modelId
stringlengths 5
139
| author
stringlengths 2
42
| last_modified
timestamp[us, tz=UTC]date 2020-02-15 11:33:14
2025-09-07 06:34:03
| downloads
int64 0
223M
| likes
int64 0
11.7k
| library_name
stringclasses 544
values | tags
listlengths 1
4.05k
| pipeline_tag
stringclasses 55
values | createdAt
timestamp[us, tz=UTC]date 2022-03-02 23:29:04
2025-09-07 06:33:46
| card
stringlengths 11
1.01M
|
|---|---|---|---|---|---|---|---|---|---|
unrealheinrich/carol_realistic_dreambooth
|
unrealheinrich
| 2024-01-10T16:18:37Z | 2 | 0 |
diffusers
|
[
"diffusers",
"art",
"text-to-image",
"en",
"license:mit",
"region:us"
] |
text-to-image
| 2024-01-10T16:16:06Z |
---
license: mit
language:
- en
library_name: diffusers
pipeline_tag: text-to-image
tags:
- art
---
|
Sphealls/gpt2-finetuned-wikitext2
|
Sphealls
| 2024-01-10T16:18:18Z | 48 | 0 |
transformers
|
[
"transformers",
"tf",
"gpt2",
"text-generation",
"generated_from_keras_callback",
"base_model:openai-community/gpt2",
"base_model:finetune:openai-community/gpt2",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2024-01-10T15:56:05Z |
---
license: mit
base_model: gpt2
tags:
- generated_from_keras_callback
model-index:
- name: Sphealls/gpt2-finetuned-wikitext2
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. -->
# Sphealls/gpt2-finetuned-wikitext2
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 6.5033
- Validation Loss: 6.3566
- 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 |
|:----------:|:---------------:|:-----:|
| 7.3132 | 6.7758 | 0 |
| 6.5033 | 6.3566 | 1 |
### Framework versions
- Transformers 4.35.2
- TensorFlow 2.15.0
- Datasets 2.16.1
- Tokenizers 0.15.0
|
hyunjerry/distilbert-base-uncased-finetuned-squad
|
hyunjerry
| 2024-01-10T16:15:26Z | 111 | 0 |
transformers
|
[
"transformers",
"tensorboard",
"safetensors",
"distilbert",
"question-answering",
"generated_from_trainer",
"base_model:distilbert/distilbert-base-uncased",
"base_model:finetune:distilbert/distilbert-base-uncased",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
question-answering
| 2023-12-24T06:08:15Z |
---
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
model-index:
- name: distilbert-base-uncased-finetuned-squad
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# distilbert-base-uncased-finetuned-squad
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.4525
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 2.8801 | 1.0 | 507 | 1.7791 |
| 1.5209 | 2.0 | 1014 | 1.4818 |
| 1.1737 | 3.0 | 1521 | 1.4525 |
### Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0
|
invalid-coder/Sakura-SOLAR-Instruct-CarbonVillain-en-10.7B-v2-slerp
|
invalid-coder
| 2024-01-10T16:13:44Z | 13,347 | 0 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"merge",
"mergekit",
"lazymergekit",
"jeonsworld/CarbonVillain-en-10.7B-v2",
"kyujinpy/Sakura-SOLAR-Instruct",
"conversational",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2024-01-10T16:06:58Z |
---
license: apache-2.0
tags:
- merge
- mergekit
- lazymergekit
- jeonsworld/CarbonVillain-en-10.7B-v2
- kyujinpy/Sakura-SOLAR-Instruct
---
# NeuralPipe-7B-slerp
NeuralPipe-7B-slerp is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [jeonsworld/CarbonVillain-en-10.7B-v2](https://huggingface.co/jeonsworld/CarbonVillain-en-10.7B-v2)
* [kyujinpy/Sakura-SOLAR-Instruct](https://huggingface.co/kyujinpy/Sakura-SOLAR-Instruct)
## 🧩 Configuration
```yaml
slices:
- sources:
- model: jeonsworld/CarbonVillain-en-10.7B-v2
layer_range: [0, 48]
- model: kyujinpy/Sakura-SOLAR-Instruct
layer_range: [0, 48]
merge_method: slerp
base_model: jeonsworld/CarbonVillain-en-10.7B-v2
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5 # fallback for rest of tensors
tokenizer_source: union
dtype: float16
```
## 💻 Usage
```python
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "invalid-coder/NeuralPipe-7B-slerp"
messages = [{"role": "user", "content": "What is a large language model?"}]
tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
"text-generation",
model=model,
torch_dtype=torch.float16,
device_map="auto",
)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
```
|
vipinbansal179/SetFit_sms_Analyzer1
|
vipinbansal179
| 2024-01-10T16:06:25Z | 52 | 0 |
setfit
|
[
"setfit",
"safetensors",
"mpnet",
"sentence-transformers",
"text-classification",
"generated_from_setfit_trainer",
"arxiv:2209.11055",
"base_model:sentence-transformers/all-mpnet-base-v2",
"base_model:finetune:sentence-transformers/all-mpnet-base-v2",
"model-index",
"region:us"
] |
text-classification
| 2024-01-10T16:04:01Z |
---
library_name: setfit
tags:
- setfit
- sentence-transformers
- text-classification
- generated_from_setfit_trainer
metrics:
- accuracy
widget:
- text: 'pay rs.20.00 / c 91xx3402 ganeshramkudisodebur 22 - 09 - 2023 . ref:3648483126
. query ? click http://m.paytm.me/care : ppbl'
- text: inform m / s shree salasar balaji tex transfer rs . 10000.00 account . xxxxxxxx2869
yes bank account rtgs / neft / imp
- text: undelivered!\nyour hdfc bank debit card 9875 / c 8494\nreason ch shift . case
address change , update seamless card delivery > > hdfcbk.io/a/0nzoo052
- text: rs 5000.00 debit / c upi 23 - 09 - 2023 14:21:12 vpa 35890012004230@cnrb -
( upi ref 363290511260)-federal bank
- text: 472448 otp set hdfc bank 4 digit login pin . share otp you?call 18002586161
pipeline_tag: text-classification
inference: true
base_model: sentence-transformers/all-mpnet-base-v2
model-index:
- name: SetFit with sentence-transformers/all-mpnet-base-v2
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: Unknown
type: unknown
split: test
metrics:
- type: accuracy
value: 0.9715909090909091
name: Accuracy
---
# SetFit with sentence-transformers/all-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/all-mpnet-base-v2](https://huggingface.co/sentence-transformers/all-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/all-mpnet-base-v2](https://huggingface.co/sentence-transformers/all-mpnet-base-v2)
- **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
- **Maximum Sequence Length:** 384 tokens
- **Number of Classes:** 3 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 |
|:------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| 2 | <ul><li>'840989 otp proceed canara bank mobile banking . valid 15 minute . share otp . - canara bank . kbl8a1ju0mt'</li><li>'cheque . 000102 issue riya collection rs . 12,000.00 present / c xxxxx546157 return unpaid insufficient fund . team idfc bank'</li><li>'avl bal / c xxxx0959 10 - jul-2022 06:06:24 inr 0.00 . combine avl bal inr 0.00 . use mb app track / c - kotak bank'</li></ul> |
| 0 | <ul><li>'/ c . xxxxxxxx7146 debit rs.11933.00 16 - 09 - 23 / c xxxxxxxx4716 credit ( imp ref 325908759095 ) . warm regard , yes bank'</li><li>'send rs.290.00 kotak bank ac x4524 bharatpe90727843812@yesbankltd 13-10-23.upi ref 328684167136 . , kotak.com/fraud'</li><li>'rs.295 transfer / c ... 4322 : lien_marking_fo . total bal : rs.188.8cr . avlbl amt : rs.609.97(28 - 06 - 2022 16:39:53 ) - bank baroda'</li></ul> |
| 1 | <ul><li>'rs 15000credite / c xx4524via neft neofirst technology india private- utr ref hsbcn23276508097 ; avail . bal.:rs 215180.62kotak bank'</li><li>'/ c : xx6775 credit rs.60.00 14 - 11 - 2023 10:47:49 upi - id 8733076955@omni ( upi ref 331800008439).-canara bank'</li><li>'rs.28 credit / c ... 7783 upi/323962847509 kiwicashback_ax . total bal : rs.122751.36cr . avlbl amt : rs.94671.36(27 - 08 - 2023 15:37:01 ) - bank baroda'</li></ul> |
## Evaluation
### Metrics
| Label | Accuracy |
|:--------|:---------|
| **all** | 0.9716 |
## 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("vipinbansal179/SetFit_sms_Analyzer1")
# Run inference
preds = model("472448 otp set hdfc bank 4 digit login pin . share otp you?call 18002586161")
```
<!--
### 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 | 4 | 23.17 | 65 |
| Label | Training Sample Count |
|:------|:----------------------|
