modelId
stringlengths 5
139
| author
stringlengths 2
42
| last_modified
timestamp[us, tz=UTC]date 2020-02-15 11:33:14
2025-09-03 12:31:03
| downloads
int64 0
223M
| likes
int64 0
11.7k
| library_name
stringclasses 537
values | tags
listlengths 1
4.05k
| pipeline_tag
stringclasses 55
values | createdAt
timestamp[us, tz=UTC]date 2022-03-02 23:29:04
2025-09-03 12:30:52
| card
stringlengths 11
1.01M
|
|---|---|---|---|---|---|---|---|---|---|
ahe61/my-awesome-setfit-model
|
ahe61
| 2024-05-21T11:41:35Z | 5 | 0 |
setfit
|
[
"setfit",
"safetensors",
"mpnet",
"sentence-transformers",
"text-classification",
"generated_from_setfit_trainer",
"arxiv:2209.11055",
"base_model:sentence-transformers/paraphrase-mpnet-base-v2",
"base_model:finetune:sentence-transformers/paraphrase-mpnet-base-v2",
"model-index",
"region:us"
] |
text-classification
| 2024-05-21T11:41:18Z |
---
library_name: setfit
tags:
- setfit
- sentence-transformers
- text-classification
- generated_from_setfit_trainer
base_model: sentence-transformers/paraphrase-mpnet-base-v2
metrics:
- accuracy
widget:
- text: 'a literate presentation that wonderfully weaves a murderous event in 1873
with murderous rage in 2002 . '
- text: 'an entertaining , colorful , action-filled crime story with an intimate heart
. '
- text: 'drops you into a dizzying , volatile , pressure-cooker of a situation that
quickly snowballs out of control , while focusing on the what much more than the
why . '
- text: 'the most compelling wiseman epic of recent years . '
- text: 'in the end , the movie collapses on its shaky foundation despite the best
efforts of director joe carnahan . '
pipeline_tag: text-classification
inference: true
model-index:
- name: SetFit with sentence-transformers/paraphrase-mpnet-base-v2
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: Unknown
type: unknown
split: test
metrics:
- type: accuracy
value: 0.8589449541284404
name: Accuracy
---
# SetFit with sentence-transformers/paraphrase-mpnet-base-v2
This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [sentence-transformers/paraphrase-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-mpnet-base-v2) as the Sentence Transformer embedding model. A [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance is used for classification.
The model has been trained using an efficient few-shot learning technique that involves:
1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
2. Training a classification head with features from the fine-tuned Sentence Transformer.
## Model Details
### Model Description
- **Model Type:** SetFit
- **Sentence Transformer body:** [sentence-transformers/paraphrase-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-mpnet-base-v2)
- **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
- **Maximum Sequence Length:** 512 tokens
- **Number of Classes:** 2 classes
<!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
<!-- - **Language:** Unknown -->
<!-- - **License:** Unknown -->
### Model Sources
- **Repository:** [SetFit on GitHub](https://github.com/huggingface/setfit)
- **Paper:** [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055)
- **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
### Model Labels
| Label | Examples |
|:------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| 0 | <ul><li>'stale and uninspired . '</li><li>"the film 's considered approach to its subject matter is too calm and thoughtful for agitprop , and the thinness of its characterizations makes it a failure as straight drama . ' "</li><li>"that their charm does n't do a load of good "</li></ul> |
| 1 | <ul><li>"broomfield is energized by volletta wallace 's maternal fury , her fearlessness "</li><li>'flawless '</li><li>'insightfully written , delicately performed '</li></ul> |
## Evaluation
### Metrics
| Label | Accuracy |
|:--------|:---------|
| **all** | 0.8589 |
## Uses
### Direct Use for Inference
First install the SetFit library:
```bash
pip install setfit
```
Then you can load this model and run inference.
```python
from setfit import SetFitModel
# Download from the 🤗 Hub
model = SetFitModel.from_pretrained("ahe61/my-awesome-setfit-model")
# Run inference
preds = model("the most compelling wiseman epic of recent years . ")
```
<!--
### Downstream Use
*List how someone could finetune this model on their own dataset.*
-->
<!--
### Out-of-Scope Use
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
-->
<!--
## Bias, Risks and Limitations
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
-->
<!--
### Recommendations
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
-->
## Training Details
### Training Set Metrics
| Training set | Min | Median | Max |
|:-------------|:----|:--------|:----|
| Word count | 2 | 11.4375 | 33 |
| Label | Training Sample Count |
|:------|:----------------------|
| 0 | 8 |
| 1 | 8 |
### Training Hyperparameters
- batch_size: (16, 16)
- num_epochs: (1, 1)
- max_steps: -1
- sampling_strategy: oversampling
- num_iterations: 20
- body_learning_rate: (2e-05, 2e-05)
- head_learning_rate: 2e-05
- loss: CosineSimilarityLoss
- distance_metric: cosine_distance
- margin: 0.25
- end_to_end: False
- use_amp: False
- warmup_proportion: 0.1
- seed: 42
- eval_max_steps: -1
- load_best_model_at_end: False
### Training Results
| Epoch | Step | Training Loss | Validation Loss |
|:-----:|:----:|:-------------:|:---------------:|
| 0.025 | 1 | 0.2054 | - |
### Framework Versions
- Python: 3.10.12
- SetFit: 1.0.3
- Sentence Transformers: 2.7.0
- Transformers: 4.40.2
- PyTorch: 2.2.1+cu121
- Datasets: 2.19.1
- Tokenizers: 0.19.1
## Citation
### BibTeX
```bibtex
@article{https://doi.org/10.48550/arxiv.2209.11055,
doi = {10.48550/ARXIV.2209.11055},
url = {https://arxiv.org/abs/2209.11055},
author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
title = {Efficient Few-Shot Learning Without Prompts},
publisher = {arXiv},
year = {2022},
copyright = {Creative Commons Attribution 4.0 International}
}
```
<!--
## Glossary
*Clearly define terms in order to be accessible across audiences.*
-->
<!--
## Model Card Authors
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
-->
<!--
## Model Card Contact
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
-->
|
Ramikan-BR/tinyllama-coder-py-4bit_LORA-v3
|
Ramikan-BR
| 2024-05-21T11:40:45Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"text-generation-inference",
"unsloth",
"llama",
"trl",
"en",
"base_model:unsloth/tinyllama-chat-bnb-4bit",
"base_model:finetune:unsloth/tinyllama-chat-bnb-4bit",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2024-05-21T11:40:12Z |
---
language:
- en
license: apache-2.0
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
base_model: unsloth/tinyllama-chat-bnb-4bit
---
# Uploaded model
- **Developed by:** Ramikan-BR
- **License:** apache-2.0
- **Finetuned from model :** unsloth/tinyllama-chat-bnb-4bit
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
HigginsAI/GrepBiasLlama
|
HigginsAI
| 2024-05-21T11:35:27Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"text-generation-inference",
"unsloth",
"llama",
"trl",
"en",
"base_model:unsloth/llama-3-8b-bnb-4bit",
"base_model:finetune:unsloth/llama-3-8b-bnb-4bit",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2024-05-21T11:34:55Z |
---
language:
- en
license: apache-2.0
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
base_model: unsloth/llama-3-8b-bnb-4bit
---
# Uploaded model
- **Developed by:** HigginsAI
- **License:** apache-2.0
- **Finetuned from model :** unsloth/llama-3-8b-bnb-4bit
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
JoshuaKelleyDs/quickdraw-DeiT-Distilled-tiny-finetune
|
JoshuaKelleyDs
| 2024-05-21T11:34:10Z | 202 | 0 |
transformers
|
[
"transformers",
"onnx",
"safetensors",
"deit",
"image-classification",
"generated_from_trainer",
"base_model:facebook/deit-tiny-distilled-patch16-224",
"base_model:quantized:facebook/deit-tiny-distilled-patch16-224",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
image-classification
| 2024-05-21T04:47:27Z |
---
license: apache-2.0
base_model: facebook/deit-tiny-distilled-patch16-224
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: quickdraw-DeiT-tiny-c
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. -->
# quickdraw-DeiT-tiny-c
This model is a fine-tuned version of [facebook/deit-tiny-distilled-patch16-224](https://huggingface.co/facebook/deit-tiny-distilled-patch16-224) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.8784
- Accuracy: 0.7849
## 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: 0.0008
- train_batch_size: 512
- eval_batch_size: 512
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 10000
- num_epochs: 8
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:------:|:-----:|:---------------:|:--------:|
| 1.2697 | 0.5688 | 5000 | 1.2368 | 0.6883 |
| 1.1262 | 1.1377 | 10000 | 1.1299 | 0.7127 |
| 1.0215 | 1.7065 | 15000 | 1.0110 | 0.7403 |
| 0.939 | 2.2753 | 20000 | 0.9628 | 0.7521 |
| 0.9129 | 2.8441 | 25000 | 0.9281 | 0.7606 |
| 0.8507 | 3.4130 | 30000 | 0.8973 | 0.7687 |
| 0.8354 | 3.9818 | 35000 | 0.8696 | 0.7752 |
| 0.7773 | 4.5506 | 40000 | 0.8575 | 0.7791 |
| 0.7011 | 5.1195 | 45000 | 0.8497 | 0.7829 |
| 0.6989 | 5.6883 | 50000 | 0.8350 | 0.7860 |
| 0.624 | 6.2571 | 55000 | 0.8524 | 0.7857 |
| 0.6245 | 6.8259 | 60000 | 0.8499 | 0.7874 |
| 0.565 | 7.3948 | 65000 | 0.8795 | 0.7849 |
| 0.5663 | 7.9636 | 70000 | 0.8784 | 0.7849 |
### Framework versions
- Transformers 4.41.0
- Pytorch 2.2.1
- Datasets 2.19.1
- Tokenizers 0.19.1
|
Dominic0406/convai2_gpt2
|
Dominic0406
| 2024-05-21T11:32:44Z | 137 | 0 |
transformers
|
[
"transformers",
"safetensors",
"gpt2",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2024-05-21T11:32:29Z |
---
library_name: transformers
tags: []
---
# 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. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **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]
|
wangzhekd/blip-opt-2.7b-football-alltest
|
wangzhekd
| 2024-05-21T11:31:53Z | 62 | 0 |
transformers
|
[
"transformers",
"safetensors",
"blip",
"image-text-to-text",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] |
image-text-to-text
| 2024-05-12T09:14:17Z |
---
library_name: transformers
tags: []
---
# 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. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **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]
|
Ja3ffar/superior-MistCard
|
Ja3ffar
| 2024-05-21T11:31:15Z | 0 | 0 |
peft
|
[
"peft",
"safetensors",
"arxiv:1910.09700",
"base_model:mistralai/Mistral-7B-Instruct-v0.2",
"base_model:adapter:mistralai/Mistral-7B-Instruct-v0.2",
"region:us"
] | null | 2024-05-20T12:34:48Z |
---
library_name: peft
base_model: mistralai/Mistral-7B-Instruct-v0.2
---
# 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]
### Framework versions
- PEFT 0.11.1
|
Dhahlan2000/Translation-GPT-v4
|
Dhahlan2000
| 2024-05-21T11:30:26Z | 61 | 0 |
transformers
|
[
"transformers",
"tf",
"mt5",
"text2text-generation",
"generated_from_keras_callback",
"base_model:Dhahlan2000/Translation-GPT-v3",
"base_model:finetune:Dhahlan2000/Translation-GPT-v3",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text2text-generation
| 2024-05-21T11:29:05Z |
---
license: apache-2.0
tags:
- generated_from_keras_callback
base_model: Dhahlan2000/Translation-GPT-v3
model-index:
- name: Translation-GPT-v4
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. -->
# Translation-GPT-v4
This model is a fine-tuned version of [Dhahlan2000/Translation-GPT-v3](https://huggingface.co/Dhahlan2000/Translation-GPT-v3) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 2.8506
- Validation Loss: 2.2484
- Epoch: 1
## 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': 'AdamWeightDecay', 'learning_rate': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
- training_precision: float32
### Training results
| Train Loss | Validation Loss | Epoch |
|:----------:|:---------------:|:-----:|
| 3.0246 | 2.3872 | 0 |
| 2.8506 | 2.2484 | 1 |
### Framework versions
- Transformers 4.40.2
- TensorFlow 2.15.0
- Datasets 2.17.0
- Tokenizers 0.19.1
|
MohamedSaeed-dev/gemma-2b-1500steps
|
MohamedSaeed-dev
| 2024-05-21T11:27:35Z | 136 | 0 |
transformers
|
[
"transformers",
"pytorch",
"gemma",
"text-generation",
"unsloth",
"trl",
"sft",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2024-05-21T11:21:36Z |
---
library_name: transformers
tags:
- unsloth
- trl
- sft
---
# 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. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **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]
|
Qyzi/bert-finetuned-ner
|
Qyzi
| 2024-05-21T11:27:20Z | 105 | 0 |
transformers
|
[
"transformers",
"tensorboard",
"safetensors",
"bert",
"token-classification",
"generated_from_trainer",
"dataset:conll2003",
"base_model:google-bert/bert-base-cased",
"base_model:finetune:google-bert/bert-base-cased",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
token-classification
| 2024-05-21T08:37:20Z |
---
license: apache-2.0
base_model: bert-base-cased
tags:
- generated_from_trainer
datasets:
- conll2003
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: bert-finetuned-ner
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: conll2003
type: conll2003
config: conll2003
split: validation
args: conll2003
metrics:
- name: Precision
type: precision
value: 0.9355853618148701
- name: Recall
type: recall
value: 0.9508582968697409
- name: F1
type: f1
value: 0.9431600033386196
- name: Accuracy
type: accuracy
value: 0.9866221227997881
---
<!-- 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-ner
This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the conll2003 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0629
- Precision: 0.9356
- Recall: 0.9509
- F1: 0.9432
- Accuracy: 0.9866
## 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
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| 0.0743 | 1.0 | 1756 | 0.0638 | 0.9066 | 0.9325 | 0.9194 | 0.9814 |
| 0.0354 | 2.0 | 3512 | 0.0688 | 0.9325 | 0.9460 | 0.9392 | 0.9849 |
| 0.0225 | 3.0 | 5268 | 0.0629 | 0.9356 | 0.9509 | 0.9432 | 0.9866 |
### Framework versions
- Transformers 4.41.0
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
|
arjuntheprogrammer/llama3-8b-oig-unsloth
|
arjuntheprogrammer
| 2024-05-21T11:24:34Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"text-generation-inference",
"unsloth",
"llama",
"trl",
"en",
"base_model:unsloth/llama-3-8b-bnb-4bit",
"base_model:finetune:unsloth/llama-3-8b-bnb-4bit",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2024-05-21T11:24:04Z |
---
language:
- en
license: apache-2.0
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
base_model: unsloth/llama-3-8b-bnb-4bit
---
# Uploaded model
- **Developed by:** arjuntheprogrammer
- **License:** apache-2.0
- **Finetuned from model :** unsloth/llama-3-8b-bnb-4bit
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
krispychicken/openai-whisper-medium.en-colab
|
krispychicken
| 2024-05-21T11:18:43Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2024-05-21T11:18:37Z |
---
library_name: transformers
tags: []
---
# 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. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **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]
|
himadhithv/serv_360_v2
|
himadhithv
| 2024-05-21T11:13:40Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"text-generation-inference",
"unsloth",
"llama",
"trl",
"en",
"base_model:unsloth/llama-3-8b-bnb-4bit",
"base_model:finetune:unsloth/llama-3-8b-bnb-4bit",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2024-05-21T10:35:06Z |
---
language:
- en
license: apache-2.0
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
base_model: unsloth/llama-3-8b-bnb-4bit
---
# Uploaded model
- **Developed by:** himadhithv
- **License:** apache-2.0
- **Finetuned from model :** unsloth/llama-3-8b-bnb-4bit
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
botbot-ai/Cabra-72b
|
botbot-ai
| 2024-05-21T11:13:18Z | 21 | 4 |
transformers
|
[
"transformers",
"safetensors",
"qwen2",
"text-generation",
"text-generation-inference",
"qwen",
"gguf",
"brazil",
"brasil",
"72bb",
"portuguese",
"conversational",
"pt",
"en",
"base_model:Qwen/Qwen1.5-72B-Chat",
"base_model:finetune:Qwen/Qwen1.5-72B-Chat",
"license:cc-by-nc-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2024-04-03T04:22:49Z |
---
language:
- pt
- en
license: cc-by-nc-2.0
tags:
- text-generation-inference
- transformers
- qwen
- gguf
- brazil
- brasil
- 72bb
- portuguese
base_model: Qwen/Qwen1.5-72B-Chat
pipeline_tag: text-generation
model-index:
- name: Cabra-72b
results:
- task:
type: text-generation
name: Text Generation
dataset:
name: ENEM Challenge (No Images)
type: eduagarcia/enem_challenge
split: train
args:
num_few_shot: 3
metrics:
- type: acc
value: 80.62
name: accuracy
source:
url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=botbot-ai/Cabra-72b
name: Open Portuguese LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: BLUEX (No Images)
type: eduagarcia-temp/BLUEX_without_images
split: train
args:
num_few_shot: 3
metrics:
- type: acc
value: 67.45
name: accuracy
source:
url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=botbot-ai/Cabra-72b
name: Open Portuguese LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: OAB Exams
type: eduagarcia/oab_exams
split: train
args:
num_few_shot: 3
metrics:
- type: acc
value: 57.18
name: accuracy
source:
url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=botbot-ai/Cabra-72b
name: Open Portuguese LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: Assin2 RTE
type: assin2
split: test
args:
num_few_shot: 15
metrics:
- type: f1_macro
value: 93.58
name: f1-macro
source:
url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=botbot-ai/Cabra-72b
name: Open Portuguese LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: Assin2 STS
type: eduagarcia/portuguese_benchmark
split: test
args:
num_few_shot: 15
metrics:
- type: pearson
value: 78.03
name: pearson
source:
url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=botbot-ai/Cabra-72b
name: Open Portuguese LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: FaQuAD NLI
type: ruanchaves/faquad-nli
split: test
args:
num_few_shot: 15
metrics:
- type: f1_macro
value: 45.45
name: f1-macro
source:
url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=botbot-ai/Cabra-72b
name: Open Portuguese LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: HateBR Binary
type: ruanchaves/hatebr
split: test
args:
num_few_shot: 25
metrics:
- type: f1_macro
value: 72.12
name: f1-macro
source:
url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=botbot-ai/Cabra-72b
name: Open Portuguese LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: PT Hate Speech Binary
type: hate_speech_portuguese
split: test
args:
num_few_shot: 25
metrics:
- type: f1_macro
value: 68.65
name: f1-macro
source:
url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=botbot-ai/Cabra-72b
name: Open Portuguese LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: tweetSentBR
type: eduagarcia/tweetsentbr_fewshot
split: test
args:
num_few_shot: 25
metrics:
- type: f1_macro
value: 71.64
name: f1-macro
source:
url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=botbot-ai/Cabra-72b
name: Open Portuguese LLM Leaderboard
---
# Cabra 72b
<img src="https://uploads-ssl.webflow.com/65f77c0240ae1c68f8192771/6611c4d5c4e2b5eaea0b979c_cabra72b.png" width="400" height="400">
Cabra 72b é um finetune do [Qwen 1.5 72b Chat](https://huggingface.co/Qwen/Qwen1.5-72B-Chat) com o dataset Cabra 30k. Esse modelo é otimizado para português e responde em portuguese. Ele apresenta melhoria em vários benchmarks brasileiros em comparação com o modelo base.
