
```
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
```shell
mkdir tora-13B-v1.0-GPTQ
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/tora-13B-v1.0-GPTQ --local-dir tora-13B-v1.0-GPTQ --local-dir-use-symlinks False
```
Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
</details>
### With `git` (**not** recommended)
To clone a specific branch with `git`, use a command like this:
```shell
git clone --single-branch --branch gptq-4bit-32g-actorder_True https://huggingface.co/TheBloke/tora-13B-v1.0-GPTQ
```
Note that using Git with HF repos is strongly discouraged. It will be much slower than using `huggingface-hub`, and will use twice as much disk space as it has to store the model files twice (it stores every byte both in the intended target folder, and again in the `.git` folder as a blob.)
<!-- README_GPTQ.md-download-from-branches end -->
<!-- README_GPTQ.md-text-generation-webui start -->
## How to easily download and use this model in [text-generation-webui](https://github.com/oobabooga/text-generation-webui).
Please make sure you're using the latest version of [text-generation-webui](https://github.com/oobabooga/text-generation-webui).
It is strongly recommended to use the text-generation-webui one-click-installers unless you're sure you know how to make a manual install.
1. Click the **Model tab**.
2. Under **Download custom model or LoRA**, enter `TheBloke/tora-13B-v1.0-GPTQ`.
- To download from a specific branch, enter for example `TheBloke/tora-13B-v1.0-GPTQ:gptq-4bit-32g-actorder_True`
- see Provided Files above for the list of branches for each option.
3. Click **Download**.
4. The model will start downloading. Once it's finished it will say "Done".
5. In the top left, click the refresh icon next to **Model**.
6. In the **Model** dropdown, choose the model you just downloaded: `tora-13B-v1.0-GPTQ`
7. The model will automatically load, and is now ready for use!
8. If you want any custom settings, set them and then click **Save settings for this model** followed by **Reload the Model** in the top right.
* Note that you do not need to and should not set manual GPTQ parameters any more. These are set automatically from the file `quantize_config.json`.
9. Once you're ready, click the **Text Generation tab** and enter a prompt to get started!
<!-- README_GPTQ.md-text-generation-webui end -->
<!-- README_GPTQ.md-use-from-tgi start -->
## Serving this model from Text Generation Inference (TGI)
It's recommended to use TGI version 1.1.0 or later. The official Docker container is: `ghcr.io/huggingface/text-generation-inference:1.1.0`
Example Docker parameters:
```shell
--model-id TheBloke/tora-13B-v1.0-GPTQ --port 3000 --quantize awq --max-input-length 3696 --max-total-tokens 4096 --max-batch-prefill-tokens 4096
```
Example Python code for interfacing with TGI (requires huggingface-hub 0.17.0 or later):
```shell
pip3 install huggingface-hub
```
```python
from huggingface_hub import InferenceClient
endpoint_url = "https://your-endpoint-url-here"
prompt = "Tell me about AI"
prompt_template=f'''<|user|>
{prompt}
<|assistant|>
'''
client = InferenceClient(endpoint_url)
response = client.text_generation(prompt,
max_new_tokens=128,
do_sample=True,
temperature=0.7,
top_p=0.95,
top_k=40,
repetition_penalty=1.1)
print(f"Model output: {response}")
```
<!-- README_GPTQ.md-use-from-tgi end -->
<!-- README_GPTQ.md-use-from-python start -->
## How to use this GPTQ model from Python code
### Install the necessary packages
Requires: Transformers 4.33.0 or later, Optimum 1.12.0 or later, and AutoGPTQ 0.4.2 or later.
```shell
pip3 install transformers optimum
pip3 install auto-gptq --extra-index-url https://huggingface.github.io/autogptq-index/whl/cu118/ # Use cu117 if on CUDA 11.7
```
If you have problems installing AutoGPTQ using the pre-built wheels, install it from source instead:
```shell
pip3 uninstall -y auto-gptq
git clone https://github.com/PanQiWei/AutoGPTQ
cd AutoGPTQ
git checkout v0.4.2
pip3 install .
```
### You can then use the following code
```python
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
model_name_or_path = "TheBloke/tora-13B-v1.0-GPTQ"
# To use a different branch, change revision
# For example: revision="gptq-4bit-32g-actorder_True"
model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
device_map="auto",
trust_remote_code=False,
revision="main")
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
prompt = "Tell me about AI"
prompt_template=f'''<|user|>
{prompt}
<|assistant|>
'''
print("\n\n*** Generate:")
input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda()
output = model.generate(inputs=input_ids, temperature=0.7, do_sample=True, top_p=0.95, top_k=40, max_new_tokens=512)
print(tokenizer.decode(output[0]))
# Inference can also be done using transformers' pipeline
print("*** Pipeline:")
pipe = pipeline(
"text-generation",
model=model,
tokenizer=tokenizer,
max_new_tokens=512,
do_sample=True,
temperature=0.7,
top_p=0.95,
top_k=40,
repetition_penalty=1.1
)
print(pipe(prompt_template)[0]['generated_text'])
```
<!-- README_GPTQ.md-use-from-python end -->
<!-- README_GPTQ.md-compatibility start -->
## Compatibility
The files provided are tested to work with AutoGPTQ, both via Transformers and using AutoGPTQ directly. They should also work with [Occ4m's GPTQ-for-LLaMa fork](https://github.com/0cc4m/KoboldAI).
[ExLlama](https://github.com/turboderp/exllama) is compatible with Llama and Mistral models in 4-bit. Please see the Provided Files table above for per-file compatibility.
[Huggingface Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference) is compatible with all GPTQ models.
<!-- README_GPTQ.md-compatibility end -->
<!-- footer start -->
<!-- 200823 -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute
Thanks to the [chirper.ai](https://chirper.ai) team!
Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Aemon Algiz.
**Patreon special mentions**: Pierre Kircher, Stanislav Ovsiannikov, Michael Levine, Eugene Pentland, Andrey, 준교 김, Randy H, Fred von Graf, Artur Olbinski, Caitlyn Gatomon, terasurfer, Jeff Scroggin, James Bentley, Vadim, Gabriel Puliatti, Harry Royden McLaughlin, Sean Connelly, Dan Guido, Edmond Seymore, Alicia Loh, subjectnull, AzureBlack, Manuel Alberto Morcote, Thomas Belote, Lone Striker, Chris Smitley, Vitor Caleffi, Johann-Peter Hartmann, Clay Pascal, biorpg, Brandon Frisco, sidney chen, transmissions 11, Pedro Madruga, jinyuan sun, Ajan Kanaga, Emad Mostaque, Trenton Dambrowitz, Jonathan Leane, Iucharbius, usrbinkat, vamX, George Stoitzev, Luke Pendergrass, theTransient, Olakabola, Swaroop Kallakuri, Cap'n Zoog, Brandon Phillips, Michael Dempsey, Nikolai Manek, danny, Matthew Berman, Gabriel Tamborski, alfie_i, Raymond Fosdick, Tom X Nguyen, Raven Klaugh, LangChain4j, Magnesian, Illia Dulskyi, David Ziegler, Mano Prime, Luis Javier Navarrete Lozano, Erik Bjäreholt, 阿明, Nathan Dryer, Alex, Rainer Wilmers, zynix, TL, Joseph William Delisle, John Villwock, Nathan LeClaire, Willem Michiel, Joguhyik, GodLy, OG, Alps Aficionado, Jeffrey Morgan, ReadyPlayerEmma, Tiffany J. Kim, Sebastain Graf, Spencer Kim, Michael Davis, webtim, Talal Aujan, knownsqashed, John Detwiler, Imad Khwaja, Deo Leter, Jerry Meng, Elijah Stavena, Rooh Singh, Pieter, SuperWojo, Alexandros Triantafyllidis, Stephen Murray, Ai Maven, ya boyyy, Enrico Ros, Ken Nordquist, Deep Realms, Nicholas, Spiking Neurons AB, Elle, Will Dee, Jack West, RoA, Luke @flexchar, Viktor Bowallius, Derek Yates, Subspace Studios, jjj, Toran Billups, Asp the Wyvern, Fen Risland, Ilya, NimbleBox.ai, Chadd, Nitin Borwankar, Emre, Mandus, Leonard Tan, Kalila, K, Trailburnt, S_X, Cory Kujawski
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
<!-- footer end -->
# Original model card: LLM-Agents's ToRA 13B v1.0
<h1 align="center">
ToRA: A Tool-Integrated Reasoning Agent <br> for Mathematical Problem Solving
</h1>
<p align="center">
<a href="https://microsoft.github.io/ToRA/"><b>[🌐 Website]</b></a> •
<a href="https://arxiv.org/abs/2309.17452"><b>[📜 Paper]</b></a> •
<a href="https://huggingface.co/llm-agents"><b>[🤗 HF Models]</b></a> •
<a href="https://github.com/microsoft/ToRA"><b>[🐱 GitHub]</b></a>
<br>
<a href="https://twitter.com/zhs05232838/status/1708860992631763092"><b>[🐦 Twitter]</b></a> •
<a href="https://www.reddit.com/r/LocalLLaMA/comments/1703k6d/tora_a_toolintegrated_reasoning_agent_for/"><b>[💬 Reddit]</b></a> •
<a href="https://notes.aimodels.fyi/researchers-announce-tora-training-language-models-to-better-understand-math-using-external-tools/">[🍀 Unofficial Blog]</a>
<!-- <a href="#-quick-start">Quick Start</a> • -->
<!-- <a href="#%EF%B8%8F-citation">Citation</a> -->
</p>
<p align="center">
Repo for "<a href="https://arxiv.org/abs/2309.17452" target="_blank">ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving</a>"
</p>
## 🔥 News
- [2023/10/08] 🔥🔥🔥 All ToRA models released at [HuggingFace](https://huggingface.co/llm-agents)!!!