| 0 | 231 |
| 1 | 131 |
| 2 | 338 |
### Training Hyperparameters
- batch_size: (16, 16)
- num_epochs: (2, 2)
- max_steps: -1
- sampling_strategy: oversampling
- body_learning_rate: (2e-05, 1e-05)
- head_learning_rate: 0.01
- 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: True
### Training Results
| Epoch | Step | Training Loss | Validation Loss |
|:-------:|:---------:|:-------------:|:---------------:|
| 0.0001 | 1 | 0.2945 | - |
| 0.0026 | 50 | 0.3574 | - |
| 0.0052 | 100 | 0.2512 | - |
| 0.0079 | 150 | 0.2319 | - |
| 0.0105 | 200 | 0.2787 | - |
| 0.0131 | 250 | 0.2129 | - |
| 0.0157 | 300 | 0.2189 | - |
| 0.0183 | 350 | 0.0857 | - |
| 0.0210 | 400 | 0.0932 | - |
| 0.0236 | 450 | 0.065 | - |
| 0.0262 | 500 | 0.0553 | - |
| 0.0288 | 550 | 0.0674 | - |
| 0.0314 | 600 | 0.0239 | - |
| 0.0341 | 650 | 0.0054 | - |
| 0.0367 | 700 | 0.0025 | - |
| 0.0393 | 750 | 0.002 | - |
| 0.0419 | 800 | 0.0007 | - |
| 0.0446 | 850 | 0.001 | - |
| 0.0472 | 900 | 0.0008 | - |
| 0.0498 | 950 | 0.0008 | - |
| 0.0524 | 1000 | 0.0003 | - |
| 0.0550 | 1050 | 0.0012 | - |
| 0.0577 | 1100 | 0.002 | - |
| 0.0603 | 1150 | 0.0192 | - |
| 0.0629 | 1200 | 0.0041 | - |
| 0.0655 | 1250 | 0.0002 | - |
| 0.0681 | 1300 | 0.0001 | - |
| 0.0708 | 1350 | 0.0001 | - |
| 0.0734 | 1400 | 0.0001 | - |
| 0.0760 | 1450 | 0.0004 | - |
| 0.0786 | 1500 | 0.0003 | - |
| 0.0812 | 1550 | 0.0002 | - |
| 0.0839 | 1600 | 0.0004 | - |
| 0.0865 | 1650 | 0.0002 | - |
| 0.0891 | 1700 | 0.0002 | - |
| 0.0917 | 1750 | 0.0001 | - |
| 0.0943 | 1800 | 0.0001 | - |
| 0.0970 | 1850 | 0.0001 | - |
| 0.0996 | 1900 | 0.0001 | - |
| 0.1022 | 1950 | 0.0001 | - |
| 0.1048 | 2000 | 0.0001 | - |
| 0.1075 | 2050 | 0.0015 | - |
| 0.1101 | 2100 | 0.0001 | - |
| 0.1127 | 2150 | 0.0001 | - |
| 0.1153 | 2200 | 0.0001 | - |
| 0.1179 | 2250 | 0.0001 | - |
| 0.1206 | 2300 | 0.0 | - |
| 0.1232 | 2350 | 0.0001 | - |
| 0.1258 | 2400 | 0.0 | - |
| 0.1284 | 2450 | 0.0001 | - |
| 0.1310 | 2500 | 0.0 | - |
| 0.1337 | 2550 | 0.0001 | - |
| 0.1363 | 2600 | 0.0 | - |
| 0.1389 | 2650 | 0.0001 | - |
| 0.1415 | 2700 | 0.0 | - |
| 0.1441 | 2750 | 0.0 | - |
| 0.1468 | 2800 | 0.0 | - |
| 0.1494 | 2850 | 0.0 | - |
| 0.1520 | 2900 | 0.0 | - |
| 0.1546 | 2950 | 0.0 | - |
| 0.1572 | 3000 | 0.0 | - |
| 0.1599 | 3050 | 0.0 | - |
| 0.1625 | 3100 | 0.0 | - |
| 0.1651 | 3150 | 0.0 | - |
| 0.1677 | 3200 | 0.0 | - |
| 0.1704 | 3250 | 0.0 | - |
| 0.1730 | 3300 | 0.0 | - |
| 0.1756 | 3350 | 0.0 | - |
| 0.1782 | 3400 | 0.0 | - |
| 0.1808 | 3450 | 0.0 | - |
| 0.1835 | 3500 | 0.0 | - |
| 0.1861 | 3550 | 0.0003 | - |
| 0.1887 | 3600 | 0.0131 | - |
| 0.1913 | 3650 | 0.0004 | - |
| 0.1939 | 3700 | 0.0001 | - |
| 0.1966 | 3750 | 0.0 | - |
| 0.1992 | 3800 | 0.0001 | - |
| 0.2018 | 3850 | 0.0002 | - |
| 0.2044 | 3900 | 0.0 | - |
| 0.2070 | 3950 | 0.0 | - |
| 0.2097 | 4000 | 0.0001 | - |
| 0.2123 | 4050 | 0.0015 | - |
| 0.2149 | 4100 | 0.0002 | - |
| 0.2175 | 4150 | 0.0 | - |
| 0.2201 | 4200 | 0.0 | - |
| 0.2228 | 4250 | 0.0 | - |
| 0.2254 | 4300 | 0.0 | - |
| 0.2280 | 4350 | 0.0 | - |
| 0.2306 | 4400 | 0.0 | - |
| 0.2333 | 4450 | 0.0 | - |
| 0.2359 | 4500 | 0.0 | - |
| 0.2385 | 4550 | 0.0 | - |
| 0.2411 | 4600 | 0.0 | - |
| 0.2437 | 4650 | 0.0 | - |
| 0.2464 | 4700 | 0.0 | - |
| 0.2490 | 4750 | 0.0 | - |
| 0.2516 | 4800 | 0.0 | - |
| 0.2542 | 4850 | 0.0 | - |
| 0.2568 | 4900 | 0.0 | - |
| 0.2595 | 4950 | 0.0 | - |
| 0.2621 | 5000 | 0.0 | - |
| 0.2647 | 5050 | 0.0 | - |
| 0.2673 | 5100 | 0.0 | - |
| 0.2699 | 5150 | 0.0 | - |
| 0.2726 | 5200 | 0.0 | - |
| 0.2752 | 5250 | 0.0 | - |
| 0.2778 | 5300 | 0.0 | - |
| 0.2804 | 5350 | 0.0 | - |
| 0.2830 | 5400 | 0.0 | - |
| 0.2857 | 5450 | 0.0 | - |
| 0.2883 | 5500 | 0.0 | - |
| 0.2909 | 5550 | 0.0 | - |
| 0.2935 | 5600 | 0.0 | - |
| 0.2962 | 5650 | 0.0 | - |
| 0.2988 | 5700 | 0.0 | - |
| 0.3014 | 5750 | 0.0 | - |
| 0.3040 | 5800 | 0.0 | - |
| 0.3066 | 5850 | 0.0 | - |
| 0.3093 | 5900 | 0.0 | - |
| 0.3119 | 5950 | 0.0 | - |
| 0.3145 | 6000 | 0.0 | - |
| 0.3171 | 6050 | 0.0 | - |
| 0.3197 | 6100 | 0.0 | - |
| 0.3224 | 6150 | 0.0 | - |
| 0.3250 | 6200 | 0.0 | - |
| 0.3276 | 6250 | 0.0 | - |
| 0.3302 | 6300 | 0.0 | - |
| 0.3328 | 6350 | 0.0 | - |
| 0.3355 | 6400 | 0.0 | - |
| 0.3381 | 6450 | 0.0 | - |
| 0.3407 | 6500 | 0.0 | - |
| 0.3433 | 6550 | 0.0 | - |
| 0.3459 | 6600 | 0.0 | - |
| 0.3486 | 6650 | 0.0 | - |
| 0.3512 | 6700 | 0.0 | - |
| 0.3538 | 6750 | 0.0 | - |
| 0.3564 | 6800 | 0.0 | - |
| 0.3591 | 6850 | 0.0 | - |
| 0.3617 | 6900 | 0.0 | - |
| 0.3643 | 6950 | 0.0 | - |
| 0.3669 | 7000 | 0.0 | - |
| 0.3695 | 7050 | 0.0 | - |
| 0.3722 | 7100 | 0.0 | - |
| 0.3748 | 7150 | 0.0 | - |
| 0.3774 | 7200 | 0.0 | - |
| 0.3800 | 7250 | 0.0 | - |
| 0.3826 | 7300 | 0.0 | - |
| 0.3853 | 7350 | 0.0 | - |
| 0.3879 | 7400 | 0.0 | - |
| 0.3905 | 7450 | 0.0 | - |
| 0.3931 | 7500 | 0.0 | - |
| 0.3957 | 7550 | 0.0 | - |
| 0.3984 | 7600 | 0.0 | - |
| 0.4010 | 7650 | 0.0 | - |
| 0.4036 | 7700 | 0.0 | - |
| 0.4062 | 7750 | 0.0 | - |
| 0.4088 | 7800 | 0.0 | - |
| 0.4115 | 7850 | 0.0 | - |
| 0.4141 | 7900 | 0.0 | - |
| 0.4167 | 7950 | 0.0 | - |
| 0.4193 | 8000 | 0.0 | - |
| 0.4220 | 8050 | 0.0 | - |
| 0.4246 | 8100 | 0.0 | - |
| 0.4272 | 8150 | 0.0 | - |
| 0.4298 | 8200 | 0.0 | - |
| 0.4324 | 8250 | 0.0 | - |
| 0.4351 | 8300 | 0.0 | - |
| 0.4377 | 8350 | 0.0 | - |
| 0.4403 | 8400 | 0.0 | - |
| 0.4429 | 8450 | 0.0 | - |
| 0.4455 | 8500 | 0.0 | - |
| 0.4482 | 8550 | 0.0 | - |
| 0.4508 | 8600 | 0.0 | - |
| 0.4534 | 8650 | 0.0 | - |
| 0.4560 | 8700 | 0.0 | - |
| 0.4586 | 8750 | 0.0 | - |
| 0.4613 | 8800 | 0.0 | - |
| 0.4639 | 8850 | 0.0 | - |
| 0.4665 | 8900 | 0.0 | - |
| 0.4691 | 8950 | 0.0001 | - |
| 0.4717 | 9000 | 0.0 | - |
| 0.4744 | 9050 | 0.0 | - |
| 0.4770 | 9100 | 0.0 | - |
| 0.4796 | 9150 | 0.0 | - |
| 0.4822 | 9200 | 0.0 | - |
| 0.4849 | 9250 | 0.0 | - |
| 0.4875 | 9300 | 0.0 | - |
| 0.4901 | 9350 | 0.0 | - |
| 0.4927 | 9400 | 0.0 | - |
| 0.4953 | 9450 | 0.0 | - |
| 0.4980 | 9500 | 0.0 | - |
| 0.5006 | 9550 | 0.0 | - |
| 0.5032 | 9600 | 0.0 | - |
| 0.5058 | 9650 | 0.0 | - |
| 0.5084 | 9700 | 0.0 | - |
| 0.5111 | 9750 | 0.0 | - |
| 0.5137 | 9800 | 0.0 | - |
| 0.5163 | 9850 | 0.0 | - |
| 0.5189 | 9900 | 0.0 | - |
| 0.5215 | 9950 | 0.0 | - |
| 0.5242 | 10000 | 0.0 | - |
| 0.5268 | 10050 | 0.0 | - |
| 0.5294 | 10100 | 0.0 | - |
| 0.5320 | 10150 | 0.0 | - |
| 0.5346 | 10200 | 0.0 | - |
| 0.5373 | 10250 | 0.0 | - |
| 0.5399 | 10300 | 0.0 | - |
| 0.5425 | 10350 | 0.0 | - |
| 0.5451 | 10400 | 0.0 | - |
| 0.5478 | 10450 | 0.0 | - |
| 0.5504 | 10500 | 0.0 | - |
| 0.5530 | 10550 | 0.0 | - |
| 0.5556 | 10600 | 0.0 | - |
| 0.5582 | 10650 | 0.0 | - |
| 0.5609 | 10700 | 0.0 | - |
| 0.5635 | 10750 | 0.0 | - |
| 0.5661 | 10800 | 0.0 | - |
| 0.5687 | 10850 | 0.0 | - |
| 0.5713 | 10900 | 0.0 | - |
| 0.5740 | 10950 | 0.0 | - |
| 0.5766 | 11000 | 0.0 | - |
| 0.5792 | 11050 | 0.0 | - |
| 0.5818 | 11100 | 0.0 | - |
| 0.5844 | 11150 | 0.0 | - |
| 0.5871 | 11200 | 0.0 | - |
| 0.5897 | 11250 | 0.0 | - |
| 0.5923 | 11300 | 0.0 | - |
| 0.5949 | 11350 | 0.0 | - |
| 0.5975 | 11400 | 0.0 | - |
| 0.6002 | 11450 | 0.0 | - |
| 0.6028 | 11500 | 0.0 | - |
| 0.6054 | 11550 | 0.0 | - |
| 0.6080 | 11600 | 0.0 | - |
| 0.6107 | 11650 | 0.0 | - |
| 0.6133 | 11700 | 0.0 | - |
| 0.6159 | 11750 | 0.0 | - |
| 0.6185 | 11800 | 0.0 | - |
| 0.6211 | 11850 | 0.0 | - |
| 0.6238 | 11900 | 0.0 | - |
| 0.6264 | 11950 | 0.0 | - |
| 0.6290 | 12000 | 0.0 | - |
| 0.6316 | 12050 | 0.0 | - |
| 0.6342 | 12100 | 0.0 | - |
| 0.6369 | 12150 | 0.0 | - |
| 0.6395 | 12200 | 0.0 | - |
| 0.6421 | 12250 | 0.0 | - |
| 0.6447 | 12300 | 0.0 | - |
| 0.6473 | 12350 | 0.0 | - |
| 0.6500 | 12400 | 0.0 | - |
| 0.6526 | 12450 | 0.0 | - |
| 0.6552 | 12500 | 0.0 | - |
| 0.6578 | 12550 | 0.0 | - |
| 0.6604 | 12600 | 0.0 | - |
| 0.6631 | 12650 | 0.0 | - |
| 0.6657 | 12700 | 0.0 | - |
| 0.6683 | 12750 | 0.0 | - |
| 0.6709 | 12800 | 0.0 | - |
| 0.6736 | 12850 | 0.0 | - |
| 0.6762 | 12900 | 0.0 | - |
| 0.6788 | 12950 | 0.0 | - |