**Conheça os nossos outros [modelos Cabra](https://huggingface.co/collections/botbot-ai/models-6604c2069ceef04f834ba99b).**
## Detalhes do modelo base
### Modelo: Qwen 1.5 72b chat
Qwen1.5 é uma série de modelos de linguagem que inclui modelos de linguagem decodificadores de diferentes tamanhos de modelo. Para cada tamanho, lançamos o modelo de linguagem base e o modelo de chat alinhado. Baseia-se na arquitetura Transformer com ativação SwiGLU, viés de atenção QKV, atenção de consulta em grupo, mistura de atenção de janela deslizante e atenção completa, etc. Adicionalmente, temos um tokenizador melhorado adaptativo a múltiplas línguas naturais e códigos. Para a versão beta, temporariamente não incluímos GQA e a mistura de SWA e atenção completa.
### dataset: Cabra 30k
Dataset interno para fine-tuning. Vamos lançar em breve.
### Quantização / GGUF
Colocamos diversas versões (GGUF) quantanizadas no branch "quantanization". Infelizmente o HF limita o tamanho de arquivo a <50gb.
### Exemplo
```
<s> [INST]Quem são os jogadores brasileiros de futebol mais conhecidos, atuais e pasados? [/INST]
O Brasil tem uma rica história na produção de alguns dos maiores jogadores de futebol do mundo. Alguns dos jogadores brasileiros mais importantes atualmente e que já jogaram incluem:
Pelé - amplamente considerado um dos maiores jogadores de todos os tempos, o Pelé venceu três Copas do Mundo com o Brasil e marcou mais de 1.000 gols em sua carreira.
Ronaldo Nazário de Lima - conhecido como Ronaldo, este jogador de ataque é o segundo maior artilheiro da história da seleção brasileira e ajudou o Brasil a vencer duas Copas do Mundo.
Ronaldinho Gaúcho - um criativo meio-campista ofensivo que jogou pelo Barcelona e pela AC Milan, o Ronaldinho foi nomeado Jogador Mundial FIFA de 2004 e ajudou o Brasil a vencer a Copa do Mundo de 2002.
Neymar Jr. - um dos melhores jogadores do mundo hoje, o Neymar desempenhou um papel fundamental ao liderar o Brasil para várias vitórias em torneios principais e é conhecido por suas habilidades incríveis de drible e capacidade de marcar gols.
Esses são apenas alguns exemplos dos muitos talentosos jogadores de futebol que vieram do Brasil ao longo de sua rica história.
</s>
```
### Paramentros de trainamento
```
- train/epoch: 3
- train/global_step: 1,893
- train/grad_norm: 0.5843151168226935
- train/learning_rate: 0.00000000006323276533
- train/loss: 0.4379
- train/total_flos: 7,334,660,338,089,984
- train/train_loss: 0.628420232404053
- train/train_runtime: 415,863.2395
- train/train_samples_per_second: 0.437
- train/train_steps_per_second: 0.005
- GPU: 8x A100 80GB SXB
```
### Framework
- Transformers 4.39.0.dev0
- Pytorch 2.1.2+cu118
- Datasets 2.14.6
- Tokenizers 0.15.2
## Uso
O modelo é destinado, por agora, a fins de pesquisa. As áreas e tarefas de pesquisa possíveis incluem:
- Pesquisa sobre modelos gerativos.
- Investigação e compreensão das limitações e vieses de modelos gerativos.
**Proibido para uso comercial. Somente Pesquisa. Entre em contato para mais informações. **
### Evals
| Tasks | Version | Filter | n-shot | Metric | Value | ± | Stderr |
|------------------------------|---------|-----------------------|--------|----------|-------|----|--------|
| assin2_rte | 1.1 | all | 15 | f1_macro | 0.9358| ± | 0.0035 |
| | | all | 15 | acc | 0.9359| ± | 0.0035 |
| assin2_sts | 1.1 | all | 15 | pearson | 0.7803| ± | 0.0068 |
| | | all | 15 | mse | 0.5815| ± | N/A |
| bluex | 1.1 | all | 3 | acc | 0.6745| ± | 0.0101 |
| | | exam_id__USP_2019 | 3 | acc | 0.5500| ± | 0.0453 |
| | | exam_id__UNICAMP_2021_1| 3 | acc | 0.5870| ± | 0.0418 |
| | | exam_id__USP_2020 | 3 | acc | 0.6250| ± | 0.0373 |
| | | exam_id__USP_2022 | 3 | acc | 0.6939| ± | 0.0381 |
| | | exam_id__UNICAMP_2019 | 3 | acc | 0.7200| ± | 0.0367 |
| | | exam_id__UNICAMP_2024 | 3 | acc | 0.5778| ± | 0.0425 |
| | | exam_id__USP_2018 | 3 | acc | 0.5926| ± | 0.0385 |
| | | exam_id__USP_2021 | 3 | acc | 0.6538| ± | 0.0381 |
| | | exam_id__UNICAMP_2023 | 3 | acc | 0.7442| ± | 0.0385 |
| | | exam_id__UNICAMP_2021_2| 3 | acc | 0.6667| ± | 0.0380 |
| | | exam_id__UNICAMP_2020 | 3 | acc | 0.7091| ± | 0.0355 |
| | | exam_id__USP_2023 | 3 | acc | 0.8182| ± | 0.0336 |
| | | exam_id__USP_2024 | 3 | acc | 0.8537| ± | 0.0318 |
| | | exam_id__UNICAMP_2022 | 3 | acc | 0.6667| ± | 0.0435 |
| | | exam_id__UNICAMP_2018 | 3 | acc | 0.6852| ± | 0.0364 |
| enem | 1.1 | all | 3 | acc | 0.8062| ± | 0.0060 |
| | | exam_id__2016_2 | 3 | acc | 0.7967| ± | 0.0210 |
| | | exam_id__2014 | 3 | acc | 0.8165| ± | 0.0214 |
| | | exam_id__2010 | 3 | acc | 0.8291| ± | 0.0202 |
| | | exam_id__2023 | 3 | acc | 0.8000| ± | 0.0199 |
| | | exam_id__2009 | 3 | acc | 0.7913| ± | 0.0219 |
| | | exam_id__2017 | 3 | acc | 0.7931| ± | 0.0217 |
| | | exam_id__2011 | 3 | acc | 0.8718| ± | 0.0178 |
| | | exam_id__2015 | 3 | acc | 0.8151| ± | 0.0205 |
| | | exam_id__2012 | 3 | acc | 0.8621| ± | 0.0185 |
| | | exam_id__2016 | 3 | acc | 0.8430| ± | 0.0190 |
| | | exam_id__2013 | 3 | acc | 0.7870| ± | 0.0228 |
| | | exam_id__2022 | 3 | acc | 0.6842| ± | 0.0233 |
| faquad_nli | 1.1 | all | 15 | f1_macro | 0.4545| ± | 0.0081 |
| | | all | 15 | acc | 0.7877| ± | 0.0113 |
| hatebr_offensive_binary | 1.0 | all | 25 | f1_macro | 0.7212| ± | 0.0087 |
| | | all | 25 | acc | 0.7393| ± | 0.0083 |
| oab_exams | 1.5 | all | 3 | acc | 0.5718| ± | 0.0061 |
# Open Portuguese LLM Leaderboard Evaluation Results
Detailed results can be found [here](https://huggingface.co/datasets/eduagarcia-temp/llm_pt_leaderboard_raw_results/tree/main/botbot-ai/Cabra-72b) and on the [🚀 Open Portuguese LLM Leaderboard](https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard)
| Metric | Value |
|--------------------------|---------|
|Average |**70.52**|
|ENEM Challenge (No Images)| 80.62|
|BLUEX (No Images) | 67.45|
|OAB Exams | 57.18|
|Assin2 RTE | 93.58|
|Assin2 STS | 78.03|
|FaQuAD NLI | 45.45|
|HateBR Binary | 72.12|
|PT Hate Speech Binary | 68.65|
|tweetSentBR | 71.64|
|
SunnyAxe/bert_NER_task
|
SunnyAxe
| 2024-05-21T11:12:12Z | 106 | 0 |
transformers
|
[
"transformers",
"pytorch",
"bert",
"token-classification",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
token-classification
| 2024-05-21T10:41:04Z |
# Introduction
本模型是在SRTP项目中，为中文文学领域文献摘要的命名实体识别（人名、国名与书名）任务而训练的基于RoBERT的模型。
# Format of input and output
input最大长度128。
input: 文本；output: 与文本长度对应、位置对应的标记，标记有如下七种：
{'O': 无标记, 'B-PER': 人名开始标记, 'I-PER': 人名中间标记, 'B-CNT': 国名开始标记, 'I-CNT': 国名中间标记, 'B-BK': 书名开始标记, 'I-BK': 书名中间标记}
例如：
input: 谢默斯・希尼是当代爱尔兰著名诗人
output: B-PER I-PER I-PER I-PER I-PER I-PER O O O B-CNT I-CNT I-CNT O O O O O
另外，由于模型能力有限，在推理过程中可能遇到识别出来的实体标记直接从"I-"开始，建议将第一个标记向前一个文字作为对应的"B-"标记。
如：爱尔兰 --推理--> O I-CNT I-CNT --后续处理--> B-CNT I-CNT I-CNT
|
SunnyAxe/bert_country_infer
|
SunnyAxe
| 2024-05-21T11:10:04Z | 108 | 0 |
transformers
|
[
"transformers",
"safetensors",
"bert",
"text-classification",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2024-05-21T11:02:33Z |
# Introduction
本模型是在SRTP项目中，为中文文学领域文献的国别板块推理任务而训练的基于BERT的模型。
# Format of input and output
input文本最大长度150，label个数11。
label与推理出的数值对应如下：
{0: '比较文学', 1: '大洋洲', 2: '东欧、北欧', 3: '翻译研究', 4: '非洲', 5: '加拿大及其他美洲国家', 6: '美国', 7: '文艺理论与批评', 8: '西欧', 9: '亚洲', 10: '中欧、南欧'}
input: 论文标题+论文关键词+论文摘要（拼接） output: 板块（0~10）
|
adriansanz/FS_25_05
|
adriansanz
| 2024-05-21T11:07:50Z | 108 | 0 |
transformers
|
[
"transformers",
"tensorboard",
"safetensors",
"roberta",
"text-classification",
"generated_from_trainer",
"base_model:projecte-aina/roberta-base-ca-v2",
"base_model:finetune:projecte-aina/roberta-base-ca-v2",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2024-05-20T12:19:08Z |
---
license: apache-2.0
base_model: projecte-aina/roberta-base-ca-v2
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: FS_25_05
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. -->
# FS_25_05
This model is a fine-tuned version of [projecte-aina/roberta-base-ca-v2](https://huggingface.co/projecte-aina/roberta-base-ca-v2) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1403
- Accuracy: 0.9745
- Precision: 0.9751
- Recall: 0.9743
- F1: 0.9744
- Ratio: 0.0529
## 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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 5
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | Ratio |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|:------:|
| 1.7313 | 1.0 | 362 | 1.5891 | 0.9137 | 0.9237 | 0.9138 | 0.9148 | 0.0569 |
| 0.3284 | 2.0 | 724 | 0.2812 | 0.9529 | 0.9560 | 0.9528 | 0.9533 | 0.0490 |
| 0.103 | 3.0 | 1086 | 0.1580 | 0.9667 | 0.9681 | 0.9665 | 0.9663 | 0.0510 |
| 0.1073 | 4.0 | 1448 | 0.1532 | 0.9686 | 0.9693 | 0.9685 | 0.9686 | 0.0529 |
| 0.1295 | 5.0 | 1810 | 0.1403 | 0.9745 | 0.9751 | 0.9743 | 0.9744 | 0.0529 |
### Framework versions
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
|
dickdiss/llama3_qlora
|
dickdiss
| 2024-05-21T11:01:41Z | 0 | 1 |
transformers
|
[
"transformers",
"safetensors",
"trl",
"sft",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2024-05-16T03:46:44Z |
---
library_name: transformers
tags:
- trl
- sft
---
# 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. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **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]
|
KangXen/enta-st-xlmr
|
KangXen
| 2024-05-21T11:00:34Z | 165 | 0 |
transformers
|
[
"transformers",
"safetensors",
"xlm-roberta",
"text-classification",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2024-05-21T10:59:50Z |
---
library_name: transformers
tags: []
---
# 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. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **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]
|
NLP-FEUP/DA-FT-distilbert-base-uncased
|
NLP-FEUP
| 2024-05-21T11:00:15Z | 121 | 0 |
transformers
|
[
"transformers",
"safetensors",
"distilbert",
"text-classification",
"generated_from_trainer",
"base_model:NLP-FEUP/DA-distilbert-base-uncased",
"base_model:finetune:NLP-FEUP/DA-distilbert-base-uncased",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2024-05-20T15:19:06Z |
---
license: apache-2.0
base_model: NLP-FEUP/DA-distilbert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: DA-FT-distilbert-base-uncased
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. -->
# DA-FT-distilbert-base-uncased
This model is a fine-tuned version of [NLP-FEUP/DA-distilbert-base-uncased](https://huggingface.co/NLP-FEUP/DA-distilbert-base-uncased) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6205
- Accuracy: 0.725
## 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
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| No log | 1.0 | 40 | 0.6767 | 0.625 |
| No log | 2.0 | 80 | 0.6476 | 0.675 |
| No log | 3.0 | 120 | 0.6205 | 0.725 |
### Framework versions
- Transformers 4.41.0
- Pytorch 2.3.0
- Datasets 2.19.1
- Tokenizers 0.19.1
|
bhoopendrakumar/passport_330
|
bhoopendrakumar
| 2024-05-21T10:59:22Z | 48 | 0 |
transformers
|
[
"transformers",
"safetensors",
"vision-encoder-decoder",
"image-text-to-text",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] |
image-text-to-text
| 2024-05-21T10:56:34Z |
---
library_name: transformers
tags: []
---
# 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. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **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]
|
KitsuneX07/so-vits-svc4.1_mosquito
|
KitsuneX07
| 2024-05-21T10:58:42Z | 0 | 2 | null |
[
"license:cc-by-nc-sa-4.0",
"region:us"
] | null | 2024-05-21T10:54:22Z |
---
license: cc-by-nc-sa-4.0
---
Offcial Website：https://github.com/svc-develop-team/so-vits-svc
|
LinStevenn/model8bit_itri_0
|
LinStevenn
| 2024-05-21T10:52:11Z | 6 | 0 |
transformers
|
[
"transformers",
"gguf",
"llama",
"text-generation-inference",
"unsloth",
"en",
"base_model:unsloth/llama-3-8b-bnb-4bit",
"base_model:quantized:unsloth/llama-3-8b-bnb-4bit",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2024-05-21T10:36:48Z |
---
language:
- en
license: apache-2.0
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- gguf
base_model: unsloth/llama-3-8b-bnb-4bit
---
# Uploaded model
- **Developed by:** LinStevenn
- **License:** apache-2.0
- **Finetuned from model :** unsloth/llama-3-8b-bnb-4bit
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
abzoo/llama3-finetuned-Pima-Indians-Diabetes
|
abzoo
| 2024-05-21T10:51:55Z | 0 | 1 | null |
[
"safetensors",
"license:apache-2.0",
"region:us"
] | null | 2024-05-21T10:28:36Z |
---
license: apache-2.0
---
## Model
I used the finetuning notebook offerd by [unsloth](https://github.com/unslothai/unsloth).