- [2023/09/29] ToRA paper, repo, and website released.
## 💡 Introduction
ToRA is a series of Tool-integrated Reasoning Agents designed to solve challenging mathematical reasoning problems by interacting with tools, e.g., computation libraries and symbolic solvers. ToRA series seamlessly integrate natural language reasoning with the utilization of external tools, thereby amalgamating the analytical prowess of language and the computational efficiency of external tools.
| Model | Size | GSM8k | MATH | AVG@10 math tasks<sup>†</sup> |
|---|---|---|---|---|
| GPT-4 | - | 92.0 | 42.5 | 78.3 |
| GPT-4 (PAL) | - | 94.2 | 51.8 | 86.4 |
| [ToRA-7B](https://huggingface.co/llm-agents/tora-7b-v1.0) | 7B | 68.8 | 40.1 | 62.4|
| [ToRA-Code-7B](https://huggingface.co/llm-agents/tora-code-7b-v1.0) | 7B | 72.6 | 44.6 | 66.5|
| [ToRA-13B](https://huggingface.co/llm-agents/tora-13b-v1.0) | 13B | 72.7 | 43.0 | 65.9|
| [ToRA-Code-13B](https://huggingface.co/llm-agents/tora-code-13b-v1.0) | 13B | 75.8 | 48.1 | 71.3 |
| [ToRA-Code-34B<sup>*</sup>](https://huggingface.co/llm-agents/tora-code-34b-v1.0) | 34B | 80.7 | **51.0** | 74.8 |
| [ToRA-70B](https://huggingface.co/llm-agents/tora-70b-v1.0) | 70B | **84.3** | 49.7 | **76.9** |
- <sup>*</sup>ToRA-Code-34B is currently the first and only open-source model to achieve over 50% accuracy (pass@1) on the MATH dataset, which significantly outperforms GPT-4’s CoT result (51.0 vs. 42.5), and is competitive with GPT-4 solving problems with programs. By open-sourcing our codes and models, we hope more breakthroughs will come!
- <sup>†</sup>10 math tasks include GSM8k, MATH, GSM-Hard, SVAMP, TabMWP, ASDiv, SingleEQ, SingleOP, AddSub, and MultiArith.
## ⚡️ Training
The models are trained on ToRA-Corpus 16k, which contains tool-integrated reasoning trajectories of MATH and GSM8k from GPT-4.
We use imitation learning (i.e., SFT) to fine-tune the models, and then apply our proposed *output space shaping* to improve tool-integrated reasoning behaviors. Please refer to the [paper](https://arxiv.org/pdf/2309.17452.pdf) for more details.
## 🪁 Inference & Evaluation
Please refer to ToRA's [GitHub repo](https://github.com/microsoft/ToRA) for inference, evaluation, and training code.
## ☕️ Citation
If you find this repository helpful, please consider citing our paper:
```
@misc{gou2023tora,
title={ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving},
author={Zhibin Gou and Zhihong Shao and Yeyun Gong and yelong shen and Yujiu Yang and Minlie Huang and Nan Duan and Weizhu Chen},
year={2023},
eprint={2309.17452},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
|
liuhaotian/llava-v1.5-13b-shard3gb
|
liuhaotian
| 2023-10-14T20:02:23Z | 39 | 14 |
transformers
|
[
"transformers",
"pytorch",
"llava",
"text-generation",
"autotrain_compatible",
"region:us"
] |
text-generation
| 2023-10-14T05:23:14Z |
---
inference: false
---
<br>
<br>
# LLaVA Model Card
## Model details
**This is the same model checkpoint as [liuhaotian/llava-v1.5-13b](https://huggingface.co/liuhaotian/llava-v1.5-13b), except that this one is sharded with a 3GB per-shard size limit to support machines with limited CPU RAM.**
**Model type:**
LLaVA is an open-source chatbot trained by fine-tuning LLaMA/Vicuna on GPT-generated multimodal instruction-following data.
It is an auto-regressive language model, based on the transformer architecture.
**Model date:**
LLaVA-v1.5-13B was trained in September 2023.
**Paper or resources for more information:**
https://llava-vl.github.io/
## License
Llama 2 is licensed under the LLAMA 2 Community License,
Copyright (c) Meta Platforms, Inc. All Rights Reserved.
**Where to send questions or comments about the model:**
https://github.com/haotian-liu/LLaVA/issues
## Intended use
**Primary intended uses:**
The primary use of LLaVA is research on large multimodal models and chatbots.
**Primary intended users:**
The primary intended users of the model are researchers and hobbyists in computer vision, natural language processing, machine learning, and artificial intelligence.
## Training dataset
- 558K filtered image-text pairs from LAION/CC/SBU, captioned by BLIP.
- 158K GPT-generated multimodal instruction-following data.
- 450K academic-task-oriented VQA data mixture.
- 40K ShareGPT data.
## Evaluation dataset
A collection of 12 benchmarks, including 5 academic VQA benchmarks and 7 recent benchmarks specifically proposed for instruction-following LMMs.
|
TheBloke/tora-13B-v1.0-GGUF
|
TheBloke
| 2023-10-14T19:36:30Z | 57 | 3 |
transformers
|
[
"transformers",
"gguf",
"llama",
"code",
"math",
"text-generation",
"en",
"dataset:gsm8k",
"dataset:competition_math",
"arxiv:2309.17452",
"base_model:llm-agents/tora-13b-v1.0",
"base_model:quantized:llm-agents/tora-13b-v1.0",
"license:llama2",
"region:us"
] |
text-generation
| 2023-10-14T19:30:20Z |
---
base_model: llm-agents/tora-13b-v1.0
datasets:
- gsm8k
- competition_math
inference: false
language:
- en
library_name: transformers
license: llama2
metrics:
- exact_match
model_creator: LLM-Agents
model_name: ToRA 13B v1.0
model_type: llama
pipeline_tag: text-generation
prompt_template: '<|user|>
{prompt}
<|assistant|>
'
quantized_by: TheBloke
tags:
- code
- math
---
<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->
# ToRA 13B v1.0 - GGUF
- Model creator: [LLM-Agents](https://huggingface.co/llm-agents)
- Original model: [ToRA 13B v1.0](https://huggingface.co/llm-agents/tora-13b-v1.0)
<!-- description start -->
## Description
This repo contains GGUF format model files for [LLM-Agents's ToRA 13B v1.0](https://huggingface.co/llm-agents/tora-13b-v1.0).
<!-- description end -->
<!-- README_GGUF.md-about-gguf start -->
### About GGUF
GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp.
Here is an incomplate list of clients and libraries that are known to support GGUF:
* [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option.
* [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.
* [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.
* [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration.
* [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection.
* [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.
* [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server.
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
* [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use.
<!-- README_GGUF.md-about-gguf end -->
<!-- repositories-available start -->
## Repositories available
* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/tora-13B-v1.0-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/tora-13B-v1.0-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/tora-13B-v1.0-GGUF)
* [LLM-Agents's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/llm-agents/tora-13b-v1.0)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: ToRA
```
<|user|>
{prompt}
<|assistant|>
```
<!-- prompt-template end -->
<!-- compatibility_gguf start -->
## Compatibility
These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221)
They are also compatible with many third party UIs and libraries - please see the list at the top of this README.