| 0.6814 | 13000 | 0.0 | - |
| 0.6840 | 13050 | 0.0 | - |
| 0.6867 | 13100 | 0.0 | - |
| 0.6893 | 13150 | 0.0 | - |
| 0.6919 | 13200 | 0.0 | - |
| 0.6945 | 13250 | 0.0 | - |
| 0.6971 | 13300 | 0.0 | - |
| 0.6998 | 13350 | 0.0 | - |
| 0.7024 | 13400 | 0.0 | - |
| 0.7050 | 13450 | 0.0 | - |
| 0.7076 | 13500 | 0.0 | - |
| 0.7102 | 13550 | 0.0 | - |
| 0.7129 | 13600 | 0.0 | - |
| 0.7155 | 13650 | 0.0 | - |
| 0.7181 | 13700 | 0.0 | - |
| 0.7207 | 13750 | 0.0 | - |
| 0.7233 | 13800 | 0.0 | - |
| 0.7260 | 13850 | 0.0 | - |
| 0.7286 | 13900 | 0.0 | - |
| 0.7312 | 13950 | 0.0 | - |
| 0.7338 | 14000 | 0.0 | - |
| 0.7365 | 14050 | 0.0 | - |
| 0.7391 | 14100 | 0.0 | - |
| 0.7417 | 14150 | 0.0 | - |
| 0.7443 | 14200 | 0.0 | - |
| 0.7469 | 14250 | 0.0 | - |
| 0.7496 | 14300 | 0.0 | - |
| 0.7522 | 14350 | 0.0 | - |
| 0.7548 | 14400 | 0.0 | - |
| 0.7574 | 14450 | 0.0 | - |
| 0.7600 | 14500 | 0.0 | - |
| 0.7627 | 14550 | 0.0 | - |
| 0.7653 | 14600 | 0.0 | - |
| 0.7679 | 14650 | 0.0 | - |
| 0.7705 | 14700 | 0.0 | - |
| 0.7731 | 14750 | 0.0 | - |
| 0.7758 | 14800 | 0.0 | - |
| 0.7784 | 14850 | 0.0 | - |
| 0.7810 | 14900 | 0.0 | - |
| 0.7836 | 14950 | 0.0 | - |
| 0.7862 | 15000 | 0.0 | - |
| 0.7889 | 15050 | 0.0 | - |
| 0.7915 | 15100 | 0.0 | - |
| 0.7941 | 15150 | 0.0 | - |
| 0.7967 | 15200 | 0.0 | - |
| 0.7994 | 15250 | 0.0 | - |
| 0.8020 | 15300 | 0.0 | - |
| 0.8046 | 15350 | 0.0 | - |
| 0.8072 | 15400 | 0.0 | - |
| 0.8098 | 15450 | 0.0 | - |
| 0.8125 | 15500 | 0.0 | - |
| 0.8151 | 15550 | 0.0 | - |
| 0.8177 | 15600 | 0.0 | - |
| 0.8203 | 15650 | 0.0 | - |
| 0.8229 | 15700 | 0.0 | - |
| 0.8256 | 15750 | 0.0 | - |
| 0.8282 | 15800 | 0.0 | - |
| 0.8308 | 15850 | 0.0 | - |
| 0.8334 | 15900 | 0.0 | - |
| 0.8360 | 15950 | 0.0 | - |
| 0.8387 | 16000 | 0.0 | - |
| 0.8413 | 16050 | 0.0 | - |
| 0.8439 | 16100 | 0.0 | - |
| 0.8465 | 16150 | 0.0 | - |
| 0.8491 | 16200 | 0.0 | - |
| 0.8518 | 16250 | 0.0 | - |
| 0.8544 | 16300 | 0.0 | - |
| 0.8570 | 16350 | 0.0 | - |
| 0.8596 | 16400 | 0.0 | - |
| 0.8622 | 16450 | 0.0 | - |
| 0.8649 | 16500 | 0.0 | - |
| 0.8675 | 16550 | 0.0 | - |
| 0.8701 | 16600 | 0.0 | - |
| 0.8727 | 16650 | 0.0 | - |
| 0.8754 | 16700 | 0.0 | - |
| 0.8780 | 16750 | 0.0 | - |
| 0.8806 | 16800 | 0.0 | - |
| 0.8832 | 16850 | 0.0 | - |
| 0.8858 | 16900 | 0.0 | - |
| 0.8885 | 16950 | 0.0 | - |
| 0.8911 | 17000 | 0.0 | - |
| 0.8937 | 17050 | 0.0 | - |
| 0.8963 | 17100 | 0.0 | - |
| 0.8989 | 17150 | 0.0 | - |
| 0.9016 | 17200 | 0.0 | - |
| 0.9042 | 17250 | 0.0 | - |
| 0.9068 | 17300 | 0.0 | - |
| 0.9094 | 17350 | 0.0 | - |
| 0.9120 | 17400 | 0.0 | - |
| 0.9147 | 17450 | 0.0 | - |
| 0.9173 | 17500 | 0.0 | - |
| 0.9199 | 17550 | 0.0 | - |
| 0.9225 | 17600 | 0.0 | - |
| 0.9251 | 17650 | 0.0 | - |
| 0.9278 | 17700 | 0.0 | - |
| 0.9304 | 17750 | 0.0 | - |
| 0.9330 | 17800 | 0.0 | - |
| 0.9356 | 17850 | 0.0 | - |
| 0.9383 | 17900 | 0.0 | - |
| 0.9409 | 17950 | 0.0 | - |
| 0.9435 | 18000 | 0.0 | - |
| 0.9461 | 18050 | 0.0 | - |
| 0.9487 | 18100 | 0.0 | - |
| 0.9514 | 18150 | 0.0 | - |
| 0.9540 | 18200 | 0.0 | - |
| 0.9566 | 18250 | 0.0 | - |
| 0.9592 | 18300 | 0.0 | - |
| 0.9618 | 18350 | 0.0 | - |
| 0.9645 | 18400 | 0.0 | - |
| 0.9671 | 18450 | 0.0 | - |
| 0.9697 | 18500 | 0.0 | - |
| 0.9723 | 18550 | 0.0 | - |
| 0.9749 | 18600 | 0.0 | - |
| 0.9776 | 18650 | 0.0 | - |
| 0.9802 | 18700 | 0.0 | - |
| 0.9828 | 18750 | 0.0 | - |
| 0.9854 | 18800 | 0.0 | - |
| 0.9880 | 18850 | 0.0 | - |
| 0.9907 | 18900 | 0.0 | - |
| 0.9933 | 18950 | 0.0 | - |
| 0.9959 | 19000 | 0.0 | - |
| 0.9985 | 19050 | 0.0 | - |
| **1.0** | **19078** | **-** | **0.0437** |
| 1.0012 | 19100 | 0.0 | - |
| 1.0038 | 19150 | 0.0 | - |
| 1.0064 | 19200 | 0.0 | - |
| 1.0090 | 19250 | 0.0 | - |
| 1.0116 | 19300 | 0.0 | - |
| 1.0143 | 19350 | 0.0 | - |
| 1.0169 | 19400 | 0.0 | - |
| 1.0195 | 19450 | 0.3698 | - |
| 1.0221 | 19500 | 0.1546 | - |
| 1.0247 | 19550 | 0.0179 | - |
| 1.0274 | 19600 | 0.0004 | - |
| 1.0300 | 19650 | 0.0005 | - |
| 1.0326 | 19700 | 0.0 | - |
| 1.0352 | 19750 | 0.0002 | - |
| 1.0378 | 19800 | 0.0 | - |
| 1.0405 | 19850 | 0.0 | - |
| 1.0431 | 19900 | 0.0 | - |
| 1.0457 | 19950 | 0.0002 | - |
| 1.0483 | 20000 | 0.0011 | - |
| 1.0509 | 20050 | 0.0 | - |
| 1.0536 | 20100 | 0.0 | - |
| 1.0562 | 20150 | 0.0 | - |
| 1.0588 | 20200 | 0.0003 | - |
| 1.0614 | 20250 | 0.0 | - |
| 1.0641 | 20300 | 0.0003 | - |
| 1.0667 | 20350 | 0.0003 | - |
| 1.0693 | 20400 | 0.0 | - |
| 1.0719 | 20450 | 0.0 | - |
| 1.0745 | 20500 | 0.0 | - |
| 1.0772 | 20550 | 0.0 | - |
| 1.0798 | 20600 | 0.0 | - |
| 1.0824 | 20650 | 0.0 | - |
| 1.0850 | 20700 | 0.0 | - |
| 1.0876 | 20750 | 0.0 | - |
| 1.0903 | 20800 | 0.0 | - |
| 1.0929 | 20850 | 0.0 | - |
| 1.0955 | 20900 | 0.0 | - |
| 1.0981 | 20950 | 0.0 | - |
| 1.1007 | 21000 | 0.0 | - |
| 1.1034 | 21050 | 0.0 | - |
| 1.1060 | 21100 | 0.0 | - |
| 1.1086 | 21150 | 0.0 | - |
| 1.1112 | 21200 | 0.0 | - |
| 1.1138 | 21250 | 0.0 | - |
| 1.1165 | 21300 | 0.0 | - |
| 1.1191 | 21350 | 0.0 | - |
| 1.1217 | 21400 | 0.0 | - |
| 1.1243 | 21450 | 0.0 | - |
| 1.1270 | 21500 | 0.0 | - |
| 1.1296 | 21550 | 0.0 | - |
| 1.1322 | 21600 | 0.0 | - |
| 1.1348 | 21650 | 0.0 | - |
| 1.1374 | 21700 | 0.0 | - |
| 1.1401 | 21750 | 0.0 | - |
| 1.1427 | 21800 | 0.0 | - |
| 1.1453 | 21850 | 0.0 | - |
| 1.1479 | 21900 | 0.0 | - |
| 1.1505 | 21950 | 0.0 | - |
| 1.1532 | 22000 | 0.0 | - |
| 1.1558 | 22050 | 0.0 | - |
| 1.1584 | 22100 | 0.0 | - |
| 1.1610 | 22150 | 0.0 | - |
| 1.1636 | 22200 | 0.0 | - |
| 1.1663 | 22250 | 0.0 | - |
| 1.1689 | 22300 | 0.0 | - |
| 1.1715 | 22350 | 0.0 | - |
| 1.1741 | 22400 | 0.0 | - |
| 1.1767 | 22450 | 0.0 | - |
| 1.1794 | 22500 | 0.0 | - |
| 1.1820 | 22550 | 0.0 | - |
| 1.1846 | 22600 | 0.0 | - |
| 1.1872 | 22650 | 0.0 | - |
| 1.1899 | 22700 | 0.0 | - |
| 1.1925 | 22750 | 0.0 | - |
| 1.1951 | 22800 | 0.0 | - |
| 1.1977 | 22850 | 0.0 | - |
| 1.2003 | 22900 | 0.0 | - |
| 1.2030 | 22950 | 0.0 | - |
| 1.2056 | 23000 | 0.0 | - |
| 1.2082 | 23050 | 0.0 | - |
| 1.2108 | 23100 | 0.0 | - |
| 1.2134 | 23150 | 0.0 | - |
| 1.2161 | 23200 | 0.0 | - |
| 1.2187 | 23250 | 0.0 | - |
| 1.2213 | 23300 | 0.0 | - |
| 1.2239 | 23350 | 0.0 | - |
| 1.2265 | 23400 | 0.0 | - |
| 1.2292 | 23450 | 0.0 | - |
| 1.2318 | 23500 | 0.0 | - |
| 1.2344 | 23550 | 0.0 | - |
| 1.2370 | 23600 | 0.0 | - |
| 1.2396 | 23650 | 0.0 | - |
| 1.2423 | 23700 | 0.0 | - |
| 1.2449 | 23750 | 0.0 | - |
| 1.2475 | 23800 | 0.0 | - |
| 1.2501 | 23850 | 0.0 | - |
| 1.2528 | 23900 | 0.0 | - |
| 1.2554 | 23950 | 0.0 | - |
| 1.2580 | 24000 | 0.0 | - |
| 1.2606 | 24050 | 0.0 | - |
| 1.2632 | 24100 | 0.0 | - |
| 1.2659 | 24150 | 0.0 | - |
| 1.2685 | 24200 | 0.0 | - |
| 1.2711 | 24250 | 0.0 | - |
| 1.2737 | 24300 | 0.0 | - |
| 1.2763 | 24350 | 0.0 | - |
| 1.2790 | 24400 | 0.0 | - |
| 1.2816 | 24450 | 0.0 | - |
| 1.2842 | 24500 | 0.0 | - |
| 1.2868 | 24550 | 0.0 | - |
| 1.2894 | 24600 | 0.0 | - |
| 1.2921 | 24650 | 0.0 | - |
| 1.2947 | 24700 | 0.0 | - |
| 1.2973 | 24750 | 0.0 | - |
| 1.2999 | 24800 | 0.0 | - |
| 1.3025 | 24850 | 0.0 | - |
| 1.3052 | 24900 | 0.0 | - |
| 1.3078 | 24950 | 0.0 | - |
| 1.3104 | 25000 | 0.0 | - |
| 1.3130 | 25050 | 0.0 | - |
| 1.3157 | 25100 | 0.0 | - |
| 1.3183 | 25150 | 0.0 | - |
| 1.3209 | 25200 | 0.0 | - |
| 1.3235 | 25250 | 0.0 | - |
| 1.3261 | 25300 | 0.0 | - |
| 1.3288 | 25350 | 0.0 | - |
| 1.3314 | 25400 | 0.0 | - |
| 1.3340 | 25450 | 0.0 | - |
| 1.3366 | 25500 | 0.0 | - |
| 1.3392 | 25550 | 0.0 | - |
| 1.3419 | 25600 | 0.0 | - |
| 1.3445 | 25650 | 0.0 | - |
| 1.3471 | 25700 | 0.0 | - |
| 1.3497 | 25750 | 0.0 | - |
| 1.3523 | 25800 | 0.0 | - |
| 1.3550 | 25850 | 0.0 | - |
| 1.3576 | 25900 | 0.0 | - |
| 1.3602 | 25950 | 0.0 | - |
| 1.3628 | 26000 | 0.0 | - |
| 1.3654 | 26050 | 0.0 | - |
| 1.3681 | 26100 | 0.0 | - |
| 1.3707 | 26150 | 0.0 | - |
| 1.3733 | 26200 | 0.0 | - |
| 1.3759 | 26250 | 0.0 | - |
| 1.3786 | 26300 | 0.0 | - |
| 1.3812 | 26350 | 0.0 | - |
| 1.3838 | 26400 | 0.0 | - |
| 1.3864 | 26450 | 0.0 | - |