Complete notebook can be found in ```notebooks/Create_synthetic_dataset``` or on [GoogleColab](https://colab.research.google.com/drive/1iSAv8jwN3-fV9NVGqd_xEgAnu4p7kttq?usp=sharing)
## Data
The dataset was created using an existing dataset [Pima Indians Diabetes Database](https://www.kaggle.com/datasets/uciml/pima-indians-diabetes-database)
The steps to create and produce the data was as follows:
1. Turn every column of the dataset into into text description of the patient using prepared text templates.
2. Prompt gpt4-o asking for a complete analysis, detailed illustration and diagnostics.
3. Use gpt4-o output to train a smaller model like llama 8b
|
MaziyarPanahi/T3qInex12-7B-GGUF
|
MaziyarPanahi
| 2024-05-21T10:49:27Z | 81 | 0 |
transformers
|
[
"transformers",
"gguf",
"mistral",
"quantized",
"2-bit",
"3-bit",
"4-bit",
"5-bit",
"6-bit",
"8-bit",
"GGUF",
"safetensors",
"text-generation",
"merge",
"mergekit",
"lazymergekit",
"automerger",
"base_model:chihoonlee10/T3Q-Mistral-Orca-Math-DPO",
"base_model:MSL7/INEX12-7b",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us",
"base_model:automerger/T3qInex12-7B",
"base_model:quantized:automerger/T3qInex12-7B"
] |
text-generation
| 2024-05-21T10:20:39Z |
---
tags:
- quantized
- 2-bit
- 3-bit
- 4-bit
- 5-bit
- 6-bit
- 8-bit
- GGUF
- transformers
- safetensors
- mistral
- text-generation
- merge
- mergekit
- lazymergekit
- automerger
- base_model:chihoonlee10/T3Q-Mistral-Orca-Math-DPO
- base_model:MSL7/INEX12-7b
- license:apache-2.0
- autotrain_compatible
- endpoints_compatible
- text-generation-inference
- region:us
- text-generation
model_name: T3qInex12-7B-GGUF
base_model: automerger/T3qInex12-7B
inference: false
model_creator: automerger
pipeline_tag: text-generation
quantized_by: MaziyarPanahi
---
# [MaziyarPanahi/T3qInex12-7B-GGUF](https://huggingface.co/MaziyarPanahi/T3qInex12-7B-GGUF)
- Model creator: [automerger](https://huggingface.co/automerger)
- Original model: [automerger/T3qInex12-7B](https://huggingface.co/automerger/T3qInex12-7B)
## Description
[MaziyarPanahi/T3qInex12-7B-GGUF](https://huggingface.co/MaziyarPanahi/T3qInex12-7B-GGUF) contains GGUF format model files for [automerger/T3qInex12-7B](https://huggingface.co/automerger/T3qInex12-7B).
### 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 incomplete 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.
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
* [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration. Linux available, in beta as of 27/11/2023.
* [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.
* [GPT4All](https://gpt4all.io/index.html), a free and open source local running GUI, supporting Windows, Linux and macOS with full GPU accel.
* [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.
* [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use.
* [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server. Note, as of time of writing (November 27th 2023), ctransformers has not been updated in a long time and does not support many recent models.
## Special thanks
🙏 Special thanks to [Georgi Gerganov](https://github.com/ggerganov) and the whole team working on [llama.cpp](https://github.com/ggerganov/llama.cpp/) for making all of this possible.
|
ytcheng/llama3-70B-lora-pretrain_v2
|
ytcheng
| 2024-05-21T10:47:04Z | 2 | 0 |
peft
|
[
"peft",
"safetensors",
"llama-factory",
"lora",
"generated_from_trainer",
"base_model:meta-llama/Meta-Llama-3-70B-Instruct",
"base_model:adapter:meta-llama/Meta-Llama-3-70B-Instruct",
"license:llama3",
"region:us"
] | null | 2024-05-20T06:10:36Z |
---
license: llama3
library_name: peft
tags:
- llama-factory
- lora
- generated_from_trainer
base_model: meta-llama/Meta-Llama-3-70B-Instruct
model-index:
- name: llama3-70B-lora-pretrain_v2
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. -->
# llama3-70B-lora-pretrain_v2
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-70B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-70B-Instruct) on the sm_artile dataset.
It achieves the following results on the evaluation set:
- Loss: 1.9382
## 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: 2
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- total_eval_batch_size: 2
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 500
- num_epochs: 3.0
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 2.6995 | 0.0939 | 100 | 2.6305 |
| 2.4199 | 0.1877 | 200 | 2.3979 |
| 2.2722 | 0.2816 | 300 | 2.2180 |
| 2.0762 | 0.3754 | 400 | 2.1251 |
| 1.9652 | 0.4693 | 500 | 2.0858 |
| 2.1893 | 0.5631 | 600 | 2.0629 |
| 2.0153 | 0.6570 | 700 | 2.0473 |
| 1.9911 | 0.7508 | 800 | 2.0318 |
| 2.1041 | 0.8447 | 900 | 2.0198 |
| 2.0488 | 0.9385 | 1000 | 2.0117 |
| 1.897 | 1.0324 | 1100 | 2.0018 |
| 2.0298 | 1.1262 | 1200 | 1.9952 |
| 2.0989 | 1.2201 | 1300 | 1.9890 |
| 1.8695 | 1.3139 | 1400 | 1.9838 |
| 2.1573 | 1.4078 | 1500 | 1.9764 |
| 2.0183 | 1.5016 | 1600 | 1.9713 |
| 1.9229 | 1.5955 | 1700 | 1.9672 |
| 1.9732 | 1.6893 | 1800 | 1.9617 |
| 1.6835 | 1.7832 | 1900 | 1.9574 |
| 1.9874 | 1.8771 | 2000 | 1.9539 |
| 1.7607 | 1.9709 | 2100 | 1.9512 |
| 1.9459 | 2.0648 | 2200 | 1.9480 |
| 1.7611 | 2.1586 | 2300 | 1.9463 |
| 1.8491 | 2.2525 | 2400 | 1.9441 |
| 1.9121 | 2.3463 | 2500 | 1.9427 |
| 1.8849 | 2.4402 | 2600 | 1.9413 |
| 2.0679 | 2.5340 | 2700 | 1.9400 |
| 1.9908 | 2.6279 | 2800 | 1.9394 |
| 1.9557 | 2.7217 | 2900 | 1.9388 |
| 1.9627 | 2.8156 | 3000 | 1.9384 |
| 1.8339 | 2.9094 | 3100 | 1.9383 |
### Framework versions
- PEFT 0.10.0
- Transformers 4.40.0
- Pytorch 2.2.1
- Datasets 2.18.0
- Tokenizers 0.19.1
|
Boadiwaa/LORA-colab
|
Boadiwaa
| 2024-05-21T10:45:45Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2024-05-21T10:45:33Z |
---
library_name: transformers
tags: []
---
# 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. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **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]
|
zhouliguo/abc
|
zhouliguo
| 2024-05-21T10:43:32Z | 0 | 0 | null |
[
"license:apache-2.0",
"region:us"
] | null | 2024-05-21T10:36:24Z |
---
license: apache-2.0
---
|
joosma/ppo-v3
|
joosma
| 2024-05-21T10:40:39Z | 0 | 0 | null |
[
"tensorboard",
"LunarLander-v2",
"ppo",
"deep-reinforcement-learning",
"reinforcement-learning",
"custom-implementation",
"deep-rl-course",
"model-index",
"region:us"
] |
reinforcement-learning
| 2024-05-21T10:31:59Z |
---
tags:
- LunarLander-v2
- ppo
- deep-reinforcement-learning
- reinforcement-learning
- custom-implementation
- deep-rl-course
model-index:
- name: PPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: LunarLander-v2
type: LunarLander-v2
metrics:
- type: mean_reward
value: -151.06 +/- 77.67
name: mean_reward
verified: false
---
# PPO Agent Playing LunarLander-v2
This is a trained model of a PPO agent playing LunarLander-v2.
# Hyperparameters
```python
{'exp_name': 'ppo'
'seed': 1
'torch_deterministic': True
'cuda': True
'track': False
'wandb_project_name': 'cleanRL'
'wandb_entity': None
'capture_video': False
'env_id': 'LunarLander-v2'
'total_timesteps': 1000000
'learning_rate': 0.0002
'num_envs': 20
'num_steps': 2048
'anneal_lr': True
'gae': True
'gamma': 0.99
'gae_lambda': 0.95
'num_minibatches': 10
'update_epochs': 4
'norm_adv': True
'clip_coef': 0.2
'clip_vloss': True
'ent_coef': 0.01
'vf_coef': 0.5
'max_grad_norm': 0.5
'target_kl': None
'repo_id': 'joosma/ppo-v3'
'batch_size': 40960
'minibatch_size': 4096}
```
|
llama-duo/gemma7b-summarize-gpt4o-30k
|
llama-duo
| 2024-05-21T10:35:32Z | 2 | 1 |
peft
|
[
"peft",
"tensorboard",
"safetensors",
"gemma",
"alignment-handbook",
"trl",
"sft",
"generated_from_trainer",
"dataset:llama-duo/synth_summarize_dataset",
"base_model:google/gemma-7b",
"base_model:adapter:google/gemma-7b",
"license:gemma",
"4-bit",
"bitsandbytes",
"region:us"
] | null | 2024-05-19T15:22:55Z |
---
license: gemma
library_name: peft
tags:
- alignment-handbook
- trl
- sft
- generated_from_trainer
base_model: google/gemma-7b
datasets:
- llama-duo/synth_summarize_dataset
model-index:
- name: gemma7b-summarize-gpt4o-30k
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. -->
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/chansung18/huggingface/runs/gtgsbwvu)
# gemma7b-summarize-gpt4o-30k
This model is a fine-tuned version of [google/gemma-7b](https://huggingface.co/google/gemma-7b) on the llama-duo/synth_summarize_dataset dataset.
It achieves the following results on the evaluation set:
- Loss: 3.2430
## 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: 2
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- total_eval_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 1.1572 | 1.0 | 111 | 2.3072 |
| 0.9296 | 2.0 | 222 | 2.1789 |
| 0.8273 | 3.0 | 333 | 2.1709 |
| 0.7586 | 4.0 | 444 | 2.2164 |
| 0.6613 | 5.0 | 555 | 2.3182 |
| 0.577 | 6.0 | 666 | 2.4774 |
| 0.4958 | 7.0 | 777 | 2.7036 |
| 0.4205 | 8.0 | 888 | 2.9689 |
| 0.382 | 9.0 | 999 | 3.2252 |
| 0.372 | 10.0 | 1110 | 3.2430 |
### Framework versions
- PEFT 0.11.1
- Transformers 4.41.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
|
hgnoi/dippy8
|
hgnoi
| 2024-05-21T10:27:05Z | 119 | 0 |
transformers
|
[
"transformers",
"safetensors",
"stablelm",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2024-05-21T07:28:15Z |
---
library_name: transformers
tags: []
---
# 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. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **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]
|
fahad-1499/text-to-image
|
fahad-1499
| 2024-05-21T10:22:03Z | 0 | 0 | null |
[
"license:bsd-3-clause",
"region:us"
] | null | 2024-05-21T10:22:03Z |
---
license: bsd-3-clause
---
|
hgnoi/dippy4
|
hgnoi
| 2024-05-21T10:21:19Z | 88 | 0 |
transformers
|
[
"transformers",
"safetensors",
"stablelm",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2024-05-21T01:41:45Z |
---
library_name: transformers
tags: []
---
# 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. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **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]
|
lupobricco/relation_classification_single_label
|
lupobricco
| 2024-05-21T10:21:17Z | 104 | 0 |
transformers
|
[
"transformers",
"safetensors",
"camembert",
"text-classification",
"generated_from_trainer",
"base_model:Musixmatch/umberto-commoncrawl-cased-v1",
"base_model:finetune:Musixmatch/umberto-commoncrawl-cased-v1",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2024-05-21T10:11:36Z |
---
base_model: Musixmatch/umberto-commoncrawl-cased-v1
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: relation_classification_single_label
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. -->
# relation_classification_single_label
This model is a fine-tuned version of [Musixmatch/umberto-commoncrawl-cased-v1](https://huggingface.co/Musixmatch/umberto-commoncrawl-cased-v1) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.8861
- Accuracy: 0.6822
- F1: 0.6573
## 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: 10
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| No log | 1.0 | 121 | 0.8453 | 0.6357 | 0.6305 |
| No log | 2.0 | 242 | 0.9264 | 0.6434 | 0.6392 |
| No log | 3.0 | 363 | 0.8861 | 0.6822 | 0.6573 |
| No log | 4.0 | 484 | 1.0027 | 0.6822 | 0.6558 |
| 0.6343 | 5.0 | 605 | 1.1278 | 0.6667 | 0.6356 |
| 0.6343 | 6.0 | 726 | 1.3472 | 0.6512 | 0.6100 |
| 0.6343 | 7.0 | 847 | 1.4766 | 0.6434 | 0.5919 |
| 0.6343 | 8.0 | 968 | 1.5769 | 0.6667 | 0.6303 |
| 0.1581 | 9.0 | 1089 | 1.6284 | 0.6434 | 0.5971 |
| 0.1581 | 10.0 | 1210 | 1.6729 | 0.6589 | 0.6175 |
### Framework versions
- Transformers 4.40.1
- Pytorch 2.3.0+cu118
- Datasets 2.19.0
- Tokenizers 0.19.1
|
meharuu/python_llama
|
meharuu
| 2024-05-21T10:20:03Z | 5 | 0 |
transformers
|
[
"transformers",
"safetensors",
"roberta",
"fill-mask",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
fill-mask
| 2024-05-21T07:06:46Z |
---
license: apache-2.0
---
|
hgnoi/dippy2
|
hgnoi
| 2024-05-21T10:18:29Z | 121 | 0 |
transformers
|
[
"transformers",
"safetensors",
"stablelm",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2024-05-21T10:17:00Z |
---
library_name: transformers
tags: []
---
# 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. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **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]
|
oscpalML/DeBERTa-political-classification
|
oscpalML
| 2024-05-21T10:14:20Z | 132 | 0 |
transformers
|
[
"transformers",
"safetensors",
"deberta-v2",
"text-classification",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2024-05-12T10:53:55Z |
---
library_name: transformers
tags: []
---
# Model Card for Model ID
This model was trained as part of a submission to the Touché task *Ideology and Power Identification in Parliamentary Debates* as part of CLEF 2024.
Made by team PolicyParsingPanthers.