## Explanation of quantisation methods
<details>
<summary>Click to see details</summary>
The new methods available are:
* GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
* GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
* GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
* GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
* GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
Refer to the Provided Files table below to see what files use which methods, and how.
</details>
<!-- compatibility_gguf end -->
<!-- README_GGUF.md-provided-files start -->
## Provided files
| Name | Quant method | Bits | Size | Max RAM required | Use case |
| ---- | ---- | ---- | ---- | ---- | ----- |
| [tora-13b-v1.0.Q2_K.gguf](https://huggingface.co/TheBloke/tora-13B-v1.0-GGUF/blob/main/tora-13b-v1.0.Q2_K.gguf) | Q2_K | 2 | 5.43 GB| 7.93 GB | smallest, significant quality loss - not recommended for most purposes |
| [tora-13b-v1.0.Q3_K_S.gguf](https://huggingface.co/TheBloke/tora-13B-v1.0-GGUF/blob/main/tora-13b-v1.0.Q3_K_S.gguf) | Q3_K_S | 3 | 5.66 GB| 8.16 GB | very small, high quality loss |
| [tora-13b-v1.0.Q3_K_M.gguf](https://huggingface.co/TheBloke/tora-13B-v1.0-GGUF/blob/main/tora-13b-v1.0.Q3_K_M.gguf) | Q3_K_M | 3 | 6.34 GB| 8.84 GB | very small, high quality loss |
| [tora-13b-v1.0.Q3_K_L.gguf](https://huggingface.co/TheBloke/tora-13B-v1.0-GGUF/blob/main/tora-13b-v1.0.Q3_K_L.gguf) | Q3_K_L | 3 | 6.93 GB| 9.43 GB | small, substantial quality loss |
| [tora-13b-v1.0.Q4_0.gguf](https://huggingface.co/TheBloke/tora-13B-v1.0-GGUF/blob/main/tora-13b-v1.0.Q4_0.gguf) | Q4_0 | 4 | 7.37 GB| 9.87 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [tora-13b-v1.0.Q4_K_S.gguf](https://huggingface.co/TheBloke/tora-13B-v1.0-GGUF/blob/main/tora-13b-v1.0.Q4_K_S.gguf) | Q4_K_S | 4 | 7.41 GB| 9.91 GB | small, greater quality loss |
| [tora-13b-v1.0.Q4_K_M.gguf](https://huggingface.co/TheBloke/tora-13B-v1.0-GGUF/blob/main/tora-13b-v1.0.Q4_K_M.gguf) | Q4_K_M | 4 | 7.87 GB| 10.37 GB | medium, balanced quality - recommended |
| [tora-13b-v1.0.Q5_0.gguf](https://huggingface.co/TheBloke/tora-13B-v1.0-GGUF/blob/main/tora-13b-v1.0.Q5_0.gguf) | Q5_0 | 5 | 8.97 GB| 11.47 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [tora-13b-v1.0.Q5_K_S.gguf](https://huggingface.co/TheBloke/tora-13B-v1.0-GGUF/blob/main/tora-13b-v1.0.Q5_K_S.gguf) | Q5_K_S | 5 | 8.97 GB| 11.47 GB | large, low quality loss - recommended |
| [tora-13b-v1.0.Q5_K_M.gguf](https://huggingface.co/TheBloke/tora-13B-v1.0-GGUF/blob/main/tora-13b-v1.0.Q5_K_M.gguf) | Q5_K_M | 5 | 9.23 GB| 11.73 GB | large, very low quality loss - recommended |
| [tora-13b-v1.0.Q6_K.gguf](https://huggingface.co/TheBloke/tora-13B-v1.0-GGUF/blob/main/tora-13b-v1.0.Q6_K.gguf) | Q6_K | 6 | 10.68 GB| 13.18 GB | very large, extremely low quality loss |
| [tora-13b-v1.0.Q8_0.gguf](https://huggingface.co/TheBloke/tora-13B-v1.0-GGUF/blob/main/tora-13b-v1.0.Q8_0.gguf) | Q8_0 | 8 | 13.83 GB| 16.33 GB | very large, extremely low quality loss - not recommended |
**Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
<!-- README_GGUF.md-provided-files end -->
<!-- README_GGUF.md-how-to-download start -->
## How to download GGUF files
**Note for manual downloaders:** You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.
The following clients/libraries will automatically download models for you, providing a list of available models to choose from:
- LM Studio
- LoLLMS Web UI
- Faraday.dev
### In `text-generation-webui`
Under Download Model, you can enter the model repo: TheBloke/tora-13B-v1.0-GGUF and below it, a specific filename to download, such as: tora-13b-v1.0.Q4_K_M.gguf.
Then click Download.
### On the command line, including multiple files at once
I recommend using the `huggingface-hub` Python library:
```shell
pip3 install huggingface-hub
```
Then you can download any individual model file to the current directory, at high speed, with a command like this:
```shell
huggingface-cli download TheBloke/tora-13B-v1.0-GGUF tora-13b-v1.0.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
<details>
<summary>More advanced huggingface-cli download usage</summary>
You can also download multiple files at once with a pattern:
```shell
huggingface-cli download TheBloke/tora-13B-v1.0-GGUF --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'
```
For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
```shell
pip3 install hf_transfer
```
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
```shell
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/tora-13B-v1.0-GGUF tora-13b-v1.0.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
</details>
<!-- README_GGUF.md-how-to-download end -->
<!-- README_GGUF.md-how-to-run start -->
## Example `llama.cpp` command
Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
```shell
./main -ngl 32 -m tora-13b-v1.0.Q4_K_M.gguf --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "<|user|>\n{prompt}\n<|assistant|>"
```
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
Change `-c 4096` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically.
If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)
## How to run in `text-generation-webui`
Further instructions here: [text-generation-webui/docs/llama.cpp.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/llama.cpp.md).
## How to run from Python code
You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries.
### How to load this model in Python code, using ctransformers
#### First install the package
Run one of the following commands, according to your system:
```shell
# Base ctransformers with no GPU acceleration
pip install ctransformers
# Or with CUDA GPU acceleration
pip install ctransformers[cuda]
# Or with AMD ROCm GPU acceleration (Linux only)
CT_HIPBLAS=1 pip install ctransformers --no-binary ctransformers
# Or with Metal GPU acceleration for macOS systems only
CT_METAL=1 pip install ctransformers --no-binary ctransformers
```
#### Simple ctransformers example code
```python
from ctransformers import AutoModelForCausalLM
# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
llm = AutoModelForCausalLM.from_pretrained("TheBloke/tora-13B-v1.0-GGUF", model_file="tora-13b-v1.0.Q4_K_M.gguf", model_type="llama", gpu_layers=50)
print(llm("AI is going to"))
```
## How to use with LangChain
Here are guides on using llama-cpp-python and ctransformers with LangChain:
* [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp)
* [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers)
<!-- README_GGUF.md-how-to-run end -->
<!-- footer start -->
<!-- 200823 -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute
Thanks to the [chirper.ai](https://chirper.ai) team!
Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Aemon Algiz.