| 1.3890 | 26500 | 0.0 | - |
| 1.3917 | 26550 | 0.0 | - |
| 1.3943 | 26600 | 0.0 | - |
| 1.3969 | 26650 | 0.0 | - |
| 1.3995 | 26700 | 0.0 | - |
| 1.4021 | 26750 | 0.0 | - |
| 1.4048 | 26800 | 0.0 | - |
| 1.4074 | 26850 | 0.0 | - |
| 1.4100 | 26900 | 0.0 | - |
| 1.4126 | 26950 | 0.0 | - |
| 1.4152 | 27000 | 0.0 | - |
| 1.4179 | 27050 | 0.0 | - |
| 1.4205 | 27100 | 0.0 | - |
| 1.4231 | 27150 | 0.0 | - |
| 1.4257 | 27200 | 0.0 | - |
| 1.4283 | 27250 | 0.0 | - |
| 1.4310 | 27300 | 0.0 | - |
| 1.4336 | 27350 | 0.0 | - |
| 1.4362 | 27400 | 0.0 | - |
| 1.4388 | 27450 | 0.0 | - |
| 1.4415 | 27500 | 0.0 | - |
| 1.4441 | 27550 | 0.0 | - |
| 1.4467 | 27600 | 0.0 | - |
| 1.4493 | 27650 | 0.0 | - |
| 1.4519 | 27700 | 0.0 | - |
| 1.4546 | 27750 | 0.0 | - |
| 1.4572 | 27800 | 0.0 | - |
| 1.4598 | 27850 | 0.0 | - |
| 1.4624 | 27900 | 0.0 | - |
| 1.4650 | 27950 | 0.0 | - |
| 1.4677 | 28000 | 0.0 | - |
| 1.4703 | 28050 | 0.0 | - |
| 1.4729 | 28100 | 0.0 | - |
| 1.4755 | 28150 | 0.0 | - |
| 1.4781 | 28200 | 0.0 | - |
| 1.4808 | 28250 | 0.0 | - |
| 1.4834 | 28300 | 0.0 | - |
| 1.4860 | 28350 | 0.0 | - |
| 1.4886 | 28400 | 0.0 | - |
| 1.4912 | 28450 | 0.0 | - |
| 1.4939 | 28500 | 0.0 | - |
| 1.4965 | 28550 | 0.0 | - |
| 1.4991 | 28600 | 0.0 | - |
| 1.5017 | 28650 | 0.0 | - |
| 1.5044 | 28700 | 0.0 | - |
| 1.5070 | 28750 | 0.0 | - |
| 1.5096 | 28800 | 0.0 | - |
| 1.5122 | 28850 | 0.0 | - |
| 1.5148 | 28900 | 0.0 | - |
| 1.5175 | 28950 | 0.0 | - |
| 1.5201 | 29000 | 0.0 | - |
| 1.5227 | 29050 | 0.0 | - |
| 1.5253 | 29100 | 0.0 | - |
| 1.5279 | 29150 | 0.0 | - |
| 1.5306 | 29200 | 0.0 | - |
| 1.5332 | 29250 | 0.0 | - |
| 1.5358 | 29300 | 0.0 | - |
| 1.5384 | 29350 | 0.0 | - |
| 1.5410 | 29400 | 0.0 | - |
| 1.5437 | 29450 | 0.0 | - |
| 1.5463 | 29500 | 0.0 | - |
| 1.5489 | 29550 | 0.0 | - |
| 1.5515 | 29600 | 0.0 | - |
| 1.5541 | 29650 | 0.0 | - |
| 1.5568 | 29700 | 0.0 | - |
| 1.5594 | 29750 | 0.0 | - |
| 1.5620 | 29800 | 0.0 | - |
| 1.5646 | 29850 | 0.0 | - |
| 1.5673 | 29900 | 0.0 | - |
| 1.5699 | 29950 | 0.0 | - |
| 1.5725 | 30000 | 0.0 | - |
| 1.5751 | 30050 | 0.0 | - |
| 1.5777 | 30100 | 0.0 | - |
| 1.5804 | 30150 | 0.0 | - |
| 1.5830 | 30200 | 0.0 | - |
| 1.5856 | 30250 | 0.0 | - |
| 1.5882 | 30300 | 0.0 | - |
| 1.5908 | 30350 | 0.0 | - |
| 1.5935 | 30400 | 0.0 | - |
| 1.5961 | 30450 | 0.0 | - |
| 1.5987 | 30500 | 0.0 | - |
| 1.6013 | 30550 | 0.0 | - |
| 1.6039 | 30600 | 0.0 | - |
| 1.6066 | 30650 | 0.0 | - |
| 1.6092 | 30700 | 0.0 | - |
| 1.6118 | 30750 | 0.0 | - |
| 1.6144 | 30800 | 0.0 | - |
| 1.6170 | 30850 | 0.0 | - |
| 1.6197 | 30900 | 0.0 | - |
| 1.6223 | 30950 | 0.0 | - |
| 1.6249 | 31000 | 0.0 | - |
| 1.6275 | 31050 | 0.0 | - |
| 1.6301 | 31100 | 0.0 | - |
| 1.6328 | 31150 | 0.0 | - |
| 1.6354 | 31200 | 0.0 | - |
| 1.6380 | 31250 | 0.0 | - |
| 1.6406 | 31300 | 0.0 | - |
| 1.6433 | 31350 | 0.0 | - |
| 1.6459 | 31400 | 0.0 | - |
| 1.6485 | 31450 | 0.0 | - |
| 1.6511 | 31500 | 0.0 | - |
| 1.6537 | 31550 | 0.0 | - |
| 1.6564 | 31600 | 0.0 | - |
| 1.6590 | 31650 | 0.0 | - |
| 1.6616 | 31700 | 0.0 | - |
| 1.6642 | 31750 | 0.0 | - |
| 1.6668 | 31800 | 0.0 | - |
| 1.6695 | 31850 | 0.0 | - |
| 1.6721 | 31900 | 0.0 | - |
| 1.6747 | 31950 | 0.0 | - |
| 1.6773 | 32000 | 0.0 | - |
| 1.6799 | 32050 | 0.0 | - |
| 1.6826 | 32100 | 0.0 | - |
| 1.6852 | 32150 | 0.0 | - |
| 1.6878 | 32200 | 0.0 | - |
| 1.6904 | 32250 | 0.0 | - |
| 1.6930 | 32300 | 0.0 | - |
| 1.6957 | 32350 | 0.0 | - |
| 1.6983 | 32400 | 0.0 | - |
| 1.7009 | 32450 | 0.0 | - |
| 1.7035 | 32500 | 0.0 | - |
| 1.7062 | 32550 | 0.0 | - |
| 1.7088 | 32600 | 0.0 | - |
| 1.7114 | 32650 | 0.0 | - |
| 1.7140 | 32700 | 0.0 | - |
| 1.7166 | 32750 | 0.0 | - |
| 1.7193 | 32800 | 0.0 | - |
| 1.7219 | 32850 | 0.0 | - |
| 1.7245 | 32900 | 0.0 | - |
| 1.7271 | 32950 | 0.0 | - |
| 1.7297 | 33000 | 0.0 | - |
| 1.7324 | 33050 | 0.0 | - |
| 1.7350 | 33100 | 0.0 | - |
| 1.7376 | 33150 | 0.0 | - |
| 1.7402 | 33200 | 0.0 | - |
| 1.7428 | 33250 | 0.0 | - |
| 1.7455 | 33300 | 0.0 | - |
| 1.7481 | 33350 | 0.0 | - |
| 1.7507 | 33400 | 0.0 | - |
| 1.7533 | 33450 | 0.0 | - |
| 1.7559 | 33500 | 0.0 | - |
| 1.7586 | 33550 | 0.0 | - |
| 1.7612 | 33600 | 0.0 | - |
| 1.7638 | 33650 | 0.0 | - |
| 1.7664 | 33700 | 0.0 | - |
| 1.7691 | 33750 | 0.0 | - |
| 1.7717 | 33800 | 0.0 | - |
| 1.7743 | 33850 | 0.0 | - |
| 1.7769 | 33900 | 0.0 | - |
| 1.7795 | 33950 | 0.0 | - |
| 1.7822 | 34000 | 0.0 | - |
| 1.7848 | 34050 | 0.0 | - |
| 1.7874 | 34100 | 0.0 | - |
| 1.7900 | 34150 | 0.0 | - |
| 1.7926 | 34200 | 0.0 | - |
| 1.7953 | 34250 | 0.0 | - |
| 1.7979 | 34300 | 0.0 | - |
| 1.8005 | 34350 | 0.0 | - |
| 1.8031 | 34400 | 0.0 | - |
| 1.8057 | 34450 | 0.0 | - |
| 1.8084 | 34500 | 0.0 | - |
| 1.8110 | 34550 | 0.0 | - |
| 1.8136 | 34600 | 0.0 | - |
| 1.8162 | 34650 | 0.0 | - |
| 1.8188 | 34700 | 0.0 | - |
| 1.8215 | 34750 | 0.0 | - |
| 1.8241 | 34800 | 0.0 | - |
| 1.8267 | 34850 | 0.0 | - |
| 1.8293 | 34900 | 0.0 | - |
| 1.8320 | 34950 | 0.0 | - |
| 1.8346 | 35000 | 0.0 | - |
| 1.8372 | 35050 | 0.0 | - |
| 1.8398 | 35100 | 0.0 | - |
| 1.8424 | 35150 | 0.0 | - |
| 1.8451 | 35200 | 0.0 | - |
| 1.8477 | 35250 | 0.0 | - |
| 1.8503 | 35300 | 0.0 | - |
| 1.8529 | 35350 | 0.0 | - |
| 1.8555 | 35400 | 0.0 | - |
| 1.8582 | 35450 | 0.0 | - |
| 1.8608 | 35500 | 0.0 | - |
| 1.8634 | 35550 | 0.0 | - |
| 1.8660 | 35600 | 0.0 | - |
| 1.8686 | 35650 | 0.0 | - |
| 1.8713 | 35700 | 0.0 | - |
| 1.8739 | 35750 | 0.0 | - |
| 1.8765 | 35800 | 0.0 | - |
| 1.8791 | 35850 | 0.0 | - |
| 1.8817 | 35900 | 0.0 | - |
| 1.8844 | 35950 | 0.0 | - |
| 1.8870 | 36000 | 0.0 | - |
| 1.8896 | 36050 | 0.0 | - |
| 1.8922 | 36100 | 0.0 | - |
| 1.8949 | 36150 | 0.0 | - |
| 1.8975 | 36200 | 0.0 | - |
| 1.9001 | 36250 | 0.0 | - |
| 1.9027 | 36300 | 0.0 | - |
| 1.9053 | 36350 | 0.0 | - |
| 1.9080 | 36400 | 0.0 | - |
| 1.9106 | 36450 | 0.0 | - |
| 1.9132 | 36500 | 0.0 | - |
| 1.9158 | 36550 | 0.0 | - |
| 1.9184 | 36600 | 0.0 | - |
| 1.9211 | 36650 | 0.0 | - |
| 1.9237 | 36700 | 0.0 | - |
| 1.9263 | 36750 | 0.0 | - |
| 1.9289 | 36800 | 0.0 | - |
| 1.9315 | 36850 | 0.0 | - |
| 1.9342 | 36900 | 0.0 | - |
| 1.9368 | 36950 | 0.0 | - |
| 1.9394 | 37000 | 0.0 | - |
| 1.9420 | 37050 | 0.0 | - |
| 1.9446 | 37100 | 0.0 | - |
| 1.9473 | 37150 | 0.0 | - |
| 1.9499 | 37200 | 0.0 | - |
| 1.9525 | 37250 | 0.0 | - |
| 1.9551 | 37300 | 0.0 | - |
| 1.9578 | 37350 | 0.0 | - |
| 1.9604 | 37400 | 0.0 | - |
| 1.9630 | 37450 | 0.0 | - |
| 1.9656 | 37500 | 0.0 | - |
| 1.9682 | 37550 | 0.0 | - |
| 1.9709 | 37600 | 0.0 | - |
| 1.9735 | 37650 | 0.0 | - |
| 1.9761 | 37700 | 0.0 | - |
| 1.9787 | 37750 | 0.0 | - |
| 1.9813 | 37800 | 0.0 | - |
| 1.9840 | 37850 | 0.0 | - |
| 1.9866 | 37900 | 0.0 | - |
| 1.9892 | 37950 | 0.0 | - |
| 1.9918 | 38000 | 0.0 | - |
| 1.9944 | 38050 | 0.0 | - |
| 1.9971 | 38100 | 0.0 | - |
| 1.9997 | 38150 | 0.0 | - |
| 2.0 | 38156 | - | 0.0438 |
* The bold row denotes the saved checkpoint.
### Framework Versions
- Python: 3.10.12
- SetFit: 1.0.1
- Sentence Transformers: 2.2.2
- Transformers: 4.36.0
- PyTorch: 2.0.0
- Datasets: 2.16.1
- Tokenizers: 0.15.0
## 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.*
-->
|
sidaus/hatespeech-commentnews-large-ind-2
|
sidaus
| 2024-01-10T16:03:56Z | 92 | 0 |
transformers
|
[
"transformers",
"safetensors",
"bert",
"text-classification",
"id",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2024-01-04T15:36:12Z |
---
language:
- id
metrics:
- accuracy
pipeline_tag: text-classification
---
|
mibressler/tumproject
|
mibressler
| 2024-01-10T15:53:37Z | 0 | 0 | null |
[
"tensorboard",
"safetensors",
"autotrain",
"text-generation",
"conversational",
"license:other",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2024-01-10T15:53:32Z |
---
tags:
- autotrain
- text-generation
widget:
- text: "I love AutoTrain because "
license: other
---
# Model Trained Using AutoTrain
This model was trained using AutoTrain. For more information, please visit [AutoTrain](https://hf.co/docs/autotrain).