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **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]
|
vuongnhathien/ConvnextV2-tiny
|
vuongnhathien
| 2024-05-21T10:13:56Z | 193 | 1 |
transformers
|
[
"transformers",
"tensorboard",
"safetensors",
"convnextv2",
"image-classification",
"generated_from_trainer",
"dataset:imagefolder",
"base_model:facebook/convnextv2-tiny-22k-384",
"base_model:finetune:facebook/convnextv2-tiny-22k-384",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
image-classification
| 2024-05-21T05:18:49Z |
---
license: apache-2.0
base_model: facebook/convnextv2-tiny-22k-384
tags:
- image-classification
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: ConvnextV2-base
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: vuongnhathien/30VNFoods
type: imagefolder
config: default
split: validation
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.9192460317460317
---
<!-- 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. -->
# ConvnextV2-base
This model is a fine-tuned version of [facebook/convnextv2-tiny-22k-384](https://huggingface.co/facebook/convnextv2-tiny-22k-384) on the vuongnhathien/30VNFoods dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4650
- Accuracy: 0.9192
## 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: 32
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.5453 | 1.0 | 550 | 0.5385 | 0.8465 |
| 0.3201 | 2.0 | 1100 | 0.5494 | 0.8465 |
| 0.1818 | 3.0 | 1650 | 0.4973 | 0.8732 |
| 0.0974 | 4.0 | 2200 | 0.5644 | 0.8652 |
| 0.059 | 5.0 | 2750 | 0.5624 | 0.8891 |
| 0.0371 | 6.0 | 3300 | 0.6428 | 0.8755 |
| 0.0118 | 7.0 | 3850 | 0.5426 | 0.9026 |
| 0.0169 | 8.0 | 4400 | 0.4927 | 0.9161 |
| 0.0103 | 9.0 | 4950 | 0.5011 | 0.9105 |
| 0.0017 | 10.0 | 5500 | 0.4820 | 0.9165 |
### Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2
|
hgnoi/dippy0
|
hgnoi
| 2024-05-21T10:13:04Z | 120 | 0 |
transformers
|
[
"transformers",
"safetensors",
"stablelm",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2024-05-21T10:11:34Z |
---
library_name: transformers
tags: []
---
# 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. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **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]
|
nizamovtimur/multilingual-e5-large-wikiutmn
|
nizamovtimur
| 2024-05-21T10:12:38Z | 25 | 2 |
sentence-transformers
|
[
"sentence-transformers",
"safetensors",
"xlm-roberta",
"feature-extraction",
"sentence-similarity",
"autotrain_compatible",
"text-embeddings-inference",
"endpoints_compatible",
"region:us"
] |
sentence-similarity
| 2024-05-21T10:07:23Z |
---
library_name: sentence-transformers
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
---
# nizamovtimur/multilingual-e5-large-wikiutmn
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 1024 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('nizamovtimur/multilingual-e5-large-wikiutmn')
embeddings = model.encode(sentences)
print(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=nizamovtimur/multilingual-e5-large-wikiutmn)
## Training
The model was trained with the parameters:
**DataLoader**:
`torch.utils.data.dataloader.DataLoader` of length 23 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": 10,
"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": 355,
"weight_decay": 0.01
}
```
## Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: XLMRobertaModel
(1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
(2): Normalize()
)
```
## Citing & Authors
<!--- Describe where people can find more information -->
|
rahul1vemula/q-FrozenLake-v1-4x4-noSlippery
|
rahul1vemula
| 2024-05-21T10:05:13Z | 0 | 0 | null |
[
"FrozenLake-v1-4x4-no_slippery",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2024-05-21T10:05:08Z |
---
tags:
- FrozenLake-v1-4x4-no_slippery
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: q-FrozenLake-v1-4x4-noSlippery
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: FrozenLake-v1-4x4-no_slippery
type: FrozenLake-v1-4x4-no_slippery
metrics:
- type: mean_reward
value: 1.00 +/- 0.00
name: mean_reward
verified: false
---
# **Q-Learning** Agent playing1 **FrozenLake-v1**
This is a trained model of a **Q-Learning** agent playing **FrozenLake-v1** .
## Usage
```python
model = load_from_hub(repo_id="rahul1vemula/q-FrozenLake-v1-4x4-noSlippery", 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"])
```
|
yzhuang/Meta-Llama-3-8B-Instruct_fictional_gsm8k_Korean_v1
|
yzhuang
| 2024-05-21T10:02:08Z | 7 | 0 |
transformers
|
[
"transformers",
"tensorboard",
"safetensors",
"llama",
"text-generation",
"trl",
"sft",
"generated_from_trainer",
"conversational",
"dataset:generator",
"base_model:meta-llama/Meta-Llama-3-8B-Instruct",
"base_model:finetune:meta-llama/Meta-Llama-3-8B-Instruct",
"license:llama3",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2024-05-20T01:02:35Z |
---
license: llama3
base_model: meta-llama/Meta-Llama-3-8B-Instruct
tags:
- trl
- sft
- generated_from_trainer
datasets:
- generator
model-index:
- name: Meta-Llama-3-8B-Instruct_fictional_gsm8k_Korean_v1
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. -->
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/yufanz/autotree/runs/7283704781.17487-9818c277-4a86-4343-b288-7864588621de)
# Meta-Llama-3-8B-Instruct_fictional_gsm8k_Korean_v1
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the generator 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: 2
- 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
- num_epochs: 100
### Training results
### Framework versions
- Transformers 4.41.0
- Pytorch 2.1.0a0+32f93b1
- Datasets 2.19.1
- Tokenizers 0.19.1
|
falan42/Gemma-2b-int4-SODA_mark1
|
falan42
| 2024-05-21T10:01:39Z | 78 | 1 |
transformers
|
[
"transformers",
"safetensors",
"gemma",
"text-generation",
"text-generation-inference",
"unsloth",
"trl",
"sft",
"conversational",
"en",
"base_model:unsloth/gemma-2b-it-bnb-4bit",
"base_model:quantized:unsloth/gemma-2b-it-bnb-4bit",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"4-bit",
"bitsandbytes",
"region:us"
] |
text-generation
| 2024-05-21T10:00:28Z |
---
language:
- en
license: apache-2.0
tags:
- text-generation-inference
- transformers
- unsloth
- gemma
- trl
- sft
base_model: unsloth/gemma-2b-it-bnb-4bit
---
# Uploaded model
- **Developed by:** emir12
- **License:** apache-2.0
- **Finetuned from model :** unsloth/gemma-2b-it-bnb-4bit
This gemma model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
mergekit-community/TopEvolution16
|
mergekit-community
| 2024-05-21T10:00:58Z | 6 | 0 |
transformers
|
[
"transformers",
"safetensors",
"mistral",
"text-generation",
"mergekit",
"merge",
"base_model:NousResearch/Hermes-2-Theta-Llama-3-8B",
"base_model:merge:NousResearch/Hermes-2-Theta-Llama-3-8B",
"base_model:mergekit-community/TopEvolution",
"base_model:merge:mergekit-community/TopEvolution",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2024-05-21T09:54:11Z |
---
base_model:
- NousResearch/Hermes-2-Theta-Llama-3-8B
- mergekit-community/TopEvolution
library_name: transformers
tags:
- mergekit
- merge
---
# merge
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
## Merge Details
### Merge Method
This model was merged using the SLERP merge method.
### Models Merged
The following models were included in the merge:
* [NousResearch/Hermes-2-Theta-Llama-3-8B](https://huggingface.co/NousResearch/Hermes-2-Theta-Llama-3-8B)
* [mergekit-community/TopEvolution](https://huggingface.co/mergekit-community/TopEvolution)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
models:
- model: mergekit-community/TopEvolution
- model: NousResearch/Hermes-2-Theta-Llama-3-8B
merge_method: slerp
base_model: mergekit-community/TopEvolution
dtype: bfloat16
parameters:
t: [0.1, 0.2, 0.4, 0.2, 0.1] # Model Fusion By Claudio Arena
```
|
jmurphy97/mistral-7b-awq
|
jmurphy97
| 2024-05-21T09:58:55Z | 76 | 0 |
transformers
|
[
"transformers",
"safetensors",
"mistral",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"4-bit",
"awq",
"region:us"
] |
text-generation
| 2024-05-21T09:49:40Z |
---
library_name: transformers
tags: []
---
# 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. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **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]
|
sal7/rv
|
sal7
| 2024-05-21T09:57:30Z | 0 | 0 | null |
[
"license:apache-2.0",
"region:us"
] | null | 2024-05-21T09:57:30Z |
---
license: apache-2.0
---
|
PipableAI/pip-library-etl-1.3b
|
PipableAI
| 2024-05-21T09:56:05Z | 25 | 44 |
transformers
|
[
"transformers",
"pytorch",
"safetensors",
"llama",
"text-generation",
"python",
"java",
"cpp",
"sql",
"function calling",
"unit tests",
"causalLM",
"codeLLAMA modified archi",
"document",
"code",
"code2doc",
"instruction_tuned",
"basemodel",
"docstring",
"documentation",
"text-generation-inference",
"conversational",
"en",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2024-03-12T10:25:24Z |
---
language:
- en
license: apache-2.0
library_name: transformers
tags:
- python
- java
- cpp
- sql
- function calling
- unit tests
- causalLM
- codeLLAMA modified archi
- document
- code
- code2doc
- instruction_tuned
- basemodel
- pytorch
- docstring
- documentation
- text-generation-inference
metrics:
- accuracy
pipeline_tag: text-generation
widget:
- text: '<example_response>--code:def function_divide2(x): return x / 2--question:Document
the code--doc:Description:This function takes a number and divides it by 2.Parameters:-
x (numeric): The input value to be divided by 2.Returns:- float: The result of
x divided by 2.Example:To call the function, use the following code:function_divide2(1.0)</example_response><function_code>def
_plot_bounding_polygon(polygons_coordinates, output_html_path=bounding_polygon_map.html):map_center
= [sum([coord[0]for polygon_coords in polygons_coordinatesfor coord in polygon_coords])/
sum([len(polygon_coords) for polygon_coords in polygons_coordinates]),sum([coord[1]for
polygon_coords in polygons_coordinatesfor coord in polygon_coords])/ sum([len(polygon_coords)
for polygon_coords in polygons_coordinates]),]my_map = folium.Map(location=map_center,
zoom_start=12)for polygon_coords in polygons_coordinates:folium.Polygon(locations=polygon_coords,color=blue,fill=True,fill_color=blue,fill_opacity=0.2,).add_to(my_map)marker_cluster
= MarkerCluster().add_to(my_map)for polygon_coords in polygons_coordinates:for
coord in polygon_coords:folium.Marker(location=[coord[0], coord[1]], popup=fCoordinates:
{coord}).add_to(marker_cluster)draw = Draw(export=True)draw.add_to(my_map)my_map.save(output_html_path)return
output_html_path</function_code><question>Document the python code above giving
function description ,parameters and return type and example how to call the function</question><doc>'
example_title: example
---
# pip-library-etl-1.3b
[pipableAi](https://www.pipable.ai/)
[colab_notebook](https://colab.research.google.com/drive/10av3SxFf0Psx_IkmZbcUhiVznStV5pVS?usp=sharing)
[pip etl](https://github.com/PipableAI/pip-library-etl)
## How we built it?
We used softmax cross entropy and a modified form of policy grad along with Q loss, optimized in an EM set up.
The performance for the metioned tasks are comparable to much bigger LLMs and GPT-3.5
## License
The model is open source under apache 2.0. License
## Usage
### NOTE:
If you wish to try this model without utilizing your GPU, we have hosted the model on our end. To execute the library using the hosted playground model, initialize the generator as shown below:
```python
from pip_library_etl import PipEtl
generator = PipEtl(device="cloud")
```
We have hosted the model at https://playground.pipable.ai/infer. Hence, one can also make a POST request to this endpoint with the following payload:
```json
{
"model_name": "PipableAI/pip-library-etl-1.3b",
"prompt": "prompt",
"max_new_tokens": "400"
}
```
```bash
curl -X 'POST' \
'https://playground.pipable.ai/infer' \
-H 'accept: application/json' \
-H 'Content-Type: application/x-www-form-urlencoded' \
-d 'model_name=PipableAI%2Fpip-library-etl-1.3b&prompt="YOUR PROMPT"&max_new_tokens=400'
```
Alternatively, you can directly access UI endpoint at https://playground.pipable.ai/docs#/default/infer_infer_post.
### Library use
For directly using the capabilities of model without putting extra efforts on schems and prompts try to use [pip library_etl](https://github.com/PipableAI/pip-library-etl.git).
Here's a brief overview of what can be achieved using the PipEtl library:
- `Function Call Generation` : The generate_function_call method facilitates the generation of Python function calls based on provided questions and either docstrings or undocumented code. This feature can be useful for generating example function calls or for prototyping code snippets.
- `Automated Documentation Generation` : With the generate_docstring method, users can automatically generate comprehensive docstrings for Python functions. This feature aids in maintaining well-documented codebases and adhering to best practices.
- `Module Documentation` : The generate_module_docstrings method allows for generating documentation for all methods and functions within a given module or package. This capability streamlines the documentation process, especially for large codebases with numerous functions.
- `SQL Query Generation` : Users can leverage the generate_sql method to automatically generate SQL queries based on provided schemas and questions. This functionality simplifies the process of creating SQL queries, particularly for data-related tasks.
For detailed usage refer to the [colab_notebook](https://colab.research.google.com/drive/17PyMU_3QN9LROy7x-jmaema0cuLRzBvc?usp=sharing)
### Installation
```bash
pip install transformers
```
### Prompt
```python
prompt = f"""<example_response>{--question , --query}</example_response><function_code>{code}</function_code>
<question>Give one line description of the python code above in natural language.</question>
<doc>"""
prompt = f"""<example_response>{example of some --question: , --query}</example_response><schema>{schema with cols described}</schema>
<question>Write a sql query to ....</question>
<sql>"""
```
### PyTorch
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
device = "cuda"
model = AutoModelForCausalLM.from_pretrained("PipableAI/pip-library-etl-1.3b").to(device)
tokenizer = AutoTokenizer.from_pretrained("PipableAI/pip-library-etl-1.3b")
prompt = f"""
<example_response>
--code:def divide_by_two(x: float) -> float: return x / 2
--question:Document the python code above giving function description ,parameters and return type and example on how to call the function
--doc:
Description: This function divides a given number by 2.
Parameters:
- x (float): The input value to be divided by 2.
Returns:
- float: The result of x divided by 2.
Example:
divide_by_two(1.0)
</example_response>
<function_code>
def download_file(shared_url, destination):
try:
if not shared_url.startswith("https://drive.google.com"):
raise ValueError("Please provde a valid google drive link.")
file_id = shared_url.split("/d/")[1]
file_id = file_id.split("/")[0]
url = f"https://drive.google.com/uc?id={file_id}"
gdown.download(url, destination, quiet=False)
except Exception as e:
print(f"Error downloading file from Google Drive as {e}")
raise e
</function_code>
<instructions>
1. In the examples while calling function use the name mentioned after `def ` in the above function_code.
2. In the generated docs use valid python type hints as per PEP 484.
</instructions>
<question>Document the python code above giving function description ,parameters and return type and example how to call the function.</question>
<doc>
"""
inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
outputs = model.generate(**inputs, max_new_tokens=450)
doc = (
tokenizer.decode(outputs[0], skip_special_tokens=True)
.split("<doc>")[-1]
.split("</doc>")[0]
)
doc = (
doc.replace("<p>", "")
.replace("</p>", "")
.replace("<function_description>", "")
.replace("</function_description>", "")
)
print(doc)
```
## Examples
### 1. Code Documentation
### prompt
```python
prompt ='''<example_response>
--code:def divide_by_two(x: float) -> float: return x / 2
--question:Document the python code above giving function description ,parameters and return type and example on how to call the function
--doc:
Description: This function divides a given number by 2.
Parameters:
- x (float): The input value to be divided by 2.
Returns:
- float: The result of x divided by 2.
Example:
divide_by_two(1.0)
</example_response>
<function_code>def _plot_bounding_polygon(
polygons_coordinates, output_html_path="bounding_polygon_map.html"
):
# Create a Folium map centered at the average coordinates of all bounding boxes
map_center = [
sum(
[
coord[0]
for polygon_coords in polygons_coordinates
for coord in polygon_coords
]
)
/ sum([len(polygon_coords) for polygon_coords in polygons_coordinates]),
sum(
[
coord[1]
for polygon_coords in polygons_coordinates
for coord in polygon_coords
]
)
/ sum([len(polygon_coords) for polygon_coords in polygons_coordinates]),
]
my_map = folium.Map(location=map_center, zoom_start=12)
# Add each bounding polygon to the map
for polygon_coords in polygons_coordinates:
folium.Polygon(
locations=polygon_coords,
color="blue",
fill=True,
fill_color="blue",
fill_opacity=0.2,
).add_to(my_map)
# Add bounding boxes as markers to the map
marker_cluster = MarkerCluster().add_to(my_map)
for polygon_coords in polygons_coordinates:
for coord in polygon_coords:
folium.Marker(
location=[coord[0], coord[1]], popup=f"Coordinates: {coord}"
).add_to(marker_cluster)
# Add draw control to allow users to draw additional polygons
draw = Draw(export=True)
draw.add_to(my_map)
# Save the map as an HTML file
my_map.save(output_html_path)
return output_html_path
</function_code>
<instructions>
1. In the examples while calling function use the name mentioned after `def ` in the above function_code.
2. In the generated docs use valid python type hints as per PEP 484.
</instructions>
<question>Document the python code above giving function description ,parameters and return type and example how to call the function</question><doc>'''
```
### Response
```txt
Description:This function generates a map of the bounding polygons and saves it as an HTML file.
Parameters:
- polygons_coordinates (list of lists of tuples): A list of lists of tuples representing the coordinates of the polygons. Each polygon is a list of coordinates.
- output_html_path (str, optional): The path where the HTML file should be saved. Defaults to "bounding_polygon_map.html".
Returns:
- str: The path to the saved HTML file.
Example:
To call the function, use the following code:
plot_bounding_polygon([[(0, 0), (1, 0), (1, 1), (0, 1)], [(2, 2), (3, 2), (3, 3), (2, 3)]], "my_map.html").
```
### 2. SQL Generation
### prompt
```python
prompt = """Generate a simple SQL query from the schema mentioned for the following question.