**Patreon special mentions**: Pierre Kircher, Stanislav Ovsiannikov, Michael Levine, Eugene Pentland, Andrey, 준교 김, Randy H, Fred von Graf, Artur Olbinski, Caitlyn Gatomon, terasurfer, Jeff Scroggin, James Bentley, Vadim, Gabriel Puliatti, Harry Royden McLaughlin, Sean Connelly, Dan Guido, Edmond Seymore, Alicia Loh, subjectnull, AzureBlack, Manuel Alberto Morcote, Thomas Belote, Lone Striker, Chris Smitley, Vitor Caleffi, Johann-Peter Hartmann, Clay Pascal, biorpg, Brandon Frisco, sidney chen, transmissions 11, Pedro Madruga, jinyuan sun, Ajan Kanaga, Emad Mostaque, Trenton Dambrowitz, Jonathan Leane, Iucharbius, usrbinkat, vamX, George Stoitzev, Luke Pendergrass, theTransient, Olakabola, Swaroop Kallakuri, Cap'n Zoog, Brandon Phillips, Michael Dempsey, Nikolai Manek, danny, Matthew Berman, Gabriel Tamborski, alfie_i, Raymond Fosdick, Tom X Nguyen, Raven Klaugh, LangChain4j, Magnesian, Illia Dulskyi, David Ziegler, Mano Prime, Luis Javier Navarrete Lozano, Erik Bjäreholt, 阿明, Nathan Dryer, Alex, Rainer Wilmers, zynix, TL, Joseph William Delisle, John Villwock, Nathan LeClaire, Willem Michiel, Joguhyik, GodLy, OG, Alps Aficionado, Jeffrey Morgan, ReadyPlayerEmma, Tiffany J. Kim, Sebastain Graf, Spencer Kim, Michael Davis, webtim, Talal Aujan, knownsqashed, John Detwiler, Imad Khwaja, Deo Leter, Jerry Meng, Elijah Stavena, Rooh Singh, Pieter, SuperWojo, Alexandros Triantafyllidis, Stephen Murray, Ai Maven, ya boyyy, Enrico Ros, Ken Nordquist, Deep Realms, Nicholas, Spiking Neurons AB, Elle, Will Dee, Jack West, RoA, Luke @flexchar, Viktor Bowallius, Derek Yates, Subspace Studios, jjj, Toran Billups, Asp the Wyvern, Fen Risland, Ilya, NimbleBox.ai, Chadd, Nitin Borwankar, Emre, Mandus, Leonard Tan, Kalila, K, Trailburnt, S_X, Cory Kujawski
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
<!-- footer end -->
<!-- original-model-card start -->
# Original model card: LLM-Agents's ToRA 13B v1.0
<h1 align="center">
ToRA: A Tool-Integrated Reasoning Agent <br> for Mathematical Problem Solving
</h1>
<p align="center">
<a href="https://microsoft.github.io/ToRA/"><b>[🌐 Website]</b></a> •
<a href="https://arxiv.org/abs/2309.17452"><b>[📜 Paper]</b></a> •
<a href="https://huggingface.co/llm-agents"><b>[🤗 HF Models]</b></a> •
<a href="https://github.com/microsoft/ToRA"><b>[🐱 GitHub]</b></a>
<br>
<a href="https://twitter.com/zhs05232838/status/1708860992631763092"><b>[🐦 Twitter]</b></a> •
<a href="https://www.reddit.com/r/LocalLLaMA/comments/1703k6d/tora_a_toolintegrated_reasoning_agent_for/"><b>[💬 Reddit]</b></a> •
<a href="https://notes.aimodels.fyi/researchers-announce-tora-training-language-models-to-better-understand-math-using-external-tools/">[🍀 Unofficial Blog]</a>
<!-- <a href="#-quick-start">Quick Start</a> • -->
<!-- <a href="#%EF%B8%8F-citation">Citation</a> -->
</p>
<p align="center">
Repo for "<a href="https://arxiv.org/abs/2309.17452" target="_blank">ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving</a>"
</p>
## 🔥 News
- [2023/10/08] 🔥🔥🔥 All ToRA models released at [HuggingFace](https://huggingface.co/llm-agents)!!!
- [2023/09/29] ToRA paper, repo, and website released.
## 💡 Introduction
ToRA is a series of Tool-integrated Reasoning Agents designed to solve challenging mathematical reasoning problems by interacting with tools, e.g., computation libraries and symbolic solvers. ToRA series seamlessly integrate natural language reasoning with the utilization of external tools, thereby amalgamating the analytical prowess of language and the computational efficiency of external tools.
| Model | Size | GSM8k | MATH | AVG@10 math tasks<sup>†</sup> |
|---|---|---|---|---|
| GPT-4 | - | 92.0 | 42.5 | 78.3 |
| GPT-4 (PAL) | - | 94.2 | 51.8 | 86.4 |
| [ToRA-7B](https://huggingface.co/llm-agents/tora-7b-v1.0) | 7B | 68.8 | 40.1 | 62.4|
| [ToRA-Code-7B](https://huggingface.co/llm-agents/tora-code-7b-v1.0) | 7B | 72.6 | 44.6 | 66.5|
| [ToRA-13B](https://huggingface.co/llm-agents/tora-13b-v1.0) | 13B | 72.7 | 43.0 | 65.9|
| [ToRA-Code-13B](https://huggingface.co/llm-agents/tora-code-13b-v1.0) | 13B | 75.8 | 48.1 | 71.3 |
| [ToRA-Code-34B<sup>*</sup>](https://huggingface.co/llm-agents/tora-code-34b-v1.0) | 34B | 80.7 | **51.0** | 74.8 |
| [ToRA-70B](https://huggingface.co/llm-agents/tora-70b-v1.0) | 70B | **84.3** | 49.7 | **76.9** |
- <sup>*</sup>ToRA-Code-34B is currently the first and only open-source model to achieve over 50% accuracy (pass@1) on the MATH dataset, which significantly outperforms GPT-4’s CoT result (51.0 vs. 42.5), and is competitive with GPT-4 solving problems with programs. By open-sourcing our codes and models, we hope more breakthroughs will come!
- <sup>†</sup>10 math tasks include GSM8k, MATH, GSM-Hard, SVAMP, TabMWP, ASDiv, SingleEQ, SingleOP, AddSub, and MultiArith.
## ⚡️ Training
The models are trained on ToRA-Corpus 16k, which contains tool-integrated reasoning trajectories of MATH and GSM8k from GPT-4.
We use imitation learning (i.e., SFT) to fine-tune the models, and then apply our proposed *output space shaping* to improve tool-integrated reasoning behaviors. Please refer to the [paper](https://arxiv.org/pdf/2309.17452.pdf) for more details.
## 🪁 Inference & Evaluation
Please refer to ToRA's [GitHub repo](https://github.com/microsoft/ToRA) for inference, evaluation, and training code.
## ☕️ Citation
If you find this repository helpful, please consider citing our paper:
```
@misc{gou2023tora,
title={ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving},
author={Zhibin Gou and Zhihong Shao and Yeyun Gong and yelong shen and Yujiu Yang and Minlie Huang and Nan Duan and Weizhu Chen},
year={2023},
eprint={2309.17452},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
<!-- original-model-card end -->
|
Azma-AI/deberta-base-multi-label-classifier
|
Azma-AI
| 2023-10-14T19:31:58Z | 32 | 1 |
transformers
|
[
"transformers",
"pytorch",
"safetensors",
"deberta-v2",
"text-classification",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-10-10T11:09:58Z |
# Model Card for DeBERTa-v3-base-tasksource-nli
This is [DeBERTa-v3-base](https://hf.co/microsoft/deberta-v3-base) fine-tuned with multi-task learning on 600 tasks.
This checkpoint has strong zero-shot validation performance on many tasks (e.g. 70% on WNLI), and can be used for:
- Zero-shot entailment-based classification pipeline (similar to bart-mnli), see [ZS].
- Natural language inference, and many other tasks with tasksource-adapters, see [TA]
- Further fine-tuning with a new task (classification, token classification or multiple-choice).
# [ZS] Zero-shot classification pipeline
```python
from transformers import pipeline
classifier = pipeline("zero-shot-classification",model="Azma-AI/deberta-base-multi-label-classifier")
text = "one day I will see the world"
candidate_labels = ['travel', 'cooking', 'dancing']
classifier(text, candidate_labels)
|
MattStammers/appo-atari_pong-sota
|
MattStammers
| 2023-10-14T19:09:02Z | 0 | 0 |
sample-factory
|
[
"sample-factory",
"tensorboard",
"deep-reinforcement-learning",
"reinforcement-learning",
"PongNoFrameskip-v4",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-10-14T03:59:18Z |
---
library_name: sample-factory
tags:
- deep-reinforcement-learning
- reinforcement-learning
- sample-factory
- PongNoFrameskip-v4
model-index:
- name: APPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: PongNoFrameskip-v4
type: PongNoFrameskip-v4
metrics:
- type: mean_reward
value: 21.00 +/- 0.00
name: mean_reward
verified: false
---
A(n) **APPO** model trained on the **atari_pong** environment.
This model was trained using Sample-Factory 2.0: https://github.com/alex-petrenko/sample-factory.
Documentation for how to use Sample-Factory can be found at https://www.samplefactory.dev/
## Downloading the model
After installing Sample-Factory, download the model with:
```
python -m sample_factory.huggingface.load_from_hub -r MattStammers/APPO-atari_pong
```
## About the Model
This model as with all the others in the benchmarks was trained initially asynchronously un-seeded to 10 million steps for the purposes of setting a sample factory async baseline for this model on this environment but only 3/57 made it.
The aim is to reach state-of-the-art (SOTA) performance on each atari environment. I will flag the models with SOTA when they reach at or near these levels.