# Usage
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
model_path = "PATH_TO_THIS_REPO"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(
model_path,
device_map="auto",
torch_dtype='auto'
).eval()
# Prompt content: "hi"
messages = [
{"role": "user", "content": "hi"}
]
input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt')
output_ids = model.generate(input_ids.to('cuda'))
response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True)
# Model response: "Hello! How can I assist you today?"
print(response)
```
|
Abhra-loony/QA_model_with_squad
|
Abhra-loony
| 2024-01-10T15:30:21Z | 49 | 0 |
transformers
|
[
"transformers",
"tf",
"distilbert",
"question-answering",
"generated_from_keras_callback",
"base_model:distilbert/distilbert-base-uncased",
"base_model:finetune:distilbert/distilbert-base-uncased",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
question-answering
| 2024-01-09T06:41:54Z |
---
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_keras_callback
model-index:
- name: Abhra-loony/QA_model_with_squad
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. -->
# Abhra-loony/QA_model_with_squad
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 1.3882
- Validation Loss: 1.6437
- Epoch: 2
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 800, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
- training_precision: float32
### Training results
| Train Loss | Validation Loss | Epoch |
|:----------:|:---------------:|:-----:|
| 2.9201 | 1.9250 | 0 |
| 1.5912 | 1.6437 | 1 |
| 1.3882 | 1.6437 | 2 |
### Framework versions
- Transformers 4.35.2
- TensorFlow 2.15.0
- Datasets 2.16.1
- Tokenizers 0.15.0
|
Chuanming/ChatGLM3-12B-slerp
|
Chuanming
| 2024-01-10T15:24:33Z | 10 | 0 |
transformers
|
[
"transformers",
"safetensors",
"mistral",
"text-generation",
"merge",
"mergekit",
"lazymergekit",
"THUDM/chatglm3-6b-32k",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2024-01-09T16:25:00Z |
---
tags:
- merge
- mergekit
- lazymergekit
- THUDM/chatglm3-6b-32k
- THUDM/chatglm3-6b-32k
---
# ChatGLM3-12B-slerp
ChatGLM3-12B-slerp is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [THUDM/chatglm3-6b-32k](https://huggingface.co/THUDM/chatglm3-6b-32k)
* [THUDM/chatglm3-6b-32k](https://huggingface.co/THUDM/chatglm3-6b-32k)
## 🧩 Configuration
```yaml
slices:
- sources:
- model: THUDM/chatglm3-6b-32k
layer_range: [0, 28]
- model: THUDM/chatglm3-6b-32k
layer_range: [0, 28]
merge_method: slerp
base_model: OpenPipe/mistral-ft-optimized-1218
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: bfloat16
```
## 💻 Usage
```python
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "Chuanming/ChatGLM3-12B-slerp"
messages = [{"role": "user", "content": "What is a large language model?"}]
tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
"text-generation",
model=model,
torch_dtype=torch.float16,
device_map="auto",
)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
```
|
ailoveydovey/ptn
|
ailoveydovey
| 2024-01-10T15:20:30Z | 0 | 0 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2024-01-10T14:33:23Z |
---
license: creativeml-openrail-m
---
|
daochf/Lora-Meta-Llama2-13b-hf-QandA_2g_v01-v06
|
daochf
| 2024-01-10T15:11:50Z | 3 | 0 |
peft
|
[
"peft",
"safetensors",
"arxiv:1910.09700",
"base_model:meta-llama/Llama-2-13b-hf",
"base_model:adapter:meta-llama/Llama-2-13b-hf",
"region:us"
] | null | 2024-01-10T15:11:17Z |
---
library_name: peft
base_model: meta-llama/Llama-2-13b-hf
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: float16
### Framework versions
- PEFT 0.6.2
|
Perselope/Taxi-v39
|
Perselope
| 2024-01-10T15:07:58Z | 0 | 0 | null |
[
"Taxi-v3",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2024-01-10T15:04:39Z |
---
tags:
- Taxi-v3
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: Taxi-v39
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
model = load_from_hub(repo_id="Perselope/Taxi-v39", 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"])
|
vibhuagrawal/Mixtral-8x7B-Instruct-v0.1-GPTQ
|
vibhuagrawal
| 2024-01-10T15:07:53Z | 5 | 0 |
transformers
|
[
"transformers",
"safetensors",
"mixtral",
"text-generation",
"conversational",
"fr",
"it",
"de",
"es",
"en",
"base_model:mistralai/Mixtral-8x7B-Instruct-v0.1",
"base_model:quantized:mistralai/Mixtral-8x7B-Instruct-v0.1",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"4-bit",
"gptq",
"region:us"
] |
text-generation
| 2024-01-10T15:07:52Z |
---
base_model: mistralai/Mixtral-8x7B-Instruct-v0.1
inference: false
language:
- fr
- it
- de
- es
- en
license: apache-2.0
model_creator: Mistral AI_
model_name: Mixtral 8X7B Instruct v0.1
model_type: mixtral
prompt_template: '[INST] {prompt} [/INST]
'
quantized_by: TheBloke
widget:
- output:
text: 'Arr, shiver me timbers! Ye have a llama on yer lawn, ye say? Well, that
be a new one for me! Here''s what I''d suggest, arr:
1. Firstly, ensure yer safety. Llamas may look gentle, but they can be protective
if they feel threatened.
2. Try to make the area less appealing to the llama. Remove any food sources
or water that might be attracting it.
3. Contact local animal control or a wildlife rescue organization. They be the
experts and can provide humane ways to remove the llama from yer property.
4. If ye have any experience with animals, you could try to gently herd the
llama towards a nearby field or open space. But be careful, arr!
Remember, arr, it be important to treat the llama with respect and care. It
be a creature just trying to survive, like the rest of us.'
text: '[INST] You are a pirate chatbot who always responds with Arr and pirate speak!
There''s a llama on my lawn, how can I get rid of him? [/INST]'
---
<!-- markdownlint-disable MD041 -->
<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->
# Mixtral 8X7B Instruct v0.1 - GPTQ
- Model creator: [Mistral AI_](https://huggingface.co/mistralai)
- Original model: [Mixtral 8X7B Instruct v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1)
<!-- description start -->
# Description
This repo contains GPTQ model files for [Mistral AI_'s Mixtral 8X7B Instruct v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1).
Mixtral GPTQs currently require:
* Transformers 4.36.0 or later
* either, AutoGPTQ 0.6 compiled from source, or
* Transformers 4.37.0.dev0 compiled from Github with: `pip3 install git+https://github.com/huggingface/transformers`
Multiple GPTQ parameter permutations are provided; see Provided Files below for details of the options provided, their parameters, and the software used to create them.
<!-- description end -->
<!-- repositories-available start -->
## Repositories available
* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/Mixtral-8x7B-Instruct-v0.1-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Mixtral-8x7B-Instruct-v0.1-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/Mixtral-8x7B-Instruct-v0.1-GGUF)
* [Mistral AI_'s original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: Mistral
```
[INST] {prompt} [/INST]
```
<!-- prompt-template end -->
<!-- README_GPTQ.md-compatible clients start -->
## Known compatible clients / servers
GPTQ models are currently supported on Linux (NVidia/AMD) and Windows (NVidia only). macOS users: please use GGUF models.
Mixtral GPTQs currently have special requirements - see Description above.
<!-- README_GPTQ.md-compatible clients end -->
<!-- README_GPTQ.md-provided-files start -->
## Provided files, and GPTQ parameters
Multiple quantisation parameters are provided, to allow you to choose the best one for your hardware and requirements.
Each separate quant is in a different branch. See below for instructions on fetching from different branches.
Most GPTQ files are made with AutoGPTQ. Mistral models are currently made with Transformers.
<details>
<summary>Explanation of GPTQ parameters</summary>
- Bits: The bit size of the quantised model.
- GS: GPTQ group size. Higher numbers use less VRAM, but have lower quantisation accuracy. "None" is the lowest possible value.
- Act Order: True or False. Also known as `desc_act`. True results in better quantisation accuracy. Some GPTQ clients have had issues with models that use Act Order plus Group Size, but this is generally resolved now.
- Damp %: A GPTQ parameter that affects how samples are processed for quantisation. 0.01 is default, but 0.1 results in slightly better accuracy.
- GPTQ dataset: The calibration dataset used during quantisation. Using a dataset more appropriate to the model's training can improve quantisation accuracy. Note that the GPTQ calibration dataset is not the same as the dataset used to train the model - please refer to the original model repo for details of the training dataset(s).
- Sequence Length: The length of the dataset sequences used for quantisation. Ideally this is the same as the model sequence length. For some very long sequence models (16+K), a lower sequence length may have to be used. Note that a lower sequence length does not limit the sequence length of the quantised model. It only impacts the quantisation accuracy on longer inference sequences.
- ExLlama Compatibility: Whether this file can be loaded with ExLlama, which currently only supports Llama and Mistral models in 4-bit.
</details>
| Branch | Bits | GS | Act Order | Damp % | GPTQ Dataset | Seq Len | Size | ExLlama | Desc |
| ------ | ---- | -- | --------- | ------ | ------------ | ------- | ---- | ------- | ---- |
| [main](https://huggingface.co/TheBloke/Mixtral-8x7B-Instruct-v0.1-GPTQ/tree/main) | 4 | None | Yes | 0.1 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 8192 | 23.81 GB | No | 4-bit, with Act Order. No group size, to lower VRAM requirements. |
| [gptq-4bit-128g-actorder_True](https://huggingface.co/TheBloke/Mixtral-8x7B-Instruct-v0.1-GPTQ/tree/gptq-4bit-128g-actorder_True) | 4 | 128 | Yes | 0.1 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 8192 | 24.70 GB | No | 4-bit, with Act Order and group size 128g. Uses even less VRAM than 64g, but with slightly lower accuracy. |
| [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/Mixtral-8x7B-Instruct-v0.1-GPTQ/tree/gptq-4bit-32g-actorder_True) | 4 | 32 | Yes | 0.1 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 8192 | 27.42 GB | No | 4-bit, with Act Order and group size 32g. Gives highest possible inference quality, with maximum VRAM usage. |
| [gptq-3bit--1g-actorder_True](https://huggingface.co/TheBloke/Mixtral-8x7B-Instruct-v0.1-GPTQ/tree/gptq-3bit--1g-actorder_True) | 3 | None | Yes | 0.1 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 8192 | 18.01 GB | No | 3-bit, with Act Order and no group size. Lowest possible VRAM requirements. May be lower quality than 3-bit 128g. |
| [gptq-3bit-128g-actorder_True](https://huggingface.co/TheBloke/Mixtral-8x7B-Instruct-v0.1-GPTQ/tree/gptq-3bit-128g-actorder_True) | 3 | 128 | Yes | 0.1 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 8192 | 18.85 GB | No | 3-bit, with group size 128g and act-order. Higher quality than 128g-False. |
| [gptq-8bit--1g-actorder_True](https://huggingface.co/TheBloke/Mixtral-8x7B-Instruct-v0.1-GPTQ/tree/gptq-8bit--1g-actorder_True) | 8 | None | Yes | 0.1 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 8192 | 47.04 GB | No | 8-bit, with Act Order. No group size, to lower VRAM requirements. |
| [gptq-8bit-128g-actorder_True](https://huggingface.co/TheBloke/Mixtral-8x7B-Instruct-v0.1-GPTQ/tree/gptq-8bit-128g-actorder_True) | 8 | 128 | Yes | 0.1 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 8192 | 48.10 GB | No | 8-bit, with group size 128g for higher inference quality and with Act Order for even higher accuracy. |
<!-- README_GPTQ.md-provided-files end -->
<!-- README_GPTQ.md-download-from-branches start -->
## How to download, including from branches
### In text-generation-webui
To download from the `main` branch, enter `TheBloke/Mixtral-8x7B-Instruct-v0.1-GPTQ` in the "Download model" box.
To download from another branch, add `:branchname` to the end of the download name, eg `TheBloke/Mixtral-8x7B-Instruct-v0.1-GPTQ:gptq-4bit-128g-actorder_True`
### From the command line
I recommend using the `huggingface-hub` Python library:
```shell
pip3 install huggingface-hub
```
To download the `main` branch to a folder called `Mixtral-8x7B-Instruct-v0.1-GPTQ`:
```shell
mkdir Mixtral-8x7B-Instruct-v0.1-GPTQ
huggingface-cli download TheBloke/Mixtral-8x7B-Instruct-v0.1-GPTQ --local-dir Mixtral-8x7B-Instruct-v0.1-GPTQ --local-dir-use-symlinks False
```
To download from a different branch, add the `--revision` parameter:
```shell
mkdir Mixtral-8x7B-Instruct-v0.1-GPTQ
huggingface-cli download TheBloke/Mixtral-8x7B-Instruct-v0.1-GPTQ --revision gptq-4bit-128g-actorder_True --local-dir Mixtral-8x7B-Instruct-v0.1-GPTQ --local-dir-use-symlinks False
```
<details>
<summary>More advanced huggingface-cli download usage</summary>
If you remove the `--local-dir-use-symlinks False` parameter, the files will instead be stored in the central Hugging Face cache directory (default location on Linux is: `~/.cache/huggingface`), and symlinks will be added to the specified `--local-dir`, pointing to their real location in the cache. This allows for interrupted downloads to be resumed, and allows you to quickly clone the repo to multiple places on disk without triggering a download again. The downside, and the reason why I don't list that as the default option, is that the files are then hidden away in a cache folder and it's harder to know where your disk space is being used, and to clear it up if/when you want to remove a download model.