<schema>
CREATE TABLE department (
Department_ID number, -- Unique identifier for the department
Name text, -- Name of the department
Creation text, -- Date of creation or establishment
Ranking number, -- Ranking of the department
Budget_in_Billions number, -- Budget of the department in billions
Num_Employees number -- Number of employees in the department
);
CREATE TABLE head (
head_ID number, -- Unique identifier for the head
name text, -- Name of the head
born_state text, -- State where the head was born
age number -- Age of the head
);
CREATE TABLE management (
department_ID number, -- Foreign key referencing Department_ID in department table
head_ID number, -- Foreign key referencing head_ID in head table
temporary_acting text -- Indicates if the head is temporarily acting
);
</schema>
<question>What are the names of the heads who are born outside the California state?</question>
<sql>
"""
```
### response
```sql
SELECT head.name FROM head WHERE head.born_state <> 'California';
```
### 3. Performance Schema Monitoring
### prompt
```python
prompt = """Generate the SQL query for SkySQL performance schema for the following question.
<example>
--question: What are the top 10 most frequently used queries/statements?
--sql: SELECT DIGEST_TEXT, COUNT(*) as frequency FROM performance_schema.events_statements_summary_by_digest GROUP BY DIGEST_TEXT ORDER BY frequency DESC LIMIT 10;
</example>
<schema>
CREATE TABLE `accounts` (`USER` char(128) DEFAULT NULL -- 'The connection''s client user name for the connection, or NULL if an internal thread.',
`HOST` char(255) DEFAULT NULL -- 'The connection client''s host name, or NULL if an internal thread.',
`CURRENT_CONNECTIONS` bigint(20) NOT NULL -- 'Current connections for the account.',\n
`TOTAL_CONNECTIONS` bigint(20) NOT NULL -- 'Total connections for the account.'
) ;
</schema>
<question>
Tell me the number of active connections each user has.
</question>
<sql>
"""
```
### response
```sql
SELECT USER, CURRENT_CONNECTIONS FROM accounts;
```
### prompt
```python
prompt = """Generate the SQL query for SkySQL performance schema for the following question.
<example>
--question: What are the top 10 most frequently used queries/statements?
--sql: SELECT DIGEST_TEXT, COUNT(*) as frequency FROM performance_schema.events_statements_summary_by_digest GROUP BY DIGEST_TEXT ORDER BY frequency DESC LIMIT 10;
</example>
<schema>
CREATE TABLE `file_summary_by_instance` (
`FILE_NAME` varchar(512) NOT NULL -- 'File name.',
`EVENT_NAME` varchar(128) NOT NULL -- 'Event name.',
`OBJECT_INSTANCE_BEGIN` bigint(20) unsigned NOT NULL -- 'Address in memory. Together with FILE_NAME and EVENT_NAME uniquely identifies a row.',
`COUNT_STAR` bigint(20) unsigned NOT NULL -- 'Number of summarized events',
`SUM_TIMER_WAIT` bigint(20) unsigned NOT NULL -- 'Total wait time of the summarized events that are timed.',
`MIN_TIMER_WAIT` bigint(20) unsigned NOT NULL -- 'Minimum wait time of the summarized events that are timed.',
`AVG_TIMER_WAIT` bigint(20) unsigned NOT NULL -- 'Average wait time of the summarized events that are timed.',
`MAX_TIMER_WAIT` bigint(20) unsigned NOT NULL -- 'Maximum wait time of the summarized events that are timed.',
`COUNT_READ` bigint(20) unsigned NOT NULL -- 'Number of all read operations, including FGETS, FGETC, FREAD, and READ.',
`SUM_TIMER_READ` bigint(20) unsigned NOT NULL -- 'Total wait time of all read operations that are timed.',
`MIN_TIMER_READ` bigint(20) unsigned NOT NULL -- 'Minimum wait time of all read operations that are timed.',
`AVG_TIMER_READ` bigint(20) unsigned NOT NULL -- 'Average wait time of all read operations that are timed.',
`MAX_TIMER_READ` bigint(20) unsigned NOT NULL -- 'Maximum wait time of all read operations that are timed.',
`SUM_NUMBER_OF_BYTES_READ` bigint(20) NOT NULL -- 'Bytes read by read operations.',
`COUNT_WRITE` bigint(20) unsigned NOT NULL -- 'Number of all write operations, including FPUTS, FPUTC, FPRINTF, VFPRINTF, FWRITE, and PWRITE.',
`SUM_TIMER_WRITE` bigint(20) unsigned NOT NULL -- 'Total wait time of all write operations that are timed.',
`MIN_TIMER_WRITE` bigint(20) unsigned NOT NULL -- 'Minimum wait time of all write operations that are timed.',
`AVG_TIMER_WRITE` bigint(20) unsigned NOT NULL -- 'Average wait time of all write operations that are timed.',
`MAX_TIMER_WRITE` bigint(20) unsigned NOT NULL -- 'Maximum wait time of all write operations that are timed.',
`SUM_NUMBER_OF_BYTES_WRITE` bigint(20) NOT NULL -- 'Bytes written by write operations.',
`COUNT_MISC` bigint(20) unsigned NOT NULL -- 'Number of all miscellaneous operations not counted above, including CREATE, DELETE, OPEN, CLOSE, STREAM_OPEN, STREAM_CLOSE, SEEK, TELL, FLUSH, STAT, FSTAT, CHSIZE, RENAME, and SYNC.',
`SUM_TIMER_MISC` bigint(20) unsigned NOT NULL -- 'Total wait time of all miscellaneous operations that are timed.',
`MIN_TIMER_MISC` bigint(20) unsigned NOT NULL -- 'Minimum wait time of all miscellaneous operations that are timed.',
`AVG_TIMER_MISC` bigint(20) unsigned NOT NULL -- 'Average wait time of all miscellaneous operations that are timed.',
`MAX_TIMER_MISC` bigint(20) unsigned NOT NULL -- 'Maximum wait time of all miscellaneous operations that are timed.'
);
</schema>
<question>
List out 10 names of the files with the most read and writes
</question>
<sql>
"""
```
### response
```sql
SELECT FILE_NAME FROM file_summary_by_instance ORDER BY SUM_NUMBER_OF_BYTES_READ DESC, SUM_NUMBER_OF_BYTES_WRITE DESC LIMIT 10;
```
### 4. Function Calling
### prompt
```python
prompt = """
Give a function call in python langugae for the following question:
<example_response>
--doc: Description: This function logs a curl command in debug mode.
Parameters:
- method (str): The HTTP method to use for the request.
- url (str): The URL to send the request to.
- data (dict, optional): The data to send in the request. Defaults to None.
- headers (dict, optional): The headers to send with the request. Defaults to None.
- level (int, optional): The log level to use for this log message. Defaults to logging.DEBUG.
Returns:
- None
Example:
log_curl_debug('GET', 'https://example.com')
--question: log a curl PUT request for url https://web.io/
--function_call: log_curl_debug(method='PUT', url = 'https://web.io')
</example_response>
<doc>
Function Name: make_get_req()
Description: This function is used to make a GET request.
Parameters:
- path (str): The path of the URL to be requested.
- data (dict): The data to be sent in the body of the request.
- flags (dict): The flags to be sent in the request.
- params (dict): The parameters to be sent in the request.
- headers (dict): The headers to be sent in the request.
- not_json_response (bool): OPTIONAL: If set to True, the function will return the raw response content instead of trying to parse it as JSON.
- trailing (str): OPTIONAL: For wrapping slash symbol in the end of string.
- absolute (bool): OPTIONAL: If set to True, the function will not prefix the URL with the base URL.
- advanced_mode (bool): OPTIONAL: If set to True, the function will return the raw response instead of trying to parse it as JSON.
Returns:
- Union[str, dict, list, None]: The response content as a string, a dictionary, a list, or None if the response was not successful.
</doc>
<instruction>
1. Strictly use named parameters mentioned in the doc to generate function calls.
2. Only return the response as python parsable string version of function call.
3. mention the 'self' parameter if required.
</instruction>
<question>
Make a GET request for the URL parameter using variable_2. For the params parameter, use 'weight' as one of the keys with variable_3 as its value, and 'width' as another key with a value of 10. For the data parameter, use variable_1. Prefix the URL with the base URL, and ensure the response is in raw format.
</question>
<function_call>
"""
```
### response
```python
make_get_req(path='https://example.com/api/v1/users', data=variable_1, params={'weight': variable_3, 'width': 10}, headers={'Content-Type': 'application/json'}, not_json_response=True, absolute=True)
```
### prompt
```python
prompt = """
Give only function call in python langugae as response for the following question:
<example_response>
--doc:
Function:
Help on function head in module pandas.core.generic:
head(self, n: 'int' = 5) -> 'Self'
Return the first `n` rows.
This function returns the first `n` rows for the object based
on position. It is useful for quickly testing if your object
has the right type of data in it.
For negative values of `n`, this function returns all rows except
the last `|n|` rows, equivalent to ``df[:n]``.
If n is larger than the number of rows, this function returns all rows.
Parameters
----------
n : int, default 5
Number of rows to select.
Returns
-------
same type as caller
The first `n` rows of the caller object.
See Also
--------
DataFrame.tail: Returns the last `n` rows.
Examples
--------
>>> df = pd.DataFrame({'animal': ['alligator', 'bee', 'falcon', 'lion',
... 'monkey', 'parrot', 'shark', 'whale', 'zebra']})
>>> df
animal
0 alligator
--question: Get the top 5 rows with the highest Engagement_Score. Parameter Description: Use 5 as Number of rows to return ,Use variable_3 as Sorted DataFrame, Do not call any other function, Pass variable to self parameter for method calls
--function_call: head(self=variable_3, n=5)
</example_response>
<doc>
Function: sort_values
sort_values in module pandas.core.frame:
sort_values(self, by: 'IndexLabel', *, axis: 'Axis' = 0, ascending: 'bool | list[bool] | tuple[bool, ...]' = True, inplace: 'bool' = False, kind: 'SortKind' = 'quicksort', na_position: 'str' = 'last', ignore_index: 'bool' = False, key: 'ValueKeyFunc | None' = None) -> 'DataFrame | None'
Sort by the values along either axis.
Parameters
----------
by : str or list of str
Name or list of names to sort by.
- if `axis` is 0 or `'index'` then `by` may contain index
levels and/or column labels.
- if `axis` is 1 or `'columns'` then `by` may contain column
levels and/or index labels.
axis : "{0 or 'index', 1 or 'columns'}", default 0
Axis to be sorted.
ascending : bool or list of bool, default True
Sort ascending vs. descending. Specify list for multiple sort
orders. If this is a list of bools, must match the length of
the
</doc>
<instruction>
1. Strictly use named parameters mentioned in the doc to generate function calls.
2. Only return the response as python parsable string version of function call.
3. Use the 'self' parameter if required in the function call with it's value in named keyword format.
</instruction>
<question>
Using the above function, Sort the DataFrame by the Engagement_Score in descending order. Parameter Description: Use Engagement_Score as Column name to sort by ,Use False as Sort in descending order ,Use variable_1 as DataFrame to sort, Do not call any other function, Pass variable to self parameter for method calls
</question>
<function_call>
"""
```
### response
```python
sort_values(self=variable_1, by='Engagement_Score', ascending=False)
```
### Team
Avi Kothari, Gyan Ranjan, Pratham Gupta, Ritvik Aryan Kalra, Soham Acharya
|
T3Q-LLM/T3Q-FLMM-DUS-v1.0
|
T3Q-LLM
| 2024-05-21T09:54:16Z | 5 | 0 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2024-05-21T07:35:03Z |
---
library_name: transformers
tags: []
---
# 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. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **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]
[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
hf-causal-experimental (pretrained=T3Q-LLM/T3Q-FLMM-DUS-v1.0,use_accelerate=true,trust_remote_code=true), limit: None, provide_description: False, num_fewshot: 0, batch_size: 8
| Task |Version| Metric |Value | |Stderr|
|----------------|------:|--------|-----:|---|-----:|
|kobest_boolq | 0|acc |0.9509|± |0.0058|
| | |macro_f1|0.9508|± |0.0058|
|kobest_copa | 0|acc |0.7630|± |0.0135|
| | |macro_f1|0.7626|± |0.0135|
|kobest_hellaswag| 0|acc |0.4740|± |0.0224|
| | |acc_norm|0.5580|± |0.0222|
| | |macro_f1|0.4707|± |0.0223|
|kobest_sentineg | 0|acc |0.7128|± |0.0227|
| | |macro_f1|0.6946|± |0.0238|
|
subedikushal/my_awesome_eli5_clm-model
|
subedikushal
| 2024-05-21T09:53:07Z | 135 | 0 |
transformers
|
[
"transformers",
"tensorboard",
"safetensors",
"gpt2",
"text-generation",
"generated_from_trainer",
"dataset:eli5_category",
"base_model:distilbert/distilgpt2",
"base_model:finetune:distilbert/distilgpt2",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2024-05-21T09:42:06Z |
---
license: apache-2.0
tags:
- generated_from_trainer
base_model: distilbert/distilgpt2
datasets:
- eli5_category
model-index:
- name: my_awesome_eli5_clm-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_eli5_clm-model
This model is a fine-tuned version of [distilbert/distilgpt2](https://huggingface.co/distilbert/distilgpt2) on the eli5_category 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
- training_steps: 5
### Training results
### Framework versions
- Transformers 4.41.0
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
|
Rimyy/Gemma-2b-finetuneGSMdata1epSameP3ep
|
Rimyy
| 2024-05-21T09:51:26Z | 134 | 0 |
transformers
|
[
"transformers",
"safetensors",
"gemma",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2024-05-21T09:49:19Z |
---
library_name: transformers
tags: []
---
# 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. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **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]
|
lupobricco/relation_detection_textual
|
lupobricco
| 2024-05-21T09:51:10Z | 105 | 0 |
transformers
|
[
"transformers",
"tensorboard",
"safetensors",
"camembert",
"text-classification",
"generated_from_trainer",
"base_model:Musixmatch/umberto-commoncrawl-cased-v1",
"base_model:finetune:Musixmatch/umberto-commoncrawl-cased-v1",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2024-05-21T09:07:01Z |
---
base_model: Musixmatch/umberto-commoncrawl-cased-v1
tags:
- generated_from_trainer
metrics:
- f1
- accuracy
model-index:
- name: relation_detection_textual
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. -->
# relation_detection_textual
This model is a fine-tuned version of [Musixmatch/umberto-commoncrawl-cased-v1](https://huggingface.co/Musixmatch/umberto-commoncrawl-cased-v1) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5247
- F1: 0.6071
- Roc Auc: 0.6769
- Accuracy: 0.5659
## 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: 10
### Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|:--------:|
| No log | 1.0 | 33 | 0.5783 | 0.2301 | 0.5 | 0.5271 |
| No log | 2.0 | 66 | 0.5327 | 0.4997 | 0.6312 | 0.5814 |
| No log | 3.0 | 99 | 0.5276 | 0.5688 | 0.6597 | 0.5969 |
| No log | 4.0 | 132 | 0.5228 | 0.4610 | 0.6262 | 0.6434 |
| No log | 5.0 | 165 | 0.5153 | 0.5762 | 0.6594 | 0.6124 |
| No log | 6.0 | 198 | 0.5153 | 0.5762 | 0.6594 | 0.6124 |
| No log | 7.0 | 231 | 0.5190 | 0.6032 | 0.6729 | 0.5659 |
| No log | 8.0 | 264 | 0.5240 | 0.6021 | 0.6728 | 0.5736 |
| No log | 9.0 | 297 | 0.5247 | 0.6071 | 0.6769 | 0.5659 |
| No log | 10.0 | 330 | 0.5257 | 0.5924 | 0.6672 | 0.5659 |
### Framework versions
- Transformers 4.38.2
- Pytorch 2.0.0+cu118
- Datasets 2.18.0
- Tokenizers 0.15.2
|
himadhithv/serv_360
|
himadhithv
| 2024-05-21T09:50:42Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"text-generation-inference",
"unsloth",
"llama",
"trl",
"en",
"base_model:unsloth/llama-3-8b-bnb-4bit",
"base_model:finetune:unsloth/llama-3-8b-bnb-4bit",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2024-05-21T09:50:07Z |
---
language:
- en
license: apache-2.0
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
base_model: unsloth/llama-3-8b-bnb-4bit
---
# Uploaded model
- **Developed by:** himadhithv
- **License:** apache-2.0
- **Finetuned from model :** unsloth/llama-3-8b-bnb-4bit
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
team-sanai/zoo_wiki_expert
|
team-sanai
| 2024-05-21T09:46:42Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2024-05-21T09:43:20Z |
---
library_name: transformers
tags: []
---
# 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. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **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]
|
Fetanos/rl_course_vizdoom_health_gathering_supreme
|
Fetanos
| 2024-05-21T09:43:10Z | 0 | 0 |
sample-factory
|
[
"sample-factory",
"tensorboard",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2024-05-21T09:43:04Z |
---
library_name: sample-factory
tags:
- deep-reinforcement-learning
- reinforcement-learning
- sample-factory
model-index:
- name: APPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: doom_health_gathering_supreme
type: doom_health_gathering_supreme
metrics:
- type: mean_reward
value: 9.18 +/- 4.10
name: mean_reward
verified: false
---
A(n) **APPO** model trained on the **doom_health_gathering_supreme** 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 Fetanos/rl_course_vizdoom_health_gathering_supreme
```
## Using the model
To run the model after download, use the `enjoy` script corresponding to this environment:
```
python -m .usr.local.lib.python3.10.dist-packages.colab_kernel_launcher --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme
```
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 .usr.local.lib.python3.10.dist-packages.colab_kernel_launcher --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme --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.