The hyperparameters used in the model are the ones I have pushed to my fork of sample-factory: https://github.com/MattStammers/sample-factory. Given that https://huggingface.co/edbeeching has kindly shared his.
I saved time and energy by using many of his tuned hyperparameters to maximise performance. However, he used 2 billion training steps. I have started as explained above at 10 million then moved to 100m to see how performance goes:
```
hyperparameters = {
"device": "gpu",
"seed": 1234,
"num_policies": 2,
"async_rl": true,
"serial_mode": false,
"batched_sampling": true,
"num_batches_to_accumulate": 2,
"worker_num_splits": 1,
"policy_workers_per_policy": 1,
"max_policy_lag": 1000,
"num_workers": 16,
"num_envs_per_worker": 2,
"batch_size": 1024,
"num_batches_per_epoch": 8,
"num_epochs": 4,
"rollout": 128,
"recurrence": 1,
"shuffle_minibatches": false,
"gamma": 0.99,
"reward_scale": 1.0,
"reward_clip": 1000.0,
"value_bootstrap": false,
"normalize_returns": true,
"exploration_loss_coeff": 0.0004677351413,
"value_loss_coeff": 0.5,
"kl_loss_coeff": 0.0,
"exploration_loss": "entropy",
"gae_lambda": 0.95,
"ppo_clip_ratio": 0.1,
"ppo_clip_value": 1.0,
"with_vtrace": false,
"vtrace_rho": 1.0,
"vtrace_c": 1.0,
"optimizer": "adam",
"adam_eps": 1e-05,
"adam_beta1": 0.9,
"adam_beta2": 0.999,
"max_grad_norm": 0.0,
"learning_rate": 0.0003033891184,
"lr_schedule": "linear_decay",
"lr_schedule_kl_threshold": 0.008,
"lr_adaptive_min": 1e-06,
"lr_adaptive_max": 0.01,
"obs_subtract_mean": 0.0,
"obs_scale": 255.0,
"normalize_input": true,
"normalize_input_keys": [
"obs"
],
"decorrelate_experience_max_seconds": 0,
"decorrelate_envs_on_one_worker": true,
"actor_worker_gpus": [],
"set_workers_cpu_affinity": true,
"force_envs_single_thread": false,
"default_niceness": 0,
"log_to_file": true,
"experiment_summaries_interval": 3,
"flush_summaries_interval": 30,
"stats_avg": 100,
"summaries_use_frameskip": true,
"heartbeat_interval": 10,
"heartbeat_reporting_interval": 60,
"train_for_env_steps": 100000000,
"train_for_seconds": 10000000000,
"save_every_sec": 120,
"keep_checkpoints": 2,
"load_checkpoint_kind": "latest",
"save_milestones_sec": 1200,
"save_best_every_sec": 5,
"save_best_metric": "reward",
"save_best_after": 100000,
"benchmark": false,
"encoder_mlp_layers": [
512,
512
],
"encoder_conv_architecture": "convnet_atari",
"encoder_conv_mlp_layers": [
512
],
"use_rnn": false,
"rnn_size": 512,
"rnn_type": "gru",
"rnn_num_layers": 1,
"decoder_mlp_layers": [],
"nonlinearity": "relu",
"policy_initialization": "orthogonal",
"policy_init_gain": 1.0,
"actor_critic_share_weights": true,
"adaptive_stddev": false,
"continuous_tanh_scale": 0.0,
"initial_stddev": 1.0,
"use_env_info_cache": false,
"env_gpu_actions": false,
"env_gpu_observations": true,
"env_frameskip": 4,
"env_framestack": 4,
}
```
## Using the model
To run the model after download, use the `enjoy` script corresponding to this environment:
```
python -m sf_examples.atari.enjoy_atari --algo=APPO --env=atari_pong --train_dir=./train_dir --experiment=APPO-atari_pong
```
You can also upload models to the Hugging Face Hub using the same script with the `--push_to_hub` flag.
See https://www.samplefactory.dev/10-huggingface/huggingface/ for more details
## Training with this model
To continue training with this model, use the `train` script corresponding to this environment:
```
python -m sf_examples.atari.train_atari --algo=APPO --env=atari_pong --train_dir=./train_dir --experiment=APPO-atari_pong --restart_behavior=resume --train_for_env_steps=10000000000
```
Note, you may have to adjust `--train_for_env_steps` to a suitably high number as the experiment will resume at the number of steps it concluded at.
|
kuro11/llama-lora-medical-model
|
kuro11
| 2023-10-14T19:02:56Z | 0 | 1 |
peft
|
[
"peft",
"arxiv:1910.09700",
"base_model:medalpaca/medalpaca-7b",
"base_model:adapter:medalpaca/medalpaca-7b",
"region:us"
] | null | 2023-10-14T19:02:05Z |
---
library_name: peft
base_model: medalpaca/medalpaca-7b
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Data Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
## Training procedure
### Framework versions
- PEFT 0.6.0.dev0
## Training procedure
### Framework versions
- PEFT 0.6.0.dev0
|
TheBloke/ALMA-13B-GPTQ
|
TheBloke
| 2023-10-14T18:13:56Z | 21 | 2 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"arxiv:2309.11674",
"base_model:haoranxu/ALMA-13B",
"base_model:quantized:haoranxu/ALMA-13B",
"license:mit",
"autotrain_compatible",
"text-generation-inference",
"4-bit",
"gptq",
"region:us"
] |
text-generation
| 2023-10-14T17:33:06Z |
---
base_model: haoranxu/ALMA-13B
inference: false
license: mit
model_creator: Haoran Xu
model_name: ALMA 13B
model_type: llama
prompt_template: 'Translate this from Chinese to English:
Chinese: {prompt}
English:
'
quantized_by: TheBloke
---
<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->
# ALMA 13B - GPTQ
- Model creator: [Haoran Xu](https://huggingface.co/haoranxu)
- Original model: [ALMA 13B](https://huggingface.co/haoranxu/ALMA-13B)
<!-- description start -->
## Description
This repo contains GPTQ model files for [Haoran Xu's ALMA 13B](https://huggingface.co/haoranxu/ALMA-13B).
Multiple GPTQ parameter permutations are provided; see Provided Files below for details of the options provided, their parameters, and the software used to create them.
<!-- description end -->
<!-- repositories-available start -->
## Repositories available
* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/ALMA-13B-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/ALMA-13B-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/ALMA-13B-GGUF)
* [Haoran Xu's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/haoranxu/ALMA-13B)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: ALMA
```
Translate this from Chinese to English:
Chinese: {prompt}
English:
```
<!-- prompt-template end -->
<!-- licensing start -->
## Licensing
The creator of the source model has listed its license as `mit`, and this quantization has therefore used that same license.
As this model is based on Llama 2, it is also subject to the Meta Llama 2 license terms, and the license files for that are additionally included. It should therefore be considered as being claimed to be licensed under both licenses. I contacted Hugging Face for clarification on dual licensing but they do not yet have an official position. Should this change, or should Meta provide any feedback on this situation, I will update this section accordingly.
In the meantime, any questions regarding licensing, and in particular how these two licenses might interact, should be directed to the original model repository: [Haoran Xu's ALMA 13B](https://huggingface.co/haoranxu/ALMA-13B).
<!-- licensing end -->
<!-- README_GPTQ.md-provided-files start -->
## Provided files, and GPTQ parameters
Multiple quantisation parameters are provided, to allow you to choose the best one for your hardware and requirements.
Each separate quant is in a different branch. See below for instructions on fetching from different branches.
Most GPTQ files are made with AutoGPTQ. Mistral models are currently made with Transformers.
<details>
<summary>Explanation of GPTQ parameters</summary>
- Bits: The bit size of the quantised model.
- GS: GPTQ group size. Higher numbers use less VRAM, but have lower quantisation accuracy. "None" is the lowest possible value.
- Act Order: True or False. Also known as `desc_act`. True results in better quantisation accuracy. Some GPTQ clients have had issues with models that use Act Order plus Group Size, but this is generally resolved now.
- Damp %: A GPTQ parameter that affects how samples are processed for quantisation. 0.01 is default, but 0.1 results in slightly better accuracy.
- GPTQ dataset: The calibration dataset used during quantisation. Using a dataset more appropriate to the model's training can improve quantisation accuracy. Note that the GPTQ calibration dataset is not the same as the dataset used to train the model - please refer to the original model repo for details of the training dataset(s).