The cache location can be changed with the `HF_HOME` environment variable, and/or the `--cache-dir` parameter to `huggingface-cli`.
For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
```shell
pip3 install hf_transfer
```
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
```shell
mkdir Mixtral-8x7B-Instruct-v0.1-GPTQ
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/Mixtral-8x7B-Instruct-v0.1-GPTQ --local-dir Mixtral-8x7B-Instruct-v0.1-GPTQ --local-dir-use-symlinks False
```
Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
</details>
### With `git` (**not** recommended)
To clone a specific branch with `git`, use a command like this:
```shell
git clone --single-branch --branch gptq-4bit-128g-actorder_True https://huggingface.co/TheBloke/Mixtral-8x7B-Instruct-v0.1-GPTQ
```
Note that using Git with HF repos is strongly discouraged. It will be much slower than using `huggingface-hub`, and will use twice as much disk space as it has to store the model files twice (it stores every byte both in the intended target folder, and again in the `.git` folder as a blob.)
<!-- README_GPTQ.md-download-from-branches end -->
<!-- README_GPTQ.md-text-generation-webui start -->
## How to easily download and use this model in [text-generation-webui](https://github.com/oobabooga/text-generation-webui)
**NOTE**: Requires:
* Transformers 4.36.0, or Transformers 4.37.0.dev0 from Github
* Either AutoGPTQ 0.6 compiled from source and `Loader: AutoGPTQ`,
* or, `Loader: Transformers`, if you installed Transformers from Github: `pip3 install git+https://github.com/huggingface/transformers`
Please make sure you're using the latest version of [text-generation-webui](https://github.com/oobabooga/text-generation-webui).
It is strongly recommended to use the text-generation-webui one-click-installers unless you're sure you know how to make a manual install.
1. Click the **Model tab**.
2. Under **Download custom model or LoRA**, enter `TheBloke/Mixtral-8x7B-Instruct-v0.1-GPTQ`.
- To download from a specific branch, enter for example `TheBloke/Mixtral-8x7B-Instruct-v0.1-GPTQ:gptq-4bit-128g-actorder_True`
- see Provided Files above for the list of branches for each option.
3. Click **Download**.
4. The model will start downloading. Once it's finished it will say "Done".
5. In the top left, click the refresh icon next to **Model**.
6. In the **Model** dropdown, choose the model you just downloaded: `Mixtral-8x7B-Instruct-v0.1-GPTQ`
7. The model will automatically load, and is now ready for use!
8. If you want any custom settings, set them and then click **Save settings for this model** followed by **Reload the Model** in the top right.
- Note that you do not need to and should not set manual GPTQ parameters any more. These are set automatically from the file `quantize_config.json`.
9. Once you're ready, click the **Text Generation** tab and enter a prompt to get started!
<!-- README_GPTQ.md-text-generation-webui end -->
<!-- README_GPTQ.md-use-from-tgi start -->
## Serving this model from Text Generation Inference (TGI)
Not currently supported for Mixtral models.
<!-- README_GPTQ.md-use-from-tgi end -->
<!-- README_GPTQ.md-use-from-python start -->
## Python code example: inference from this GPTQ model
### Install the necessary packages
Requires: Transformers 4.37.0.dev0 from Github, Optimum 1.16.0 or later, and AutoGPTQ 0.5.1 or later.
```shell
pip3 install --upgrade "git+https://github.com/huggingface/transformers" optimum
# If using PyTorch 2.1 + CUDA 12.x:
pip3 install --upgrade auto-gptq
# or, if using PyTorch 2.1 + CUDA 11.x:
pip3 install --upgrade auto-gptq --extra-index-url https://huggingface.github.io/autogptq-index/whl/cu118/
```
If you are using PyTorch 2.0, you will need to install AutoGPTQ from source. Likewise if you have problems with the pre-built wheels, you should try building from source:
```shell
pip3 uninstall -y auto-gptq
git clone https://github.com/PanQiWei/AutoGPTQ
cd AutoGPTQ
DISABLE_QIGEN=1 pip3 install .
```
### Example Python code
```python
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
model_name_or_path = "TheBloke/Mixtral-8x7B-Instruct-v0.1-GPTQ"
# To use a different branch, change revision
# For example: revision="gptq-4bit-128g-actorder_True"
model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
device_map="auto",
trust_remote_code=False,
revision="main")
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
prompt = "Write a story about llamas"
system_message = "You are a story writing assistant"
prompt_template=f'''[INST] {prompt} [/INST]
'''
print("\n\n*** Generate:")
input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda()
output = model.generate(inputs=input_ids, temperature=0.7, do_sample=True, top_p=0.95, top_k=40, max_new_tokens=512)
print(tokenizer.decode(output[0]))
# Inference can also be done using transformers' pipeline
print("*** Pipeline:")
pipe = pipeline(
"text-generation",
model=model,
tokenizer=tokenizer,
max_new_tokens=512,
do_sample=True,
temperature=0.7,
top_p=0.95,
top_k=40,
repetition_penalty=1.1
)
print(pipe(prompt_template)[0]['generated_text'])
```
<!-- README_GPTQ.md-use-from-python end -->
<!-- README_GPTQ.md-compatibility start -->
## Compatibility
The files provided are tested to work with AutoGPTQ 0.6 (compiled from source) and Transformers 4.37.0 (installed from Github).
<!-- README_GPTQ.md-compatibility end -->
<!-- footer start -->
<!-- 200823 -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute
Thanks to the [chirper.ai](https://chirper.ai) team!
Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Aemon Algiz.
**Patreon special mentions**: Michael Levine, 阿明, Trailburnt, Nikolai Manek, John Detwiler, Randy H, Will Dee, Sebastain Graf, NimbleBox.ai, Eugene Pentland, Emad Mostaque, Ai Maven, Jim Angel, Jeff Scroggin, Michael Davis, Manuel Alberto Morcote, Stephen Murray, Robert, Justin Joy, Luke @flexchar, Brandon Frisco, Elijah Stavena, S_X, Dan Guido, Undi ., Komninos Chatzipapas, Shadi, theTransient, Lone Striker, Raven Klaugh, jjj, Cap'n Zoog, Michel-Marie MAUDET (LINAGORA), Matthew Berman, David, Fen Risland, Omer Bin Jawed, Luke Pendergrass, Kalila, OG, Erik Bjäreholt, Rooh Singh, Joseph William Delisle, Dan Lewis, TL, John Villwock, AzureBlack, Brad, Pedro Madruga, Caitlyn Gatomon, K, jinyuan sun, Mano Prime, Alex, Jeffrey Morgan, Alicia Loh, Illia Dulskyi, Chadd, transmissions 11, fincy, Rainer Wilmers, ReadyPlayerEmma, knownsqashed, Mandus, biorpg, Deo Leter, Brandon Phillips, SuperWojo, Sean Connelly, Iucharbius, Jack West, Harry Royden McLaughlin, Nicholas, terasurfer, Vitor Caleffi, Duane Dunston, Johann-Peter Hartmann, David Ziegler, Olakabola, Ken Nordquist, Trenton Dambrowitz, Tom X Nguyen, Vadim, Ajan Kanaga, Leonard Tan, Clay Pascal, Alexandros Triantafyllidis, JM33133, Xule, vamX, ya boyyy, subjectnull, Talal Aujan, Alps Aficionado, wassieverse, Ari Malik, James Bentley, Woland, Spencer Kim, Michael Dempsey, Fred von Graf, Elle, zynix, William Richards, Stanislav Ovsiannikov, Edmond Seymore, Jonathan Leane, Martin Kemka, usrbinkat, Enrico Ros
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
<!-- footer end -->
# Original model card: Mistral AI_'s Mixtral 8X7B Instruct v0.1
# Model Card for Mixtral-8x7B
The Mixtral-8x7B Large Language Model (LLM) is a pretrained generative Sparse Mixture of Experts. The Mixtral-8x7B outperforms Llama 2 70B on most benchmarks we tested.
For full details of this model please read our [release blog post](https://mistral.ai/news/mixtral-of-experts/).
## Warning
This repo contains weights that are compatible with [vLLM](https://github.com/vllm-project/vllm) serving of the model as well as Hugging Face [transformers](https://github.com/huggingface/transformers) library. It is based on the original Mixtral [torrent release](magnet:?xt=urn:btih:5546272da9065eddeb6fcd7ffddeef5b75be79a7&dn=mixtral-8x7b-32kseqlen&tr=udp%3A%2F%http://2Fopentracker.i2p.rocks%3A6969%2Fannounce&tr=http%3A%2F%http://2Ftracker.openbittorrent.com%3A80%2Fannounce), but the file format and parameter names are different. Please note that model cannot (yet) be instantiated with HF.
## Instruction format
This format must be strictly respected, otherwise the model will generate sub-optimal outputs.
The template used to build a prompt for the Instruct model is defined as follows:
```
<s> [INST] Instruction [/INST] Model answer</s> [INST] Follow-up instruction [/INST]
```
Note that `<s>` and `</s>` are special tokens for beginning of string (BOS) and end of string (EOS) while [INST] and [/INST] are regular strings.
As reference, here is the pseudo-code used to tokenize instructions during fine-tuning:
```python
def tokenize(text):
return tok.encode(text, add_special_tokens=False)
[BOS_ID] +
tokenize("[INST]") + tokenize(USER_MESSAGE_1) + tokenize("[/INST]") +
tokenize(BOT_MESSAGE_1) + [EOS_ID] +
…
tokenize("[INST]") + tokenize(USER_MESSAGE_N) + tokenize("[/INST]") +
tokenize(BOT_MESSAGE_N) + [EOS_ID]
```
In the pseudo-code above, note that the `tokenize` method should not add a BOS or EOS token automatically, but should add a prefix space.
## Run the model
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "mistralai/Mixtral-8x7B-Instruct-v0.1"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)
text = "Hello my name is"
inputs = tokenizer(text, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=20)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```
By default, transformers will load the model in full precision. Therefore you might be interested to further reduce down the memory requirements to run the model through the optimizations we offer in HF ecosystem:
### In half-precision
Note `float16` precision only works on GPU devices
<details>
<summary> Click to expand </summary>
```diff
+ import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "mistralai/Mixtral-8x7B-Instruct-v0.1"
tokenizer = AutoTokenizer.from_pretrained(model_id)
+ model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16).to(0)
text = "Hello my name is"
+ inputs = tokenizer(text, return_tensors="pt").to(0)
outputs = model.generate(**inputs, max_new_tokens=20)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```
</details>
### Lower precision using (8-bit & 4-bit) using `bitsandbytes`
<details>
<summary> Click to expand </summary>
```diff
+ import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "mistralai/Mixtral-8x7B-Instruct-v0.1"
tokenizer = AutoTokenizer.from_pretrained(model_id)
+ model = AutoModelForCausalLM.from_pretrained(model_id, load_in_4bit=True)
text = "Hello my name is"
+ inputs = tokenizer(text, return_tensors="pt").to(0)
outputs = model.generate(**inputs, max_new_tokens=20)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```
</details>
### Load the model with Flash Attention 2
<details>
<summary> Click to expand </summary>
```diff
+ import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "mistralai/Mixtral-8x7B-Instruct-v0.1"
tokenizer = AutoTokenizer.from_pretrained(model_id)
+ model = AutoModelForCausalLM.from_pretrained(model_id, use_flash_attention_2=True)
text = "Hello my name is"
+ inputs = tokenizer(text, return_tensors="pt").to(0)
outputs = model.generate(**inputs, max_new_tokens=20)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```
</details>
## Limitations
The Mixtral-8x7B Instruct model is a quick demonstration that the base model can be easily fine-tuned to achieve compelling performance.
It does not have any moderation mechanisms. We're looking forward to engaging with the community on ways to
make the model finely respect guardrails, allowing for deployment in environments requiring moderated outputs.
# The Mistral AI Team
Albert Jiang, Alexandre Sablayrolles, Arthur Mensch, Blanche Savary, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Emma Bou Hanna, Florian Bressand, Gianna Lengyel, Guillaume Bour, Guillaume Lample, Lélio Renard Lavaud, Louis Ternon, Lucile Saulnier, Marie-Anne Lachaux, Pierre Stock, Teven Le Scao, Théophile Gervet, Thibaut Lavril, Thomas Wang, Timothée Lacroix, William El Sayed.
|
Perselope/Taxi-v40
|
Perselope
| 2024-01-10T15:06:38Z | 0 | 0 | null |
[
"Taxi-v3",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2024-01-10T15:06:36Z |
---
tags:
- Taxi-v3
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: Taxi-v40
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
model = load_from_hub(repo_id="Perselope/Taxi-v40", 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"])
|
Aedelon/dqn-SpaceInvadersNoFrameskip-v4
|
Aedelon
| 2024-01-10T15:01:12Z | 0 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"SpaceInvadersNoFrameskip-v4",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2024-01-10T15:00:38Z |
---
library_name: stable-baselines3
tags:
- SpaceInvadersNoFrameskip-v4
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: DQN
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: SpaceInvadersNoFrameskip-v4
type: SpaceInvadersNoFrameskip-v4
metrics:
- type: mean_reward
value: 793.00 +/- 376.24
name: mean_reward
verified: false
---
# **DQN** Agent playing **SpaceInvadersNoFrameskip-v4**
This is a trained model of a **DQN** agent playing **SpaceInvadersNoFrameskip-v4**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3)
and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo).