|
ifyou819/summary-news-dataset-2
|
ifyou819
| 2024-05-21T09:41:46Z | 103 | 0 |
transformers
|
[
"transformers",
"tensorboard",
"safetensors",
"pegasus",
"text2text-generation",
"generated_from_trainer",
"base_model:ifyou819/summary-news-dataset-1",
"base_model:finetune:ifyou819/summary-news-dataset-1",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text2text-generation
| 2024-05-21T09:40:36Z |
---
base_model: ifyou819/summary-news-dataset-1
tags:
- generated_from_trainer
model-index:
- name: summary-news-dataset-2
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. -->
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/fine-tune-gpt-model/huggingface/runs/96x2cbez)
# summary-news-dataset-2
This model is a fine-tuned version of [ifyou819/summary-news-dataset-1](https://huggingface.co/ifyou819/summary-news-dataset-1) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 7.9757
## 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-06
- train_batch_size: 4
- eval_batch_size: 4
- 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 |
|:-------------:|:-----:|:----:|:---------------:|
| 9.2165 | 1.0 | 791 | 8.5843 |
| 8.6471 | 2.0 | 1582 | 8.1472 |
| 8.4678 | 3.0 | 2373 | 7.9757 |
### Framework versions
- Transformers 4.41.0
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.19.1
|
aaabiao/neo_7B_sft_v0_1_plus-dpo-iter2-beta0_1
|
aaabiao
| 2024-05-21T09:40:35Z | 1 | 0 |
peft
|
[
"peft",
"llama",
"alignment-handbook",
"generated_from_trainer",
"region:us"
] | null | 2024-05-21T09:34:57Z |
---
library_name: peft
tags:
- alignment-handbook
- generated_from_trainer
# base_model: /ML-A100/team/mm/zhangge/iterativeDPO/data/model/full/neo_7B_sft_v0_1_plus-dpo-iter1-beta0_3
# datasets:
# - /ML-A100/team/mm/zhangge/iterativeDPO/data/dataset/generate/neo_7B_sft_v0_1_plus-dpo-iter1-beta0_3-generate-chosen-rejected-reward
model-index:
- name: neo_7B_sft_v0_1_plus-dpo-iter2-beta0_1
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. -->
# neo_7B_sft_v0_1_plus-dpo-iter2-beta0_1
This model is a fine-tuned version of [/ML-A100/team/mm/zhangge/iterativeDPO/data/model/full/neo_7B_sft_v0_1_plus-dpo-iter1-beta0_3](https://huggingface.co//ML-A100/team/mm/zhangge/iterativeDPO/data/model/full/neo_7B_sft_v0_1_plus-dpo-iter1-beta0_3) on the /ML-A100/team/mm/zhangge/iterativeDPO/data/dataset/generate/neo_7B_sft_v0_1_plus-dpo-iter1-beta0_3-generate-chosen-rejected-reward 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-06
- train_batch_size: 3
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 128
- total_train_batch_size: 384
- total_eval_batch_size: 1024
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1
### Training results
### Framework versions
- PEFT 0.7.1
- Transformers 4.39.0.dev0
- Pytorch 2.3.0+cu121
- Datasets 2.14.6
- Tokenizers 0.15.2
|
team-sanai/zoo_math_expert
|
team-sanai
| 2024-05-21T09:39:49Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2024-05-21T09:36:35Z |
---
library_name: transformers
tags: []
---
# 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. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **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]
|
onegoodlad/deberta-disaster-tweet-recognizer
|
onegoodlad
| 2024-05-21T09:38:25Z | 104 | 0 |
transformers
|
[
"transformers",
"safetensors",
"deberta-v2",
"text-classification",
"generated_from_trainer",
"base_model:microsoft/deberta-v3-large",
"base_model:finetune:microsoft/deberta-v3-large",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2024-05-21T09:26:18Z |
---
license: mit
base_model: microsoft/deberta-v3-large
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: deberta-disaster-tweet-recognizer
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. -->
# Deberta Disaster Tweet Recognizer
This model is a fine-tuned version of [microsoft/deberta-v3-large](https://huggingface.co/microsoft/deberta-v3-large) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4104
- F1: 0.8
## 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: 8e-06
- train_batch_size: 32
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 4
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| No log | 1.0 | 191 | 0.4159 | 0.7894 |
| No log | 2.0 | 382 | 0.3845 | 0.7973 |
| 0.4497 | 3.0 | 573 | 0.3952 | 0.8016 |
| 0.4497 | 4.0 | 764 | 0.4104 | 0.8 |
### Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2
|
vinod9966/b_lora_sdxl_1.0
|
vinod9966
| 2024-05-21T09:37:09Z | 1 | 1 |
diffusers
|
[
"diffusers",
"text-to-image",
"stable-diffusion",
"lora",
"template:sd-lora",
"base_model:stabilityai/stable-diffusion-xl-base-1.0",
"base_model:adapter:stabilityai/stable-diffusion-xl-base-1.0",
"region:us"
] |
text-to-image
| 2024-05-21T09:37:03Z |
---
tags:
- text-to-image
- stable-diffusion
- lora
- diffusers
- template:sd-lora
widget:
- text: '-'
output:
url: images/balakrishna10.jpeg
base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt: Balakrishna or balakrishna
---
# b_lora_sdxl_1.0
<Gallery />
## Trigger words
You should use `Balakrishna or balakrishna` to trigger the image generation.
## Download model
Weights for this model are available in Safetensors format.
[Download](/vinod9966/b_lora_sdxl_1.0/tree/main) them in the Files & versions tab.
|
KangXen/enhi-st3-xlmr
|
KangXen
| 2024-05-21T09:33:24Z | 181 | 0 |
transformers
|
[
"transformers",
"safetensors",
"xlm-roberta",
"text-classification",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2024-05-21T09:32:41Z |
---
library_name: transformers
tags: []
---
# 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. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **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]
|
DUAL-GPO-2/phi-2-irepo-chatml-v20-i1
|
DUAL-GPO-2
| 2024-05-21T09:31:10Z | 2 | 0 |
peft
|
[
"peft",
"tensorboard",
"safetensors",
"phi",
"alignment-handbook",
"generated_from_trainer",
"trl",
"dpo",
"custom_code",
"dataset:HuggingFaceH4/ultrafeedback_binarized",
"base_model:DUAL-GPO/phi-2-irepo-chatml-merged-i0",
"base_model:adapter:DUAL-GPO/phi-2-irepo-chatml-merged-i0",
"region:us"
] | null | 2024-05-21T05:51:02Z |
---
library_name: peft
tags:
- alignment-handbook
- generated_from_trainer
- trl
- dpo
- generated_from_trainer
base_model: DUAL-GPO/phi-2-irepo-chatml-merged-i0
datasets:
- HuggingFaceH4/ultrafeedback_binarized
model-index:
- name: phi-2-irepo-chatml-v20-i1
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. -->
# phi-2-irepo-chatml-v20-i1
This model is a fine-tuned version of [DUAL-GPO/phi-2-irepo-chatml-merged-i0](https://huggingface.co/DUAL-GPO/phi-2-irepo-chatml-merged-i0) on the HuggingFaceH4/ultrafeedback_binarized 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-06
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1
### Training results
### Framework versions
- PEFT 0.7.1
- Transformers 4.36.2
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.15.2
|
AbhijitShejal/gpt-neox-20b-chat-finetune
|
AbhijitShejal
| 2024-05-21T09:30:44Z | 1 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2024-05-21T09:30:41Z |
---
library_name: peft
---
## 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 0.4.0
|
MaziyarPanahi/NeuralsynthesisMeliodas-7B-GGUF
|
MaziyarPanahi
| 2024-05-21T09:28:51Z | 121 | 0 |
transformers
|
[
"transformers",
"gguf",
"mistral",
"quantized",
"2-bit",
"3-bit",
"4-bit",
"5-bit",
"6-bit",
"8-bit",
"GGUF",
"safetensors",
"text-generation",
"merge",
"mergekit",
"lazymergekit",
"automerger",
"base_model:AurelPx/Meliodas-7b-dare",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us",
"base_model:automerger/NeuralsynthesisMeliodas-7B",
"base_model:quantized:automerger/NeuralsynthesisMeliodas-7B"
] |
text-generation
| 2024-05-21T09:00:01Z |
---
tags:
- quantized
- 2-bit
- 3-bit
- 4-bit
- 5-bit
- 6-bit
- 8-bit
- GGUF
- transformers
- safetensors
- mistral
- text-generation
- merge
- mergekit
- lazymergekit
- automerger
- base_model:AurelPx/Meliodas-7b-dare
- license:apache-2.0
- autotrain_compatible
- endpoints_compatible
- text-generation-inference
- region:us
- text-generation
model_name: NeuralsynthesisMeliodas-7B-GGUF
base_model: automerger/NeuralsynthesisMeliodas-7B
inference: false
model_creator: automerger
pipeline_tag: text-generation
quantized_by: MaziyarPanahi
---
# [MaziyarPanahi/NeuralsynthesisMeliodas-7B-GGUF](https://huggingface.co/MaziyarPanahi/NeuralsynthesisMeliodas-7B-GGUF)
- Model creator: [automerger](https://huggingface.co/automerger)
- Original model: [automerger/NeuralsynthesisMeliodas-7B](https://huggingface.co/automerger/NeuralsynthesisMeliodas-7B)
## Description
[MaziyarPanahi/NeuralsynthesisMeliodas-7B-GGUF](https://huggingface.co/MaziyarPanahi/NeuralsynthesisMeliodas-7B-GGUF) contains GGUF format model files for [automerger/NeuralsynthesisMeliodas-7B](https://huggingface.co/automerger/NeuralsynthesisMeliodas-7B).
### 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 incomplete 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.
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
* [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration. Linux available, in beta as of 27/11/2023.
* [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.
* [GPT4All](https://gpt4all.io/index.html), a free and open source local running GUI, supporting Windows, Linux and macOS with full GPU accel.
* [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.
* [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use.
* [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server. Note, as of time of writing (November 27th 2023), ctransformers has not been updated in a long time and does not support many recent models.
## Special thanks
🙏 Special thanks to [Georgi Gerganov](https://github.com/ggerganov) and the whole team working on [llama.cpp](https://github.com/ggerganov/llama.cpp/) for making all of this possible.
|
HPLT/gpt-33b-nordic-prerelease
|
HPLT
| 2024-05-21T09:28:47Z | 9 | 0 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"fi",
"nn",
"en",
"no",
"da",
"sv",
"is",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2024-02-29T12:52:40Z |
---
license: apache-2.0
language:
- fi
- nn
- en
- 'no'
- da
- sv
- is
---
This is a pre-release checkpoint for a Nordic generative language model currently in training.
This preliminary release is provided for HPLT (https://hplt-project.org/) deliverable 4.1 (“First language models trained”)(https://hplt-project.org/deliverables). Consult the HPLT website for further details.
More documentation will be provided soon.
UPDATE: our Nordic model is now called Viking!
-------
# Viking 7B, 13B and 33B
_**NOTE:** These are **research checkpoint** of a model for which **training has not been completed.** It is being provided in its current state for research and testing purposes. **Care should be taken when using the outputs of the model.** Once pretraining has completed we intend to release additional instruction-tuned and chat-tuned varieties._
Viking 7B, 13B and 13B are a 7B, 13B and 33B parameter decoder-only transformers pretrained on Finnish,
English, Swedish, Danish, Norwegian, Icelandic and code. They are being trained
on 2 trillion tokens (1.3 trillion as of this release).
Viking is a fully open source model and is made available under the Apache 2.0 License.
Viking was created in a collaboration between the [TurkuNLP group](https://turkunlp.org/) of the University of Turku, [SiloGen](https://www.silo.ai/silogen) from [Silo AI](https://www.silo.ai/), and [High Performance Language Technologies](https://hplt-project.org/) (HPLT). Training was conducted on the [LUMI supercomputer](https://www.lumi-supercomputer.eu/), using compute resources generously provided by [CSC](https://csc.fi/) - IT Center for Science, Finland.
This project is part of an ongoing effort to create open source large language models for non-English and especially low resource languages like Finnish. The mode is fluent in Finnish, English, the Scandinavian languages and capable of basic translation between them. It is also able to understand and generate code.
More info available at:
[Viking 7B](https://huggingface.co/LumiOpen/Viking-7B)
[Viking 13B](https://huggingface.co/LumiOpen/Viking-13B)
[Viking 33B](https://huggingface.co/LumiOpen/Viking-33B)
|
XingeTong/my_model_Experiment_Colab_0521
|
XingeTong
| 2024-05-21T09:28:06Z | 104 | 0 |
transformers
|
[
"transformers",
"safetensors",
"roberta",
"text-classification",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2024-05-21T09:27:04Z |
---
library_name: transformers
tags: []
---
# 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. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **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]
|
HPLT/gpt-13b-nordic-prerelease
|
HPLT
| 2024-05-21T09:28:04Z | 27 | 1 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"fi",
"nn",
"en",
"no",
"da",
"sv",
"is",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2024-02-29T12:41:58Z |
---
license: apache-2.0
language:
- fi
- nn
- en
- 'no'
- da
- sv
- is
---
This is a pre-release checkpoint for a Nordic generative language model currently in training.
This preliminary release is provided for HPLT (https://hplt-project.org/) deliverable 4.1 (“First language models trained”)(https://hplt-project.org/deliverables). Consult the HPLT website for further details.
More documentation will be provided soon.
UPDATE: our Nordic model is now called Viking!
-------
# Viking 7B, 13B and 33B
_**NOTE:** These are **research checkpoint** of a model for which **training has not been completed.** It is being provided in its current state for research and testing purposes. **Care should be taken when using the outputs of the model.** Once pretraining has completed we intend to release additional instruction-tuned and chat-tuned varieties._
Viking 7B, 13B and 13B are a 7B, 13B and 33B parameter decoder-only transformers pretrained on Finnish,
English, Swedish, Danish, Norwegian, Icelandic and code. They are being trained
on 2 trillion tokens (1.3 trillion as of this release).
Viking is a fully open source model and is made available under the Apache 2.0 License.
Viking was created in a collaboration between the [TurkuNLP group](https://turkunlp.org/) of the University of Turku, [SiloGen](https://www.silo.ai/silogen) from [Silo AI](https://www.silo.ai/), and [High Performance Language Technologies](https://hplt-project.org/) (HPLT). Training was conducted on the [LUMI supercomputer](https://www.lumi-supercomputer.eu/), using compute resources generously provided by [CSC](https://csc.fi/) - IT Center for Science, Finland.
This project is part of an ongoing effort to create open source large language models for non-English and especially low resource languages like Finnish. The mode is fluent in Finnish, English, the Scandinavian languages and capable of basic translation between them. It is also able to understand and generate code.
More info available at:
[Viking 7B](https://huggingface.co/LumiOpen/Viking-7B)
[Viking 13B](https://huggingface.co/LumiOpen/Viking-13B)
[Viking 33B](https://huggingface.co/LumiOpen/Viking-33B)
|
HPLT/gpt-7b-nordic-prerelease
|
HPLT
| 2024-05-21T09:27:30Z | 14 | 2 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"fi",
"nn",
"en",
"no",
"da",
"sv",
"is",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2024-02-29T12:16:47Z |
---
license: apache-2.0
language:
- fi
- nn
- en
- 'no'
- da
- sv
- is
---
This is a pre-release checkpoint for a Nordic generative language model currently in training.
This preliminary release is provided for HPLT (https://hplt-project.org/) deliverable 4.1 (“First language models trained”)(https://hplt-project.org/deliverables). Consult the HPLT website for further details.
More documentation will be provided soon.
UPDATE: our Nordic model is now called Viking!
-------
# Viking 7B, 13B and 33B
_**NOTE:** These are **research checkpoint** of a model for which **training has not been completed.** It is being provided in its current state for research and testing purposes. **Care should be taken when using the outputs of the model.** Once pretraining has completed we intend to release additional instruction-tuned and chat-tuned varieties._
Viking 7B, 13B and 13B are a 7B, 13B and 33B parameter decoder-only transformers pretrained on Finnish,
English, Swedish, Danish, Norwegian, Icelandic and code. They are being trained
on 2 trillion tokens (1.3 trillion as of this release).
Viking is a fully open source model and is made available under the Apache 2.0 License.
Viking was created in a collaboration between the [TurkuNLP group](https://turkunlp.org/) of the University of Turku, [SiloGen](https://www.silo.ai/silogen) from [Silo AI](https://www.silo.ai/), and [High Performance Language Technologies](https://hplt-project.org/) (HPLT). Training was conducted on the [LUMI supercomputer](https://www.lumi-supercomputer.eu/), using compute resources generously provided by [CSC](https://csc.fi/) - IT Center for Science, Finland.