- Sequence Length: The length of the dataset sequences used for quantisation. Ideally this is the same as the model sequence length. For some very long sequence models (16+K), a lower sequence length may have to be used. Note that a lower sequence length does not limit the sequence length of the quantised model. It only impacts the quantisation accuracy on longer inference sequences.
- ExLlama Compatibility: Whether this file can be loaded with ExLlama, which currently only supports Llama models in 4-bit.
</details>
| Branch | Bits | GS | Act Order | Damp % | GPTQ Dataset | Seq Len | Size | ExLlama | Desc |
| ------ | ---- | -- | --------- | ------ | ------------ | ------- | ---- | ------- | ---- |
| [main](https://huggingface.co/TheBloke/ALMA-13B-GPTQ/tree/main) | 4 | 128 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 7.26 GB | Yes | 4-bit, with Act Order and group size 128g. Uses even less VRAM than 64g, but with slightly lower accuracy. |
| [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/ALMA-13B-GPTQ/tree/gptq-4bit-32g-actorder_True) | 4 | 32 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 8.00 GB | Yes | 4-bit, with Act Order and group size 32g. Gives highest possible inference quality, with maximum VRAM usage. |
| [gptq-8bit--1g-actorder_True](https://huggingface.co/TheBloke/ALMA-13B-GPTQ/tree/gptq-8bit--1g-actorder_True) | 8 | None | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 13.36 GB | No | 8-bit, with Act Order. No group size, to lower VRAM requirements. |
| [gptq-8bit-128g-actorder_True](https://huggingface.co/TheBloke/ALMA-13B-GPTQ/tree/gptq-8bit-128g-actorder_True) | 8 | 128 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 13.65 GB | No | 8-bit, with group size 128g for higher inference quality and with Act Order for even higher accuracy. |
| [gptq-8bit-32g-actorder_True](https://huggingface.co/TheBloke/ALMA-13B-GPTQ/tree/gptq-8bit-32g-actorder_True) | 8 | 32 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 14.54 GB | No | 8-bit, with group size 32g and Act Order for maximum inference quality. |
| [gptq-4bit-64g-actorder_True](https://huggingface.co/TheBloke/ALMA-13B-GPTQ/tree/gptq-4bit-64g-actorder_True) | 4 | 64 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 7.51 GB | Yes | 4-bit, with Act Order and group size 64g. Uses less VRAM than 32g, but with slightly lower accuracy. |
<!-- README_GPTQ.md-provided-files end -->
<!-- README_GPTQ.md-download-from-branches start -->
## How to download, including from branches
### In text-generation-webui
To download from the `main` branch, enter `TheBloke/ALMA-13B-GPTQ` in the "Download model" box.
To download from another branch, add `:branchname` to the end of the download name, eg `TheBloke/ALMA-13B-GPTQ:gptq-4bit-32g-actorder_True`
### From the command line
I recommend using the `huggingface-hub` Python library:
```shell
pip3 install huggingface-hub
```
To download the `main` branch to a folder called `ALMA-13B-GPTQ`:
```shell
mkdir ALMA-13B-GPTQ
huggingface-cli download TheBloke/ALMA-13B-GPTQ --local-dir ALMA-13B-GPTQ --local-dir-use-symlinks False
```
To download from a different branch, add the `--revision` parameter:
```shell
mkdir ALMA-13B-GPTQ
huggingface-cli download TheBloke/ALMA-13B-GPTQ --revision gptq-4bit-32g-actorder_True --local-dir ALMA-13B-GPTQ --local-dir-use-symlinks False
```
<details>
<summary>More advanced huggingface-cli download usage</summary>
If you remove the `--local-dir-use-symlinks False` parameter, the files will instead be stored in the central Huggingface cache directory (default location on Linux is: `~/.cache/huggingface`), and symlinks will be added to the specified `--local-dir`, pointing to their real location in the cache. This allows for interrupted downloads to be resumed, and allows you to quickly clone the repo to multiple places on disk without triggering a download again. The downside, and the reason why I don't list that as the default option, is that the files are then hidden away in a cache folder and it's harder to know where your disk space is being used, and to clear it up if/when you want to remove a download model.
The cache location can be changed with the `HF_HOME` environment variable, and/or the `--cache-dir` parameter to `huggingface-cli`.
For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
```shell
pip3 install hf_transfer
```
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
```shell
mkdir ALMA-13B-GPTQ
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/ALMA-13B-GPTQ --local-dir ALMA-13B-GPTQ --local-dir-use-symlinks False
```
Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
</details>
### With `git` (**not** recommended)
To clone a specific branch with `git`, use a command like this:
```shell
git clone --single-branch --branch gptq-4bit-32g-actorder_True https://huggingface.co/TheBloke/ALMA-13B-GPTQ
```
Note that using Git with HF repos is strongly discouraged. It will be much slower than using `huggingface-hub`, and will use twice as much disk space as it has to store the model files twice (it stores every byte both in the intended target folder, and again in the `.git` folder as a blob.)
<!-- README_GPTQ.md-download-from-branches end -->
<!-- README_GPTQ.md-text-generation-webui start -->
## How to easily download and use this model in [text-generation-webui](https://github.com/oobabooga/text-generation-webui).
Please make sure you're using the latest version of [text-generation-webui](https://github.com/oobabooga/text-generation-webui).
It is strongly recommended to use the text-generation-webui one-click-installers unless you're sure you know how to make a manual install.
1. Click the **Model tab**.
2. Under **Download custom model or LoRA**, enter `TheBloke/ALMA-13B-GPTQ`.
- To download from a specific branch, enter for example `TheBloke/ALMA-13B-GPTQ:gptq-4bit-32g-actorder_True`
- see Provided Files above for the list of branches for each option.
3. Click **Download**.
4. The model will start downloading. Once it's finished it will say "Done".
5. In the top left, click the refresh icon next to **Model**.
6. In the **Model** dropdown, choose the model you just downloaded: `ALMA-13B-GPTQ`
7. The model will automatically load, and is now ready for use!
8. If you want any custom settings, set them and then click **Save settings for this model** followed by **Reload the Model** in the top right.
* Note that you do not need to and should not set manual GPTQ parameters any more. These are set automatically from the file `quantize_config.json`.
9. Once you're ready, click the **Text Generation tab** and enter a prompt to get started!
<!-- README_GPTQ.md-text-generation-webui end -->
<!-- README_GPTQ.md-use-from-tgi start -->
## Serving this model from Text Generation Inference (TGI)
It's recommended to use TGI version 1.1.0 or later. The official Docker container is: `ghcr.io/huggingface/text-generation-inference:1.1.0`
Example Docker parameters:
```shell
--model-id TheBloke/ALMA-13B-GPTQ --port 3000 --quantize awq --max-input-length 3696 --max-total-tokens 4096 --max-batch-prefill-tokens 4096
```
Example Python code for interfacing with TGI (requires huggingface-hub 0.17.0 or later):
```shell
pip3 install huggingface-hub
```
```python
from huggingface_hub import InferenceClient
endpoint_url = "https://your-endpoint-url-here"
prompt = "Tell me about AI"
prompt_template=f'''Translate this from Chinese to English:
Chinese: {prompt}
English:
'''
client = InferenceClient(endpoint_url)
response = client.text_generation(prompt,
max_new_tokens=128,
do_sample=True,
temperature=0.7,
top_p=0.95,
top_k=40,
repetition_penalty=1.1)
print(f"Model output: {response}")
```
<!-- README_GPTQ.md-use-from-tgi end -->
<!-- README_GPTQ.md-use-from-python start -->
## How to use this GPTQ model from Python code
### Install the necessary packages
Requires: Transformers 4.33.0 or later, Optimum 1.12.0 or later, and AutoGPTQ 0.4.2 or later.
```shell
pip3 install transformers optimum
pip3 install auto-gptq --extra-index-url https://huggingface.github.io/autogptq-index/whl/cu118/ # Use cu117 if on CUDA 11.7
```
If you have problems installing AutoGPTQ using the pre-built wheels, install it from source instead:
```shell
pip3 uninstall -y auto-gptq
git clone https://github.com/PanQiWei/AutoGPTQ
cd AutoGPTQ
git checkout v0.4.2
pip3 install .