The RL Zoo is a training framework for Stable Baselines3
reinforcement learning agents,
with hyperparameter optimization and pre-trained agents included.
## Usage (with SB3 RL Zoo)
RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/>
SB3: https://github.com/DLR-RM/stable-baselines3<br/>
SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib
Install the RL Zoo (with SB3 and SB3-Contrib):
```bash
pip install rl_zoo3
```
```
# Download model and save it into the logs/ folder
python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga Aedelon -f logs/
python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
```
If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do:
```
python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga Aedelon -f logs/
python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
```
## Training (with the RL Zoo)
```
python -m rl_zoo3.train --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
# Upload the model and generate video (when possible)
python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga Aedelon
```
## Hyperparameters
```python
OrderedDict([('batch_size', 32),
('buffer_size', 100000),
('env_wrapper',
['stable_baselines3.common.atari_wrappers.AtariWrapper']),
('exploration_final_eps', 0.01),
('exploration_fraction', 0.1),
('frame_stack', 4),
('gradient_steps', 1),
('learning_rate', 0.0001),
('learning_starts', 100000),
('n_timesteps', 1000000),
('optimize_memory_usage', False),
('policy', 'CnnPolicy'),
('target_update_interval', 1000),
('train_freq', 4),
('normalize', False)])
```
# Environment Arguments
```python
{'render_mode': 'rgb_array'}
```
|
behzadnet/Llama-2-7b-chat-hf-sharded-bf16-fine-tuned-adapters_GrounTruth_all_Seed101
|
behzadnet
| 2024-01-10T14:55:06Z | 0 | 0 |
peft
|
[
"peft",
"arxiv:1910.09700",
"base_model:Trelis/Llama-2-7b-chat-hf-sharded-bf16",
"base_model:adapter:Trelis/Llama-2-7b-chat-hf-sharded-bf16",
"region:us"
] | null | 2024-01-10T01:53:44Z |
---
library_name: peft
base_model: Trelis/Llama-2-7b-chat-hf-sharded-bf16
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Data Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- 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 0.7.0.dev0
## 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 0.7.0.dev0
## 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 0.7.0.dev0
## 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 0.7.0.dev0
|
BanUrsus/distilbert-base-uncased-fillmask-finetuned-imdb-classifier_nlp-course-chapter7-section2
|
BanUrsus
| 2024-01-10T14:51:19Z | 90 | 0 |
transformers
|
[
"transformers",
"safetensors",
"distilbert",
"text-classification",
"generated_from_trainer",
"base_model:BanUrsus/distilbert-base-uncased-finetuned-imdb_nlp-course-chapter7-section2",
"base_model:finetune:BanUrsus/distilbert-base-uncased-finetuned-imdb_nlp-course-chapter7-section2",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2024-01-10T14:37:44Z |
---
license: apache-2.0
base_model: BanUrsus/distilbert-base-uncased-finetuned-imdb_nlp-course-chapter7-section2
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: distilbert-base-uncased-fillmask-finetuned-imdb-classifier_nlp-course-chapter7-section2
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. -->
# distilbert-base-uncased-fillmask-finetuned-imdb-classifier_nlp-course-chapter7-section2
This model is a fine-tuned version of [BanUrsus/distilbert-base-uncased-finetuned-imdb_nlp-course-chapter7-section2](https://huggingface.co/BanUrsus/distilbert-base-uncased-finetuned-imdb_nlp-course-chapter7-section2) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2278
- Accuracy: 0.934
## 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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.3192 | 1.0 | 313 | 0.1938 | 0.932 |
| 0.1801 | 2.0 | 626 | 0.1996 | 0.931 |
| 0.1166 | 3.0 | 939 | 0.2278 | 0.934 |
### Framework versions
- Transformers 4.35.2
- Pytorch 1.11.0+cu102
- Datasets 2.15.0
- Tokenizers 0.15.0
|
RKessler/EVALutionRelationTrain-4
|
RKessler
| 2024-01-10T14:40:42Z | 3 | 0 |
transformers
|
[
"transformers",
"pytorch",
"roberta",
"text-classification",
"generated_from_trainer",
"base_model:FacebookAI/roberta-base",
"base_model:finetune:FacebookAI/roberta-base",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2024-01-10T13:10:07Z |
---
license: mit
base_model: roberta-base
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: EVALutionRelationTrain-4
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. -->
# EVALutionRelationTrain-4
This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6940
- Accuracy: 0.5
- Precision: 0.0
- Recall: 0.0
- F1: 0.0
## 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: 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
- num_epochs: 8
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
| No log | 0.35 | 100 | 0.7110 | 0.5 | 0.0 | 0.0 | 0.0 |
| No log | 0.71 | 200 | 0.7130 | 0.5 | 0.5 | 1.0 | 0.6667 |
| No log | 1.06 | 300 | 0.6943 | 0.5 | 0.0 | 0.0 | 0.0 |
| No log | 1.42 | 400 | 0.6932 | 0.5 | 0.5 | 1.0 | 0.6667 |
| 0.7004 | 1.77 | 500 | 0.6946 | 0.5 | 0.0 | 0.0 | 0.0 |
| 0.7004 | 2.13 | 600 | 0.6999 | 0.5 | 0.0 | 0.0 | 0.0 |
| 0.7004 | 2.48 | 700 | 0.6963 | 0.5 | 0.5 | 1.0 | 0.6667 |
| 0.7004 | 2.84 | 800 | 0.6953 | 0.5 | 0.0 | 0.0 | 0.0 |
| 0.7004 | 3.19 | 900 | 0.6932 | 0.5 | 0.5 | 1.0 | 0.6667 |
| 0.6979 | 3.55 | 1000 | 0.6942 | 0.5 | 0.0 | 0.0 | 0.0 |
| 0.6979 | 3.9 | 1100 | 0.6957 | 0.5 | 0.0 | 0.0 | 0.0 |
| 0.6979 | 4.26 | 1200 | 0.6934 | 0.5 | 0.0 | 0.0 | 0.0 |
| 0.6979 | 4.61 | 1300 | 0.6971 | 0.5 | 0.5 | 1.0 | 0.6667 |
| 0.6979 | 4.96 | 1400 | 0.6940 | 0.5 | 0.0 | 0.0 | 0.0 |
### Framework versions
- Transformers 4.34.0
- Pytorch 2.1.0+cu121
- Datasets 2.14.5
- Tokenizers 0.14.1
|
yaneq/jan_SDXL_LoRA_500_1e4_9d94
|
yaneq
| 2024-01-10T14:38:31Z | 10 | 1 |
diffusers
|
[
"diffusers",
"stable-diffusion-xl",
"stable-diffusion-xl-diffusers",
"text-to-image",
"lora",
"template:sd-lora",
"base_model:stabilityai/stable-diffusion-xl-base-1.0",
"base_model:adapter:stabilityai/stable-diffusion-xl-base-1.0",
"license:openrail++",
"region:us"
] |
text-to-image
| 2024-01-10T14:38:29Z |
---
tags:
- stable-diffusion-xl
- stable-diffusion-xl-diffusers
- text-to-image
- diffusers
- lora
- template:sd-lora
base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt: a photo of Qwerty man
license: openrail++
---
# SDXL LoRA DreamBooth - yaneq/jan_SDXL_LoRA_500_1e4_9d94
<Gallery />
## Model description
These are yaneq/jan_SDXL_LoRA_500_1e4_9d94 LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.
The weights were trained using [DreamBooth](https://dreambooth.github.io/).
LoRA for the text encoder was enabled: False.
Special VAE used for training: madebyollin/sdxl-vae-fp16-fix.
## Trigger words
You should use a photo of Qwerty man to trigger the image generation.
## Download model
Weights for this model are available in Safetensors format.
[Download](yaneq/jan_SDXL_LoRA_500_1e4_9d94/tree/main) them in the Files & versions tab.
|
arks2/234
|
arks2
| 2024-01-10T14:36:59Z | 0 | 0 | null |
[
"license:other",
"region:us"
] | null | 2024-01-10T14:36:59Z |
---
license: other
license_name: '21312'
license_link: LICENSE
---
|
aarongrainer/ppo-SnowballTarget
|
aarongrainer
| 2024-01-10T14:32:01Z | 21 | 0 |
ml-agents
|
[
"ml-agents",
"tensorboard",
"onnx",
"SnowballTarget",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-SnowballTarget",
"region:us"
] |
reinforcement-learning
| 2024-01-10T14:31:57Z |
---
library_name: ml-agents
tags:
- SnowballTarget
- deep-reinforcement-learning
- reinforcement-learning
- ML-Agents-SnowballTarget
---
# **ppo** Agent playing **SnowballTarget**
This is a trained model of a **ppo** agent playing **SnowballTarget**
using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
## Usage (with ML-Agents)
The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
- A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
- A *longer tutorial* to understand how works ML-Agents:
https://huggingface.co/learn/deep-rl-course/unit5/introduction
### Resume the training
```bash
mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
```
### Watch your Agent play
You can watch your agent **playing directly in your browser**
1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
2. Step 1: Find your model_id: aarongrainer/ppo-SnowballTarget
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
ByunByun/qlora-koalpaca-polyglot-12.8b-600step_positive_blog_keywords_fix
|
ByunByun
| 2024-01-10T14:22:22Z | 0 | 0 |
peft
|
[
"peft",
"safetensors",
"arxiv:1910.09700",
"base_model:beomi/polyglot-ko-12.8b-safetensors",
"base_model:adapter:beomi/polyglot-ko-12.8b-safetensors",
"region:us"
] | null | 2024-01-10T14:22:15Z |
---
library_name: peft
base_model: beomi/polyglot-ko-12.8b-safetensors
---
# 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 0.7.2.dev0
|
GedByrne/q-FrozenLake-v1-4x4-noSlippery
|
GedByrne
| 2024-01-10T14:16:44Z | 0 | 0 | null |
[
"FrozenLake-v1-4x4-no_slippery",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2024-01-10T14:16:42Z |
---
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="GedByrne/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"])
```
|
ayousanz/any-ONNX-models
|
ayousanz
| 2024-01-10T14:16:15Z | 0 | 3 | null |
[
"onnx",
"license:apache-2.0",
"region:us"
] | null | 2024-01-04T15:26:42Z |
---
license: apache-2.0
---
LLMの各モデルのONNXに変換したモデル群です
各モデルの使用は、モデルごとのライセンスに基づいて使用してください
以下リポジトリに含まれるモデル一覧です
**その他**
|モデル名|モデルサイズ|量子化モデル|
|---|---|---|
|bert-base-uncased|0.11B|⚪︎|
|llm-jp/llm-jp-1.3b-v1.0|1.3B|⚪︎|
**rinnaモデル**
|モデル名|モデルサイズ|量子化モデル|
|---|---|---|
|rinna/japanese-gpt2-xsmall|0.37B|⚪︎|
|rinna/japanese-gpt-neox-3.6b-instruction-ppo|3.6B|⚪︎|
|rinna/japanese-gpt-neox-3.6b|3.6B|⚪︎|
**cyberagentモデル**
|モデル名|モデルサイズ|量子化モデル|
|---|---|---|
|cyberagent/open-calm-small|0.160B|⚪︎|
|cyberagent/open-calm-medium|0.4B|⚪︎|
|cyberagent/open-calm-large|0.83B|⚪︎|
|cyberagent/open-calm-1b|1B|⚪︎|
|cyberagent/open-calm-3b|3B|⚪︎|
**lineモデル**
|モデル名|モデルサイズ|量子化モデル|
|---|---|---|
|line-corporation/japanese-large-lm-1.7b|1.7B|⚪︎|
|line-corporation/japanese-large-lm-1.7b-instruction-sft|1.7B|⚪︎|
|line-corporation/japanese-large-lm-3.6b|3.6B|⚪︎|
|line-corporation/japanese-large-lm-3.6b-instruction-sft|3.6B|⚪︎|
|
intervitens/Mixtral-8x7B-Instruct-v0.1-LimaRP-ZLoss-DARE-TIES-3.5bpw-h6-exl2-rpcal
|
intervitens
| 2024-01-10T14:13:51Z | 6 | 1 |
transformers
|
[
"transformers",
"mixtral",
"text-generation",
"mergekit",
"merge",
"arxiv:2311.03099",
"arxiv:2306.01708",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2024-01-10T14:07:16Z |
---
base_model: []
tags:
- mergekit
- merge
---
Quantized using 200 samples of 8192 tokens from an RP-oriented [PIPPA](https://huggingface.co/datasets/royallab/PIPPA-cleaned) dataset.