This project is part of an ongoing effort to create open source large language models for non-English and especially low resource languages like Finnish. The mode is fluent in Finnish, English, the Scandinavian languages and capable of basic translation between them. It is also able to understand and generate code.
More info available at:
[Viking 7B](https://huggingface.co/LumiOpen/Viking-7B)
[Viking 13B](https://huggingface.co/LumiOpen/Viking-13B)
[Viking 33B](https://huggingface.co/LumiOpen/Viking-33B)
|
stefanliemawan/w2v2-libri-10min
|
stefanliemawan
| 2024-05-21T09:27:25Z | 0 | 0 |
transformers
|
[
"transformers",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2024-05-21T09:04:50Z |
---
library_name: transformers
tags: []
---
# 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. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **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]
|
Mukalingam0813/multilingual-distilbert-taxonamy-classifier
|
Mukalingam0813
| 2024-05-21T09:23:34Z | 104 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"distilbert",
"text-classification",
"arxiv:1910.09700",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2024-05-02T05:08:18Z |
---
license: apache-2.0
---
# 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]
|
titantomorrow/taxi-v3
|
titantomorrow
| 2024-05-21T09:20:01Z | 0 | 0 | null |
[
"Taxi-v3",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2024-05-21T09:19:58Z |
---
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="titantomorrow/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"])
```
|
NLP-FEUP/FT-distilbert-base-uncased
|
NLP-FEUP
| 2024-05-21T09:19:27Z | 109 | 0 |
transformers
|
[
"transformers",
"safetensors",
"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
| 2024-05-20T14:56:34Z |
---
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: FT-distilbert-base-uncased
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. -->
# FT-distilbert-base-uncased
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5957
- Accuracy: 0.7
## 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
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| No log | 1.0 | 40 | 0.6820 | 0.575 |
| No log | 2.0 | 80 | 0.6354 | 0.725 |
| No log | 3.0 | 120 | 0.5957 | 0.7 |
### Framework versions
- Transformers 4.41.0
- Pytorch 2.3.0
- Datasets 2.19.1
- Tokenizers 0.19.1
|
mrguz170/Aura
|
mrguz170
| 2024-05-21T09:18:17Z | 2 | 0 |
transformers
|
[
"transformers",
"pytorch",
"safetensors",
"llama",
"text-generation",
"unsloth",
"trl",
"sft",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2024-05-02T00:58:28Z |
---
library_name: transformers
tags:
- unsloth
- trl
- sft
---
# 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. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **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]
|
azizkt/HPY_gpt2_vFP2
|
azizkt
| 2024-05-21T09:16:19Z | 205 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"gpt2",
"text-generation",
"generated_from_trainer",
"license:cc-by-sa-4.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2024-05-21T08:09:21Z |
---
license: cc-by-sa-4.0
tags:
- generated_from_trainer
model-index:
- name: HPY_gpt2_vFP2
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. -->
# HPY_gpt2_vFP2
This model is a fine-tuned version of [ClassCat/gpt2-base-french](https://huggingface.co/ClassCat/gpt2-base-french) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7000
## 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
- gradient_accumulation_steps: 8
- total_train_batch_size: 64
- 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 |
|:-------------:|:-----:|:----:|:---------------:|
| No log | 1.0 | 416 | 0.7576 |
| 0.8762 | 2.0 | 832 | 0.7191 |
| 0.7017 | 3.0 | 1249 | 0.7044 |
| 0.6672 | 4.0 | 1664 | 0.7000 |
### Framework versions
- Transformers 4.30.0
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.13.3
|
titantomorrow/q-FrozenLake-v1-4x4-noSlippery
|
titantomorrow
| 2024-05-21T09:14:14Z | 0 | 0 | null |
[
"FrozenLake-v1-4x4-no_slippery",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2024-05-21T09:14:12Z |
---
tags:
- FrozenLake-v1-4x4-no_slippery
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: q-FrozenLake-v1-4x4-noSlippery
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: FrozenLake-v1-4x4-no_slippery
type: FrozenLake-v1-4x4-no_slippery
metrics:
- type: mean_reward
value: 1.00 +/- 0.00
name: mean_reward
verified: false
---
# **Q-Learning** Agent playing1 **FrozenLake-v1**
This is a trained model of a **Q-Learning** agent playing **FrozenLake-v1** .
## Usage
```python
model = load_from_hub(repo_id="titantomorrow/q-FrozenLake-v1-4x4-noSlippery", 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"])
```
|
gudjonk93/male_over_49
|
gudjonk93
| 2024-05-21T09:10:01Z | 107 | 0 |
transformers
|
[
"transformers",
"pytorch",
"wav2vec2",
"automatic-speech-recognition",
"WER",
"is",
"model-index",
"endpoints_compatible",
"region:us"
] |
automatic-speech-recognition
| 2024-04-22T09:59:31Z |
---
language: is
tags:
- automatic-speech-recognition
- wav2vec2
- WER
model-index:
- name: "gudjonk93/male_over_49"
results:
- task:
name: "Automatic Speech Recognition"
type: automatic-speech-recognition
dataset:
name: "Samrómur Milljón, split=male_gt_49_yrs (Validation)"
type: "language-and-voice-lab/samromur_milljon"
split: "validation"
args: "male_gt_49_yrs"
metrics:
- name: "WER Seed 42 - Split 1"
type: wer
value: 15.5
- name: "WER Seed 42 - Split 2"
type: wer
value: 16.1
- name: "WER Seed 42 - Split 3"
type: wer
value: 16.1
- name: "WER Seed 43 - Split 1"
type: wer
value: 15.6
- name: "WER Seed 43 - Split 2"
type: wer
value: 16.1
- name: "WER Seed 43 - Split 3"
type: wer
value: 16.0
- name: "WER Seed 44 - Split 1"
type: wer
value: 15.9
- name: "WER Seed 44 - Split 2"
type: wer
value: 15.7
- name: "WER Seed 44 - Split 3"
type: wer
value: 16.0
- name: "Avg WER"
type: wer
value: 15.9
---
# Model Description
Provide your detailed description here...
|
gudjonk93/female_18_to_49
|
gudjonk93
| 2024-05-21T09:07:40Z | 107 | 0 |
transformers
|
[
"transformers",
"pytorch",
"wav2vec2",
"automatic-speech-recognition",
"WER",
"is",
"model-index",
"endpoints_compatible",
"region:us"
] |
automatic-speech-recognition
| 2024-05-08T11:09:08Z |
---
language: is
tags:
- automatic-speech-recognition
- wav2vec2
- WER
model-index:
- name: "gudjonk93/female_18_to_49"
results:
- task:
name: "Automatic Speech Recognition"
type: automatic-speech-recognition
dataset:
name: "Samrómur Milljón, split=female_18to49_yrs (Validation)"
type: "language-and-voice-lab/samromur_milljon"
split: "validation"
args: "female_18to49_yrs"
metrics:
- name: "WER Seed 42 - Split 1"
type: wer
value: 8.4
- name: "WER Seed 42 - Split 2"
type: wer
value: 8.5
- name: "WER Seed 42 - Split 3"
type: wer
value: 8.5
- name: "WER Seed 43 - Split 1"
type: wer
value: 8.4
- name: "WER Seed 43 - Split 2"
type: wer
value: 8.5
- name: "WER Seed 43 - Split 3"
type: wer
value: 8.5
- name: "WER Seed 44 - Split 1"
type: wer
value: 8.5
- name: "WER Seed 44 - Split 2"
type: wer
value: 8.5
- name: "WER Seed 44 - Split 3"
type: wer
value: 8.4
- name: "Avg WER"
type: wer
value: 8.5
---
# Model Description
Provide your detailed description here...
|
AjayMukundS/Llama-2-7b-chat-finetune
|
AjayMukundS
| 2024-05-21T09:06:22Z | 7 | 2 |
transformers
|
[
"transformers",
"pytorch",
"llama",
"text-generation",
"text-generation-inference",
"en",
"dataset:mlabonne/guanaco-llama2-1k",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2024-05-21T08:23:06Z |
---
license: mit
datasets:
- mlabonne/guanaco-llama2-1k
language:
- en
metrics:
- bleu
tags:
- text-generation-inference
pipeline_tag: text-generation
---
# Deployed Model
AjayMukundS/Llama-2-7b-chat-finetune
# Model Description
This is a Llama 2 Fine Tuned Model with 7 Billion Parameters on the Dataset from **mlabonne/guanaco-llama2**. The training data is basically a Chat between a Human and an Assistant where the Human poses some queries and the Assistant responds to those queries in a suitable fashion.
In the case of Llama 2, the following Chat Template is used for the chat models:
**(s)[INST] ((sys))**
**SYSTEM PROMPT**
**((/sys))**
**User Prompt [/INST] Model Answer (/s)**
System Prompt (optional) --> to guide the model
User prompt (required) --> to give the instruction / User Query
Model Answer (required)
# Training Data
The Instruction Dataset is reformated to follow the above Llama 2 template.
**Original Dataset** --> https://huggingface.co/datasets/timdettmers/openassistant-guanaco\
**Reformated Dataset with 1K Samples** --> https://huggingface.co/datasets/mlabonne/guanaco-llama2-1k
**Complete Reformated Datset** --> https://huggingface.co/datasets/mlabonne/guanaco-llama2
To know how this dataset was created, you can check this notebook --> https://colab.research.google.com/drive/1Ad7a9zMmkxuXTOh1Z7-rNSICA4dybpM2?usp=sharing
To drastically reduce the VRAM usage, we must fine-tune the model in 4-bit precision, which is why we’ll use QLoRA here and the GPU on which the model was fined tuned on was **L4 (Google Colab Pro)**
# Process
1) Load the dataset as defined.
2) Configure bitsandbytes for 4-bit quantization.
3) Load the Llama 2 model in 4-bit precision on a GPU (L4 - Google Colab Pro) with the corresponding tokenizer.
4) Loading configurations for QLoRA, regular training parameters, and pass everything to the SFTTrainer.
5) Fine Tuning Starts...
|
gudjonk93/female_over_49
|
gudjonk93
| 2024-05-21T09:04:27Z | 109 | 0 |
transformers
|
[
"transformers",
"pytorch",
"wav2vec2",
"automatic-speech-recognition",
"WER",
"is",
"model-index",
"endpoints_compatible",
"region:us"
] |
automatic-speech-recognition
| 2024-05-08T11:27:59Z |
---
language: is
tags:
- automatic-speech-recognition
- wav2vec2
- WER
model-index:
- name: "gudjonk93/female_over_49"
results:
- task:
name: "Automatic Speech Recognition"
type: automatic-speech-recognition
dataset:
name: "Samrómur Milljón, split=female_gt_49_yrs (Validation)"
type: "language-and-voice-lab/samromur_milljon"
split: "validation"
args: "female_gt_49_yrs"
metrics:
- name: "WER Seed 42 - Split 1"
type: wer
value: 10.9
- name: "WER Seed 42 - Split 2"
type: wer
value: 10.9
- name: "WER Seed 42 - Split 3"
type: wer
value: 11.2
- name: "WER Seed 43 - Split 1"
type: wer
value: 11.2
- name: "WER Seed 43 - Split 2"
type: wer
value: 10.9
- name: "WER Seed 43 - Split 3"
type: wer
value: 10.8
- name: "WER Seed 44 - Split 1"
type: wer
value: 11.0
- name: "WER Seed 44 - Split 2"
type: wer
value: 10.6
- name: "WER Seed 44 - Split 3"
type: wer
value: 11.2
- name: "Avg WER"
type: wer
value: 11.0
---
# Model Description
Provide your detailed description here...
|
gudjonk93/male_18_to_49
|
gudjonk93
| 2024-05-21T09:01:53Z | 109 | 0 |
transformers
|
[
"transformers",
"pytorch",
"wav2vec2",
"automatic-speech-recognition",
"WER",
"is",
"model-index",
"endpoints_compatible",
"region:us"
] |
automatic-speech-recognition
| 2024-05-09T16:35:30Z |
---
language: is
tags:
- automatic-speech-recognition
- wav2vec2
- WER
model-index:
- name: "gudjonk93/male_18_to_49"
results:
- task:
name: "Automatic Speech Recognition"
type: automatic-speech-recognition
dataset:
name: "Samrómur Milljón, split=male_18to49_yrs (Validation)"
type: "language-and-voice-lab/samromur_milljon"
split: "validation"
args: "male_18to49_yrs"
metrics:
- name: "WER Seed 42 - Split 1"
type: wer
value: 10.6
- name: "WER Seed 42 - Split 2"
type: wer
value: 10.3
- name: "WER Seed 42 - Split 3"
type: wer
value: 10.5
- name: "WER Seed 43 - Split 1"
type: wer
value: 10.5
- name: "WER Seed 43 - Split 2"
type: wer
value: 10.4
- name: "WER Seed 43 - Split 3"
type: wer
value: 10.5
- name: "WER Seed 44 - Split 1"
type: wer
value: 10.4
- name: "WER Seed 44 - Split 2"
type: wer
value: 10.7
- name: "WER Seed 44 - Split 3"
type: wer
value: 10.3
- name: "Avg WER"
type: wer
value: 10.5
---
# Model Description
Provide your detailed description here...
|
abdiharyadi/chat-indogpt-pilot
|
abdiharyadi
| 2024-05-21T08:57:42Z | 192 | 0 |
transformers
|
[
"transformers",
"tensorboard",
"safetensors",
"gpt2",
"text-generation",
"generated_from_trainer",
"base_model:indobenchmark/indogpt",
"base_model:finetune:indobenchmark/indogpt",
"license:mit",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2024-05-21T08:28:43Z |
---
license: mit
base_model: indobenchmark/indogpt
tags:
- generated_from_trainer
model-index:
- name: chat-indogpt-pilot
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. -->
# chat-indogpt-pilot
This model is a fine-tuned version of [indobenchmark/indogpt](https://huggingface.co/indobenchmark/indogpt) 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: 1e-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: 1
### Training results
### Framework versions
- Transformers 4.40.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
|
shuxing79/q-Taxi-v3
|
shuxing79
| 2024-05-21T08:57:36Z | 0 | 0 | null |
[
"Taxi-v3",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2024-05-21T08:56:08Z |
---
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 +/- 2.75
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
model = load_from_hub(repo_id="shuxing79/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"])
|
anzorq/w2v-bert-2.0-kbd-v2
|
anzorq
| 2024-05-21T08:53:24Z | 26 | 0 |
transformers
|
[
"transformers",
"safetensors",
"wav2vec2-bert",
"automatic-speech-recognition",
"kbd",
"dataset:anzorq/kbd_speech",
"dataset:anzorq/sixuxar_yijiri_mak7",
"license:mit",
"endpoints_compatible",
"region:us"
] |
automatic-speech-recognition
| 2024-05-20T01:02:55Z |
---
license: mit
language:
- kbd
datasets:
- anzorq/kbd_speech
- anzorq/sixuxar_yijiri_mak7
metrics:
- wer
pipeline_tag: automatic-speech-recognition
---
# Circassian (Kabardian) ASR Model
This is a fine-tuned model for Automatic Speech Recognition (ASR) in `kbd`, based on the `facebook/w2v-bert-2.0` model.
The model was trained on a combination of the `anzorq/kbd_speech` (filtered on `country=russia`) and `anzorq/sixuxar_yijiri_mak7` datasets.
## Model Details
- **Base Model**: facebook/w2v-bert-2.0
- **Language**: Kabardian
- **Task**: Automatic Speech Recognition (ASR)
- **Datasets**: anzorq/kbd_speech, anzorq/sixuxar_yijiri_mak7
- **Training Steps**: 4000
## Training
The model was fine-tuned using the following training arguments:
```python
TrainingArguments(
output_dir='output',
group_by_length=True,
per_device_train_batch_size=8,
gradient_accumulation_steps=2,
evaluation_strategy="steps",
num_train_epochs=10,
gradient_checkpointing=True,
fp16=True,
save_steps=1000,
eval_steps=500,
logging_steps=300,
learning_rate=5e-5,
warmup_steps=500,
save_total_limit=2,
push_to_hub=True,
report_to="wandb"
)
```
## Performance
The model's performance during training:
| Step | Training Loss | Validation Loss | Wer |
|------|---------------|-----------------|----------|
| 500 | 2.761100 | 0.572304 | 0.830552 |
| 1000 | 0.325700 | 0.352516 | 0.678261 |
| 1500 | 0.247000 | 0.271146 | 0.377438 |
| 2000 | 0.179300 | 0.235156 | 0.319859 |
| 2500 | 0.176100 | 0.229383 | 0.293537 |
| 3000 | 0.171600 | 0.208033 | 0.310458 |
| 3500 | 0.133200 | 0.199517 | 0.289542 |
| **4000** | **0.117900** | **0.208304** | **0.258989** | **<-- this model** |
| 4500 | 0.145400 | 0.184942 | 0.285311 |
| 5000 | 0.129600 | 0.195167 | 0.372033 |
| 5500 | 0.122600 | 0.203584 | 0.386369 |
| 6000 | 0.196800 | 0.270521 | 0.687662 |
## Note
To optimize training and reduce tokenizer vocabulary size, prior to training the following digraphs in the training data were replaced with single characters:
```
гъ -> ɣ
дж -> j
дз -> ӡ
жь -> ʐ
кӏ -> қ
къ -> q
кхъ -> qҳ
лъ -> ɬ
лӏ -> ԯ
пӏ -> ԥ
тӏ -> ҭ
фӏ -> ჶ
хь -> h
хъ -> ҳ
цӏ -> ҵ
щӏ -> ɕ
я -> йа
```
After obtaining the transcription, reversed replacements can be applied to restore the original characters.