```
### You can then use the following code
```python
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
model_name_or_path = "TheBloke/ALMA-13B-GPTQ"
# To use a different branch, change revision
# For example: revision="gptq-4bit-32g-actorder_True"
model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
device_map="auto",
trust_remote_code=False,
revision="main")
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
prompt = "Tell me about AI"
prompt_template=f'''Translate this from Chinese to English:
Chinese: {prompt}
English:
'''
print("\n\n*** Generate:")
input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda()
output = model.generate(inputs=input_ids, temperature=0.7, do_sample=True, top_p=0.95, top_k=40, max_new_tokens=512)
print(tokenizer.decode(output[0]))
# Inference can also be done using transformers' pipeline
print("*** Pipeline:")
pipe = pipeline(
"text-generation",
model=model,
tokenizer=tokenizer,
max_new_tokens=512,
do_sample=True,
temperature=0.7,
top_p=0.95,
top_k=40,
repetition_penalty=1.1
)
print(pipe(prompt_template)[0]['generated_text'])
```
<!-- README_GPTQ.md-use-from-python end -->
<!-- README_GPTQ.md-compatibility start -->
## Compatibility
The files provided are tested to work with AutoGPTQ, both via Transformers and using AutoGPTQ directly. They should also work with [Occ4m's GPTQ-for-LLaMa fork](https://github.com/0cc4m/KoboldAI).
[ExLlama](https://github.com/turboderp/exllama) is compatible with Llama and Mistral models in 4-bit. Please see the Provided Files table above for per-file compatibility.
[Huggingface Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference) is compatible with all GPTQ models.
<!-- README_GPTQ.md-compatibility end -->
<!-- footer start -->
<!-- 200823 -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute
Thanks to the [chirper.ai](https://chirper.ai) team!
Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Aemon Algiz.
**Patreon special mentions**: Pierre Kircher, Stanislav Ovsiannikov, Michael Levine, Eugene Pentland, Andrey, 준교 김, Randy H, Fred von Graf, Artur Olbinski, Caitlyn Gatomon, terasurfer, Jeff Scroggin, James Bentley, Vadim, Gabriel Puliatti, Harry Royden McLaughlin, Sean Connelly, Dan Guido, Edmond Seymore, Alicia Loh, subjectnull, AzureBlack, Manuel Alberto Morcote, Thomas Belote, Lone Striker, Chris Smitley, Vitor Caleffi, Johann-Peter Hartmann, Clay Pascal, biorpg, Brandon Frisco, sidney chen, transmissions 11, Pedro Madruga, jinyuan sun, Ajan Kanaga, Emad Mostaque, Trenton Dambrowitz, Jonathan Leane, Iucharbius, usrbinkat, vamX, George Stoitzev, Luke Pendergrass, theTransient, Olakabola, Swaroop Kallakuri, Cap'n Zoog, Brandon Phillips, Michael Dempsey, Nikolai Manek, danny, Matthew Berman, Gabriel Tamborski, alfie_i, Raymond Fosdick, Tom X Nguyen, Raven Klaugh, LangChain4j, Magnesian, Illia Dulskyi, David Ziegler, Mano Prime, Luis Javier Navarrete Lozano, Erik Bjäreholt, 阿明, Nathan Dryer, Alex, Rainer Wilmers, zynix, TL, Joseph William Delisle, John Villwock, Nathan LeClaire, Willem Michiel, Joguhyik, GodLy, OG, Alps Aficionado, Jeffrey Morgan, ReadyPlayerEmma, Tiffany J. Kim, Sebastain Graf, Spencer Kim, Michael Davis, webtim, Talal Aujan, knownsqashed, John Detwiler, Imad Khwaja, Deo Leter, Jerry Meng, Elijah Stavena, Rooh Singh, Pieter, SuperWojo, Alexandros Triantafyllidis, Stephen Murray, Ai Maven, ya boyyy, Enrico Ros, Ken Nordquist, Deep Realms, Nicholas, Spiking Neurons AB, Elle, Will Dee, Jack West, RoA, Luke @flexchar, Viktor Bowallius, Derek Yates, Subspace Studios, jjj, Toran Billups, Asp the Wyvern, Fen Risland, Ilya, NimbleBox.ai, Chadd, Nitin Borwankar, Emre, Mandus, Leonard Tan, Kalila, K, Trailburnt, S_X, Cory Kujawski
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
<!-- footer end -->
# Original model card: Haoran Xu's ALMA 13B
**ALMA** (**A**dvanced **L**anguage **M**odel-based tr**A**nslator) is an LLM-based translation model, which adopts a new translation model paradigm: it begins with fine-tuning on monolingual data and is further optimized using high-quality parallel data. This two-step fine-tuning process ensures strong translation performance.
Please find more details in our [paper](https://arxiv.org/abs/2309.11674).
```
@misc{xu2023paradigm,
title={A Paradigm Shift in Machine Translation: Boosting Translation Performance of Large Language Models},
author={Haoran Xu and Young Jin Kim and Amr Sharaf and Hany Hassan Awadalla},
year={2023},
eprint={2309.11674},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
We release four translation models presented in the paper:
- **ALMA-7B**: Full-weight Fine-tune LLaMA-2-7B on 20B monolingual tokens and then **Full-weight** fine-tune on human-written parallel data
- **ALMA-7B-LoRA**: Full-weight Fine-tune LLaMA-2-7B on 20B monolingual tokens and then **LoRA** fine-tune on human-written parallel data
- **ALMA-13B**: Full-weight Fine-tune LLaMA-2-7B on 12B monolingual tokens and then **Full-weight** fine-tune on human-written parallel data
- **ALMA-13B-LoRA** (Our best system): Full-weight Fine-tune LLaMA-2-7B on 12B monolingual tokens and then **LoRA** fine-tune on human-written parallel data
Model checkpoints are released at huggingface:
| Models | Base Model Link | LoRA Link |
|:-------------:|:---------------:|:---------:|
| ALMA-7B | [haoranxu/ALMA-7B](https://huggingface.co/haoranxu/ALMA-7B) | - |
| ALMA-7B-LoRA | [haoranxu/ALMA-7B-Pretrain](https://huggingface.co/haoranxu/ALMA-7B-Pretrain) | [haoranxu/ALMA-7B-Pretrain-LoRA](https://huggingface.co/haoranxu/ALMA-7B-Pretrain-LoRA) |
| ALMA-13B | [haoranxu/ALMA-13B](https://huggingface.co/haoranxu/ALMA-13B) | - |
| ALMA-13B-LoRA | [haoranxu/ALMA-13B-Pretrain](https://huggingface.co/haoranxu/ALMA-13B-Pretrain) | [haoranxu/ALMA-13B-Pretrain-LoRA](https://huggingface.co/haoranxu/ALMA-13B-Pretrain-LoRA) |
**Note that `ALMA-7B-Pretrain` and `ALMA-13B-Pretrain` are NOT translation models. They only experience stage 1 monolingual fine-tuning (20B tokens for the 7B model and 12B tokens for the 13B model), and should be utilized in conjunction with their LoRA models for translation purposes.**
A quick start to use our best system (ALMA-13B-LoRA) for translation. An example of translating "我爱机器翻译。" into English:
```
import torch
from peft import PeftModel
from transformers import AutoModelForCausalLM
from transformers import LlamaTokenizer
# Load base model and LoRA weights
model = AutoModelForCausalLM.from_pretrained("haoranxu/ALMA-13B-Pretrain", torch_dtype=torch.float16, device_map="auto")
model = PeftModel.from_pretrained(model, "haoranxu/ALMA-13B-Pretrain-LoRA")
tokenizer = LlamaTokenizer.from_pretrained("haoranxu/ALMA-13B-Pretrain", padding_side='left')
# Add the source setence into the prompt template
prompt="Translate this from Chinese to English:\nChinese: 我爱机器翻译。\nEnglish:"
input_ids = tokenizer(prompt, return_tensors="pt", padding=True, max_length=40, truncation=True).input_ids.cuda()
# Translation
with torch.no_grad():
generated_ids = model.generate(input_ids=input_ids, num_beams=5, max_new_tokens=20, do_sample=True, temperature=0.6, top_p=0.9)
outputs = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)
print(outputs)
```
Please find more details in our [GitHub repository](https://github.com/fe1ixxu/ALMA)
|
leourbina/ppo-LunarLander-V2
|
leourbina
| 2023-10-14T17:38:32Z | 0 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-10-14T17:06:41Z |
---
library_name: stable-baselines3
tags:
- LunarLander-v2
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: PPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: LunarLander-v2
type: LunarLander-v2
metrics:
- type: mean_reward
value: -371.08 +/- 90.69
name: mean_reward
verified: false
---
# **PPO** Agent playing **LunarLander-v2**
This is a trained model of a **PPO** agent playing **LunarLander-v2**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
## Usage (with Stable-baselines3)
TODO: Add your code
```python
from stable_baselines3 import ...
from huggingface_sb3 import load_from_hub
...
```
|
aiknight87/mistralai-7b-new1
|
aiknight87
| 2023-10-14T17:34:27Z | 14 | 0 |
peft
|
[
"peft",
"mistral",
"arxiv:1910.09700",
"base_model:mistralai/Mistral-7B-v0.1",
"base_model:adapter:mistralai/Mistral-7B-v0.1",
"4-bit",
"bitsandbytes",
"region:us"
] | null | 2023-10-14T16:50:19Z |
---
library_name: peft
base_model: mistralai/Mistral-7B-v0.1
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Data Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: bfloat16
### Framework versions
- PEFT 0.6.0.dev0
|
codys12/results
|
codys12
| 2023-10-14T17:25:26Z | 0 | 0 | null |
[
"generated_from_trainer",
"base_model:codellama/CodeLlama-7b-hf",
"base_model:finetune:codellama/CodeLlama-7b-hf",
"license:llama2",
"region:us"
] | null | 2023-10-14T17:25:14Z |
---
license: llama2
base_model: codellama/CodeLlama-7b-hf
tags:
- generated_from_trainer
model-index:
- name: results
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# results
This model is a fine-tuned version of [codellama/CodeLlama-7b-hf](https://huggingface.co/codellama/CodeLlama-7b-hf) on an unknown dataset.
It achieves the following results on the evaluation set:
- eval_loss: 0.8130
- eval_runtime: 8.4572
- eval_samples_per_second: 23.649
- eval_steps_per_second: 2.956
- epoch: 0.01
- step: 21
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 1
### Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
|
lordciciu/roberta-base-finetuned-wikitext2
|
lordciciu
| 2023-10-14T17:03:39Z | 12 | 0 |
transformers
|
[
"transformers",
"pytorch",
"roberta",
"text-generation",
"generated_from_trainer",
"base_model:FacebookAI/roberta-base",
"base_model:finetune:FacebookAI/roberta-base",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-10-14T14:27:43Z |
---
license: mit
base_model: roberta-base
tags:
- generated_from_trainer
model-index:
- name: roberta-base-finetuned-wikitext2
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# roberta-base-finetuned-wikitext2
This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the None dataset.
It achieves the following results on the evaluation set:
- eval_loss: 20.3064
- eval_runtime: 22.2653
- eval_samples_per_second: 89.287
- eval_steps_per_second: 11.183
- step: 0
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
### Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
|
Reangsy/pegasus-xsum-transcript
|
Reangsy
| 2023-10-14T17:01:41Z | 5 | 0 |
transformers
|
[
"transformers",
"pytorch",
"pegasus",
"text2text-generation",
"generated_from_trainer",
"base_model:google/pegasus-xsum",
"base_model:finetune:google/pegasus-xsum",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text2text-generation
| 2023-10-14T16:56:46Z |
---
base_model: google/pegasus-xsum
tags:
- generated_from_trainer
model-index:
- name: pegasus-samsum
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# pegasus-samsum
This model is a fine-tuned version of [google/pegasus-xsum](https://huggingface.co/google/pegasus-xsum) on the None dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 1
### Training results
### Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
|
Nonthachai/Mitr_Chaibancha
|
Nonthachai
| 2023-10-14T17:00:42Z | 0 | 0 |
asteroid
|
[
"asteroid",
"music",
"art",
"en",
"th",
"dataset:Open-Orca/OpenOrca",
"license:artistic-2.0",
"region:us"
] | null | 2023-10-14T16:59:09Z |
---
license: artistic-2.0
datasets:
- Open-Orca/OpenOrca
language:
- en
- th
metrics:
- accuracy
library_name: asteroid
tags:
- music
- art
---
|
digiplay/NightmareShaper_v2DarkageLobotomy
|
digiplay
| 2023-10-14T16:59:13Z | 1,867 | 2 |
diffusers
|
[
"diffusers",
"safetensors",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] |
text-to-image
| 2023-10-12T03:13:29Z |
---
license: other
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
inference: true
---
Model info :
https://civitai.com/models/93249?modelVersionId=126956
|
mozci/typestablediff
|
mozci
| 2023-10-14T16:54:31Z | 0 | 0 |
diffusers
|
[
"diffusers",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"lora",
"base_model:stabilityai/stable-diffusion-2",
"base_model:adapter:stabilityai/stable-diffusion-2",
"license:creativeml-openrail-m",
"region:us"
] |
text-to-image
| 2023-10-09T00:25:59Z |
---
license: creativeml-openrail-m
base_model: stabilityai/stable-diffusion-2
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- lora
inference: true
---
# LoRA text2image fine-tuning - mozci/typestablediff
These are LoRA adaption weights for stabilityai/stable-diffusion-2. The weights were fine-tuned on the mozci/typedb dataset. You can find some example images in the following.
|
NourhanAbosaeed/dummy-model
|
NourhanAbosaeed
| 2023-10-14T16:53:10Z | 4 | 0 |
transformers
|
[
"transformers",
"tf",
"distilbert",
"feature-extraction",
"generated_from_keras_callback",
"base_model:distilbert/distilbert-base-uncased-finetuned-sst-2-english",
"base_model:finetune:distilbert/distilbert-base-uncased-finetuned-sst-2-english",
"license:apache-2.0",
"text-embeddings-inference",
"endpoints_compatible",
"region:us"
] |
feature-extraction
| 2023-10-14T16:51:20Z |
---
license: apache-2.0
base_model: distilbert-base-uncased-finetuned-sst-2-english
tags:
- generated_from_keras_callback
model-index:
- name: dummy-model
results: []
---
<!-- This model card has been generated automatically according to the information Keras had access to. You should
probably proofread and complete it, then remove this comment. -->
# dummy-model
This model is a fine-tuned version of [distilbert-base-uncased-finetuned-sst-2-english](https://huggingface.co/distilbert-base-uncased-finetuned-sst-2-english) on an unknown dataset.
It achieves the following results on the evaluation set:
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- optimizer: None
- training_precision: float32
### Training results
### Framework versions
- Transformers 4.34.0
- TensorFlow 2.13.0
- Datasets 2.14.5
- Tokenizers 0.14.1
|
Subsets and Splits
Filtered Qwen2.5 Distill Models
Identifies specific configurations of models by filtering cards that contain 'distill', 'qwen2.5', '7b' while excluding certain base models and incorrect model ID patterns, uncovering unique model variants.
Filtered Model Cards Count
Finds the count of entries with specific card details that include 'distill', 'qwen2.5', '7b' but exclude certain base models, revealing valuable insights about the dataset's content distribution.
Filtered Distill Qwen 7B Models
Filters for specific card entries containing 'distill', 'qwen', and '7b', excluding certain strings and patterns, to identify relevant model configurations.
Filtered Qwen-7b Model Cards
The query performs a detailed filtering based on specific keywords and excludes certain entries, which could be useful for identifying a specific subset of cards but does not provide deeper insights or trends.
Filtered Qwen 7B Model Cards
The query filters for specific terms related to "distilled" or "distill", "qwen", and "7b" in the 'card' column but excludes certain base models, providing a limited set of entries for further inspection.
Qwen 7B Distilled Models
The query provides a basic filtering of records to find specific card names that include keywords related to distilled Qwen 7b models, excluding a particular base model, which gives limited insight but helps in focusing on relevant entries.
Qwen 7B Distilled Model Cards
The query filters data based on specific keywords in the modelId and card fields, providing limited insight primarily useful for locating specific entries rather than revealing broad patterns or trends.
Qwen 7B Distilled Models
Finds all entries containing the terms 'distilled', 'qwen', and '7b' in a case-insensitive manner, providing a filtered set of records but without deeper analysis.
Distilled Qwen 7B Models
The query filters for specific model IDs containing 'distilled', 'qwen', and '7b', providing a basic retrieval of relevant entries but without deeper analysis or insight.
Filtered Model Cards with Distill Qwen2.
Filters and retrieves records containing specific keywords in the card description while excluding certain phrases, providing a basic count of relevant entries.
Filtered Model Cards with Distill Qwen 7
The query filters specific variations of card descriptions containing 'distill', 'qwen', and '7b' while excluding a particular base model, providing limited but specific data retrieval.
Distill Qwen 7B Model Cards
The query filters and retrieves rows where the 'card' column contains specific keywords ('distill', 'qwen', and '7b'), providing a basic filter result that can help in identifying specific entries.