## Inference
```python
import torchaudio
from transformers import pipeline
pipe = pipeline(model="anzorq/w2v-bert-2.0-kbd-v2", device=0)
reversed_replacements = {
'ɣ': 'гъ', 'j': 'дж', 'ӡ': 'дз', 'ʐ': 'жь',
'қ': 'кӏ', 'q': 'къ', 'qҳ': 'кхъ', 'ɬ': 'лъ',
'ԯ': 'лӏ', 'ԥ': 'пӏ', 'ҭ': 'тӏ', 'ჶ': 'фӏ',
'h': 'хь', 'ҳ': 'хъ', 'ҵ': 'цӏ', 'ɕ': 'щӏ',
'йа': 'я'
}
def reverse_replace_symbols(text):
for orig, replacement in reversed_replacements.items():
text = text.replace(orig, replacement)
return text
def transcribe_speech(audio_path):
waveform, sample_rate = torchaudio.load(audio_path)
waveform = torchaudio.transforms.Resample(orig_freq=sample_rate, new_freq=16000)(waveform)
torchaudio.save("temp.wav", waveform, 16000)
transcription = pipe("temp.wav", chunk_length_s=10)['text']
transcription = reverse_replace_symbols(transcription)
return transcription
audio_path = "audio.wav"
transcription = transcribe_speech(audio_path)
print(f"Transcription: {transcription}")
```
|
GuntramG/autotrain-6doma-5m8vf
|
GuntramG
| 2024-05-21T08:50:58Z | 191 | 0 |
transformers
|
[
"transformers",
"tensorboard",
"safetensors",
"convnextv2",
"image-classification",
"autotrain",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
image-classification
| 2024-05-21T08:46:50Z |
---
tags:
- autotrain
- image-classification
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
---
# Model Trained Using AutoTrain
- Problem type: Image Classification
## Validation Metrics
loss: 0.18285594880580902
f1_macro: 0.9148614413559308
f1_micro: 0.9365456396335257
f1_weighted: 0.9364564915178187
precision_macro: 0.9159613318061458
precision_micro: 0.9365456396335257
precision_weighted: 0.9365041505044936
recall_macro: 0.9139276800740521
recall_micro: 0.9365456396335257
recall_weighted: 0.9365456396335257
accuracy: 0.9365456396335257
|
ortaymed/bert_assurance
|
ortaymed
| 2024-05-21T08:48:16Z | 408 | 0 |
transformers
|
[
"transformers",
"safetensors",
"bert",
"text-classification",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2024-05-20T12:39:15Z |
# bert_assurance
### Model Description
This is the model card of an insurance embeddings model that has been trained on customer documentation with 50K datapoints.
- **Developed by:** Taymed
- **Model type:** BERT base finetuned
- **Language(s) (NLP):** Fr
- **License:** [Spellz ltd]
- **Finetuned from model**: [BERT base]
### Model Sources [optional]
- **Huggingface:** [https://huggingface.co/google-bert/bert-base-uncased]
## How to Get Started with the Model
```python
from transformers import AutoTokenizer, AutoModel
import torch
# Define the model name (either your custom model or a pre-trained model from Hugging Face)
model_name = "ortaymed/bert_assurance" # Replace with your model name or path
# Your Hugging Face token
hf_token = "your-huggingface-token" # Replace with your actual Hugging Face token
# Load the tokenizer and model with the token
tokenizer = AutoTokenizer.from_pretrained(model_name, use_auth_token=hf_token)
model = AutoModel.from_pretrained(model_name, use_auth_token=hf_token)
# Sample input text
input_text = "Your sample input text goes here."
# Tokenize the input text
inputs = tokenizer(input_text, return_tensors="pt")
# Get embeddings
with torch.no_grad():
outputs = model(**inputs)
# Get the embeddings from the last hidden state
embeddings = outputs.last_hidden_state
print(embeddings)
```
|
Dang-gu/2nd_finetune
|
Dang-gu
| 2024-05-21T08:43:56Z | 0 | 0 |
peft
|
[
"peft",
"safetensors",
"trl",
"sft",
"generated_from_trainer",
"base_model:bigcode/starcoder2-3b",
"base_model:adapter:bigcode/starcoder2-3b",
"license:bigcode-openrail-m",
"region:us"
] | null | 2024-05-21T08:43:50Z |
---
license: bigcode-openrail-m
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: bigcode/starcoder2-3b
model-index:
- name: 2nd_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. -->
# 2nd_finetune
This model is a fine-tuned version of [bigcode/starcoder2-3b](https://huggingface.co/bigcode/starcoder2-3b) 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: 1
- eval_batch_size: 8
- seed: 0
- distributed_type: multi-GPU
- num_devices: 2
- gradient_accumulation_steps: 8
- 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: cosine
- lr_scheduler_warmup_steps: 20
- training_steps: 10000
### Training results
### Framework versions
- PEFT 0.8.2
- Transformers 4.40.0
- Pytorch 2.3.0+cu121
- Datasets 2.18.0
- Tokenizers 0.19.1
|
Rimyy/Llama-2-7b-chat-finetuneGSMdataSamzpar
|
Rimyy
| 2024-05-21T08:42:16Z | 3 | 0 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2024-05-21T08:36:33Z |
---
library_name: transformers
tags: []
---
# 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. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **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]
|
DeepMount00/GLiNER_ITA_SMALL
|
DeepMount00
| 2024-05-21T08:41:13Z | 6 | 1 |
gliner
|
[
"gliner",
"pytorch",
"text-classification",
"it",
"arxiv:2311.08526",
"license:apache-2.0",
"region:us"
] |
text-classification
| 2024-05-20T19:27:27Z |
---
license: apache-2.0
pipeline_tag: text-classification
language:
- it
library_name: gliner
---
Still needs some work to improve performance, but it's good—almost like [DeepMount00/universal_ner_ita](https://huggingface.co/DeepMount00/universal_ner_ita).
## Installation
To use this model, you must install the GLiNER Python library:
```
!pip install gliner
```
## Usage
Once you've downloaded the GLiNER library, you can import the GLiNER class. You can then load this model using `GLiNER.from_pretrained` and predict entities with `predict_entities`.
```python
from gliner import GLiNER
model = GLiNER.from_pretrained("DeepMount00/GLiNER_ITA_SMALL")
text = """..."""
labels = ["label1", "label2"]
entities = model.predict_entities(text, labels)
for entity in entities:
print(entity["text"], "=>", entity["label"])
```
## Model Author
* [Michele Montebovi](https://huggingface.co/DeepMount00)
## Citation
```bibtex
@misc{zaratiana2023gliner,
title={GLiNER: Generalist Model for Named Entity Recognition using Bidirectional Transformer},
author={Urchade Zaratiana and Nadi Tomeh and Pierre Holat and Thierry Charnois},
year={2023},
eprint={2311.08526},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
|
ML4BTweetGen/tweet-gpt2
|
ML4BTweetGen
| 2024-05-21T08:40:52Z | 0 | 1 | null |
[
"safetensors",
"text-generation",
"de",
"license:apache-2.0",
"region:us"
] |
text-generation
| 2024-05-20T18:05:42Z |
---
license: apache-2.0
language:
- de
pipeline_tag: text-generation
---
This model is a fine-tuned version of GPTLMHead (GPT2) for text generation/imitation. The models were trained on a corpus of 2.4 Million Tweets of members of the German Parliament (Bundestag), to
generate tweets in the style of each party.
Our objective was to explore the imitation abilities of a foundation model such as GPT2, and also study the rhetorics of different politcal parties, these include following parties:
AfD, CDU/CSU, B90/Die Grünen, Die Linke
|
StreamWang/FriBox-AI
|
StreamWang
| 2024-05-21T08:33:37Z | 0 | 0 | null |
[
"license:apache-2.0",
"region:us"
] | null | 2024-05-21T08:33:37Z |
---
license: apache-2.0
---
|
yqw0920/s-1
|
yqw0920
| 2024-05-21T08:29:10Z | 0 | 0 |
bertopic
|
[
"bertopic",
"biology",
"legal",
"ab",
"ak",
"license:apache-2.0",
"region:us"
] | null | 2024-05-21T06:52:56Z |
---
license: apache-2.0
language:
- ab
- ak
library_name: bertopic
tags:
- biology
- legal
---
|
Felladrin/gguf-MobileLLaMA-1.4B-Chat
|
Felladrin
| 2024-05-21T08:21:42Z | 9 | 0 | null |
[
"gguf",
"base_model:mtgv/MobileLLaMA-1.4B-Chat",
"base_model:quantized:mtgv/MobileLLaMA-1.4B-Chat",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2024-05-21T08:06:43Z |
---
license: apache-2.0
base_model: mtgv/MobileLLaMA-1.4B-Chat
---
GGUF version of [mtgv/MobileLLaMA-1.4B-Chat](https://huggingface.co/mtgv/MobileLLaMA-1.4B-Chat).
|
Felladrin/gguf-sharded-MobileLLaMA-1.4B-Chat
|
Felladrin
| 2024-05-21T08:21:11Z | 9 | 0 | null |
[
"gguf",
"base_model:mtgv/MobileLLaMA-1.4B-Chat",
"base_model:quantized:mtgv/MobileLLaMA-1.4B-Chat",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2024-05-21T08:17:05Z |
---
license: apache-2.0
base_model: mtgv/MobileLLaMA-1.4B-Chat
---
Sharded GGUF version of [mtgv/MobileLLaMA-1.4B-Chat](https://huggingface.co/mtgv/MobileLLaMA-1.4B-Chat).
|
nerottt/test_auto_class
|
nerottt
| 2024-05-21T08:20:10Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2024-05-21T08:19:15Z |
---
library_name: transformers
tags: []
---
# 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. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **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]
|
RichardErkhov/Changgil_-_K2S3-SOLAR-11b-v4.0-4bits
|
RichardErkhov
| 2024-05-21T08:19:56Z | 75 | 0 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"4-bit",
"bitsandbytes",
"region:us"
] |
text-generation
| 2024-05-21T08:10:54Z |
Quantization made by Richard Erkhov.
[Github](https://github.com/RichardErkhov)
[Discord](https://discord.gg/pvy7H8DZMG)
[Request more models](https://github.com/RichardErkhov/quant_request)
K2S3-SOLAR-11b-v4.0 - bnb 4bits
- Model creator: https://huggingface.co/Changgil/
- Original model: https://huggingface.co/Changgil/K2S3-SOLAR-11b-v4.0/
Original model description:
---
license: cc-by-nc-4.0
language:
- ko
---
---
## Developed by :
* K2S3
## Model Number:
* K2S3-SOLAR-11b-v4.0
## Base Model :
* [upstage/SOLAR-10.7B-v1.0](https://huggingface.co/upstage/SOLAR-10.7B-v1.0)
### Training Data
* The training data for this model includes the Standard Korean Dictionary, training data from KULLM at Korea University, abstracts of master's and doctoral theses, Korean language samples from AI Hub, alpaca-gpt4-data, and samples from The OpenOrca Dataset.
* 이 모델의 훈련 데이터에는 표준국어대사전, 고려대학교 KULLM에서 제공한 훈련 데이터, 석사 및 박사학위 논문의 초록, AI Hub에서 제공한 한국어 데이터 샘플, alpaca-gpt4-data, 그리고 OpenOrca Dataset에서 제공한 샘플들이 포함됩니다.
### Training Method
* This model was fine-tuned on the "upstage/SOLAR-10.7B-v1.0" base model using a full parameter tuning method with SFT (Supervised Fine-Tuning).
* 이 모델은 "upstage/SOLAR-10.7B-v1.0" 기반 모델을 SFT를 사용하여 전체 파라미터 조정 방법으로 미세조정되었습니다.
### Hardware
* Hardware: Utilized two A100 (80G*2EA) GPUs for training.
* Training Factors: This model was fine-tuned with SFT, using the HuggingFace SFTtrainer and applied fsdp.
* 이 모델은 SFT를 사용하여 HuggingFace SFTtrainer와 fsdp를 적용하여 미세조정되었습니다.
|
Dlkey/RuRoberta-rightversion
|
Dlkey
| 2024-05-21T08:19:10Z | 0 | 0 | null |
[
"license:apache-2.0",
"region:us"
] | null | 2024-05-21T08:19:10Z |
---
license: apache-2.0
---
|
chaos6749/wav2vec2-large-xlsr-test
|
chaos6749
| 2024-05-21T08:17:26Z | 138 | 0 |
transformers
|
[
"transformers",
"tensorboard",
"safetensors",
"wav2vec2",
"automatic-speech-recognition",
"generated_from_trainer",
"dataset:zeroth_korean",
"base_model:facebook/wav2vec2-large-xlsr-53",
"base_model:finetune:facebook/wav2vec2-large-xlsr-53",
"license:apache-2.0",
"model-index",
"endpoints_compatible",
"region:us"
] |
automatic-speech-recognition
| 2024-05-20T07:09:28Z |
---
license: apache-2.0
base_model: facebook/wav2vec2-large-xlsr-53
tags:
- generated_from_trainer
datasets:
- zeroth_korean
metrics:
- wer
model-index:
- name: wav2vec2-large-xlsr-test
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: zeroth_korean
type: zeroth_korean
config: clean
split: None
args: clean
metrics:
- name: Wer
type: wer
value: 1.0
---
<!-- 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. -->
# wav2vec2-large-xlsr-test
This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the zeroth_korean dataset.
It achieves the following results on the evaluation set:
- Loss: 3.8883
- Wer: 1.0
## 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: 0.0003
- train_batch_size: 64
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1000
- num_epochs: 50
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|:-------------:|:-----:|:----:|:---------------:|:---:|
| 4.3921 | 50.0 | 1000 | 3.8883 | 1.0 |
### Framework versions
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
|
cornhead/flm
|
cornhead
| 2024-05-21T08:17:01Z | 1 | 0 |
diffusers
|
[
"diffusers",
"text-to-image",
"stable-diffusion",
"lora",
"template:sd-lora",
"base_model:WarriorMama777/Other",
"base_model:adapter:WarriorMama777/Other",
"region:us"
] |
text-to-image
| 2024-05-21T08:16:42Z |
---
tags:
- text-to-image
- stable-diffusion
- lora
- diffusers
- template:sd-lora
widget:
- text: '-'
output:
url: >-
images/12186-439904498-award winning masterpiece illustration of a man
filmation motu style trending on artstation highly detailed rendered with
Un9voi1408.jpeg
base_model: WarriorMama777/Other
instance_prompt: null
---
# flm
<Gallery />
## Download model
Weights for this model are available in Safetensors format.
[Download](/cornhead/flm/tree/main) them in the Files & versions tab.
|
ifyou819/summary-news-dataset-1
|
ifyou819
| 2024-05-21T08:14:45Z | 104 | 0 |
transformers
|
[
"transformers",
"tensorboard",
"safetensors",
"pegasus",
"text2text-generation",
"generated_from_trainer",
"base_model:PoseyATX/GPTxLege_FoxHunter",
"base_model:finetune:PoseyATX/GPTxLege_FoxHunter",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text2text-generation
| 2024-05-21T08:13:27Z |
---
base_model: PoseyATX/GPTxLege_FoxHunter
tags:
- generated_from_trainer
model-index:
- name: summary-news-dataset-1
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. -->
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/fine-tune-gpt-model/huggingface/runs/c3xr2675)
# summary-news-dataset-1
This model is a fine-tuned version of [PoseyATX/GPTxLege_FoxHunter](https://huggingface.co/PoseyATX/GPTxLege_FoxHunter) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 9.1046
## 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-06
- train_batch_size: 4
- eval_batch_size: 4
- 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 |
|:-------------:|:-----:|:----:|:---------------:|
| 10.1483 | 1.0 | 791 | 9.2664 |
| 9.4317 | 2.0 | 1582 | 9.1046 |
### Framework versions
- Transformers 4.41.0
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.19.1
|
MochaPixel/4XUltrasharpV10
|
MochaPixel
| 2024-05-21T08:14:21Z | 0 | 0 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2024-05-21T08:12:50Z |
---
license: creativeml-openrail-m
---
|
yh1306/greedy
|
yh1306
| 2024-05-21T08:12:07Z | 0 | 0 | null |
[
"license:apache-2.0",
"region:us"
] | null | 2024-05-21T08:11:45Z |
---
license: apache-2.0
---
|
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.