Requires ExllamaV2 version 0.0.11 and up.
Original model link: [Doctor-Shotgun/Mixtral-8x7B-Instruct-v0.1-LimaRP-ZLoss-DARE-TIES](https://huggingface.co/Doctor-Shotgun/Mixtral-8x7B-Instruct-v0.1-LimaRP-ZLoss-DARE-TIES)
Original model README below.
***
# Mixtral-8x7B-Instruct-v0.1-LimaRP-ZLoss-DARE-TIES
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 [DARE](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using ./extra_hdd/Mixtral-8x7B-v0.1 as a base.
### Models Merged
The following models were included in the merge:
* ./extra_hdd2/Mixtral-8x7B-Instruct-v0.1
* ./extra_hdd/Mixtral-8x7B-v0.1-LimaRP-ZLoss
### Configuration
The following YAML configuration was used to produce this model:
```yaml
models:
- model: ./extra_hdd2/Mixtral-8x7B-Instruct-v0.1
parameters:
density: 0.5
weight: 1.0
- model: ./extra_hdd/Mixtral-8x7B-v0.1-LimaRP-ZLoss
parameters:
density: 0.5
weight: 0.5
merge_method: dare_ties
base_model: ./extra_hdd/Mixtral-8x7B-v0.1
parameters:
#normalize: false
#int8_mask: true
dtype: bfloat16
```
|
cyruslau/meinapastel_v6Pastel
|
cyruslau
| 2024-01-10T14:13:46Z | 0 | 0 | null |
[
"region:us"
] | null | 2024-01-10T13:48:45Z |
Clone from https://civitai.com/models/11866/meinapastel
|
gayane/BARTSmiles
|
gayane
| 2024-01-10T14:05:02Z | 212 | 2 |
transformers
|
[
"transformers",
"pytorch",
"bart",
"feature-extraction",
"arxiv:2211.16349",
"endpoints_compatible",
"region:us"
] |
feature-extraction
| 2024-01-04T06:54:55Z |
The repository is adapted based on: https://huggingface.co/chenxran/bart-smiles/tree/main
```python
from transformers import AutoTokenizer, AutoModel, SequenceFeatureExtractor
import torch
from transformers import AutoTokenizer, AutoModel
smiles = "CCC(=O)"
tokenizer = AutoTokenizer.from_pretrained("./BARTSmiles/", add_prefix_space=True)
inputs = tokenizer(smiles, return_tensors="pt", return_token_type_ids=False, add_special_tokens=True)
model = AutoModel.from_pretrained('./BARTSmiles')
model.eval()
# Use a pipeline as a high-level helper
from transformers import pipeline
extractor = pipeline("feature-extraction", model=model, tokenizer=tokenizer)
result = extractor(smiles, return_tensors=True, tokenize_kwargs={'return_token_type_ids':False})
```
## Citation
@article{chilingaryan2022bartsmiles,
title={Bartsmiles: Generative masked language models for molecular representations},
author={Chilingaryan, Gayane and Tamoyan, Hovhannes and Tevosyan, Ani and Babayan, Nelly and Khondkaryan, Lusine and Hambardzumyan, Karen and Navoyan, Zaven and Khachatrian, Hrant and Aghajanyan, Armen},
journal={arXiv preprint arXiv:2211.16349},
year={2022}
}
|
miguelvela/Taxi-unit2
|
miguelvela
| 2024-01-10T13:53:18Z | 0 | 0 | null |
[
"Taxi-v3",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2024-01-10T13:22:59Z |
---
tags:
- Taxi-v3
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: Taxi-unit2
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="miguelvela/Taxi-unit2", 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"])
```
|
rolo9/roberta-base-bne-finetuned-squad-es
|
rolo9
| 2024-01-10T13:49:39Z | 20 | 0 |
transformers
|
[
"transformers",
"tensorboard",
"safetensors",
"roberta",
"question-answering",
"generated_from_trainer",
"dataset:squad_es",
"base_model:PlanTL-GOB-ES/roberta-base-bne",
"base_model:finetune:PlanTL-GOB-ES/roberta-base-bne",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
question-answering
| 2024-01-02T15:23:03Z |
---
license: apache-2.0
base_model: PlanTL-GOB-ES/roberta-base-bne
tags:
- generated_from_trainer
datasets:
- squad_es
model-index:
- name: roberta-base-bne-finetuned-squad-es
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# roberta-base-bne-finetuned-squad-es
This model is a fine-tuned version of [PlanTL-GOB-ES/roberta-base-bne](https://huggingface.co/PlanTL-GOB-ES/roberta-base-bne) on the squad_es 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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
### Framework versions
- Transformers 4.36.2
- Pytorch 2.1.2+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0
|
ByunByun/qlora-koalpaca-polyglot-12.8b-150step_positive_blog_keywords_fix
|
ByunByun
| 2024-01-10T13:37:42Z | 3 | 0 |
peft
|
[
"peft",
"safetensors",
"arxiv:1910.09700",
"base_model:beomi/polyglot-ko-12.8b-safetensors",
"base_model:adapter:beomi/polyglot-ko-12.8b-safetensors",
"region:us"
] | null | 2024-01-10T13:37:33Z |
---
library_name: peft
base_model: beomi/polyglot-ko-12.8b-safetensors
---
# 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 0.7.2.dev0
|
moulichand/Personalised
|
moulichand
| 2024-01-10T13:31:58Z | 1 | 0 |
diffusers
|
[
"diffusers",
"text-to-image",
"autotrain",
"base_model:runwayml/stable-diffusion-v1-5",
"base_model:finetune:runwayml/stable-diffusion-v1-5",
"region:us"
] |
text-to-image
| 2024-01-10T12:59:47Z |
---
base_model: runwayml/stable-diffusion-v1-5
instance_prompt: "Photo of Moulichandbm, a young man with black hair, wearing an orange T-shirt"
tags:
- text-to-image
- diffusers
- autotrain
inference: true
---
# DreamBooth trained by AutoTrain
Text encoder was trained.
|
FungSung/distilBert_sentiment_test_2023DEC
|
FungSung
| 2024-01-10T13:27:34Z | 95 | 0 |
transformers
|
[
"transformers",
"tensorboard",
"safetensors",
"distilbert",
"text-classification",
"generated_from_trainer",
"base_model:lxyuan/distilbert-base-multilingual-cased-sentiments-student",
"base_model:finetune:lxyuan/distilbert-base-multilingual-cased-sentiments-student",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2024-01-10T13:12:22Z |
---
license: apache-2.0
base_model: lxyuan/distilbert-base-multilingual-cased-sentiments-student
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: distilBert_sentiment_test_2023DEC
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. -->
# distilBert_sentiment_test_2023DEC
This model is a fine-tuned version of [lxyuan/distilbert-base-multilingual-cased-sentiments-student](https://huggingface.co/lxyuan/distilbert-base-multilingual-cased-sentiments-student) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.8211
- Y True: [1 2 0 ... 0 2 2]
- Y Pred: [1 2 0 ... 0 2 2]
- Accuracy: 0.7725
- F1: 0.7729
- Precision: 0.7741
- Recall: 0.7725
- Confusion Matrix: [[ 792 191 18]
[ 234 1053 143]
[ 38 180 885]]
## 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
- lr_scheduler_warmup_steps: 50
- num_epochs: 5
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- Transformers 4.36.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0
|
uttam333/layoutlmv3-custom_no_text
|
uttam333
| 2024-01-10T13:26:50Z | 7 | 0 |
transformers
|
[
"transformers",
"tensorboard",
"safetensors",
"layoutlmv3",
"token-classification",
"generated_from_trainer",
"base_model:microsoft/layoutlm-base-uncased",
"base_model:finetune:microsoft/layoutlm-base-uncased",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
token-classification
| 2024-01-10T12:56:26Z |
---
license: mit
base_model: microsoft/layoutlm-base-uncased
tags:
- generated_from_trainer
model-index:
- name: layoutlmv3-custom_no_text
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. -->
# layoutlmv3-custom_no_text
This model is a fine-tuned version of [microsoft/layoutlm-base-uncased](https://huggingface.co/microsoft/layoutlm-base-uncased) on the None dataset.
It achieves the following results on the evaluation set:
- eval_loss: 0.2406
- eval_noise: {'precision': 0.772093023255814, 'recall': 0.8019323671497585, 'f1': 0.7867298578199052, 'number': 621}
- eval_signal: {'precision': 0.7472868217054264, 'recall': 0.77491961414791, 'f1': 0.7608524072612471, 'number': 622}
- eval_overall_precision: 0.7597
- eval_overall_recall: 0.7884
- eval_overall_f1: 0.7738
- eval_overall_accuracy: 0.9518
- eval_runtime: 1.0449
- eval_samples_per_second: 34.452
- eval_steps_per_second: 4.785
- epoch: 19.0
- step: 342
## 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: 3e-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: 50
- mixed_precision_training: Native AMP
### Framework versions
- Transformers 4.36.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0
|
Aedelon/ppo-LunarLander-v2
|
Aedelon
| 2024-01-10T13:25:35Z | 0 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2024-01-08T19:22:27Z |
---
library_name: stable-baselines3
tags:
- LunarLander-v2
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: PPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: LunarLander-v2
type: LunarLander-v2
metrics:
- type: mean_reward
value: 261.04 +/- 17.28
name: mean_reward
verified: false
---
# **PPO** Agent playing **LunarLander-v2**
This is a trained model of a **PPO** agent playing **LunarLander-v2**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
## Usage (with Stable-baselines3)
TODO: Add your code
```python
from stable_baselines3 import ...
from huggingface_sb3 import load_from_hub
...
```
|
ByunByun/qlora-koalpaca-polyglot-12.8b-150step_positive_blog_keywords
|
ByunByun
| 2024-01-10T13:15:33Z | 0 | 0 |
peft
|
[
"peft",
"safetensors",
"arxiv:1910.09700",
"base_model:beomi/polyglot-ko-12.8b-safetensors",
"base_model:adapter:beomi/polyglot-ko-12.8b-safetensors",
"region:us"
] | null | 2024-01-10T13:15:26Z |
---
library_name: peft
base_model: beomi/polyglot-ko-12.8b-safetensors
---
# 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 0.7.2.dev0
|
CarlosFMarques/sdxl-kream-model-lora-spotify
|
CarlosFMarques
| 2024-01-10T13:14:56Z | 1 | 1 |
diffusers
|
[
"diffusers",
"stable-diffusion-xl",
"stable-diffusion-xl-diffusers",
"text-to-image",
"lora",
"base_model:stabilityai/stable-diffusion-xl-base-1.0",
"base_model:adapter:stabilityai/stable-diffusion-xl-base-1.0",
"license:creativeml-openrail-m",
"region:us"
] |
text-to-image
| 2024-01-09T15:24:24Z |
---
license: creativeml-openrail-m
base_model: stabilityai/stable-diffusion-xl-base-1.0
dataset: CarlosFMarques/spotify
tags:
- stable-diffusion-xl
- stable-diffusion-xl-diffusers
- text-to-image
- diffusers
- lora
inference: true
---
# LoRA text2image fine-tuning - CarlosFMarques/sdxl-kream-model-lora-spotify
These are LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0. The weights were fine-tuned on the CarlosFMarques/spotify dataset. You can find some example images in the following.
LoRA for the text encoder was enabled: False.
Special VAE used for training: madebyollin/sdxl-vae-fp16-fix.
|
LarryAIDraw/jeanne-000008
|
LarryAIDraw
| 2024-01-10T13:04:16Z | 0 | 0 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2024-01-10T13:02:13Z |
---
license: creativeml-openrail-m
---
https://civitai.com/models/258851/jeanne-darc-formaldress
|
avivnat13/distilbert-base-uncased-finetuned-intent
|
avivnat13
| 2024-01-10T12:58:23Z | 91 | 0 |
transformers
|
[
"transformers",
"tensorboard",
"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
| 2024-01-08T16:53:46Z |
---
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: distilbert-base-uncased-finetuned-intent
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. -->
# distilbert-base-uncased-finetuned-intent
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: 0.0049
- Accuracy: 1.0
- F1: 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: 2e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| 0.2983 | 1.0 | 178 | 0.0111 | 0.9993 | 0.9993 |
| 0.0085 | 2.0 | 356 | 0.0049 | 1.0 | 1.0 |
### Framework versions
- Transformers 4.36.2
- Pytorch 2.1.2+cpu
- Datasets 2.16.1
- Tokenizers 0.15.0
|
LarryAIDraw/raiden_origin-10
|
LarryAIDraw
| 2024-01-10T12:55:19Z | 0 | 0 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2024-01-10T12:41:34Z |
---
license: creativeml-openrail-m
---
https://civitai.com/models/258299?modelVersionId=291251
|
LarryAIDraw/Stelle-10_IAWolf
|
LarryAIDraw
| 2024-01-10T12:54:03Z | 0 | 0 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2024-01-10T12:40:15Z |
---
license: creativeml-openrail-m
---
https://civitai.com/models/259625/stelle-honkai-star-rail
|
FungSung/distilBert_sentiment_test_23DEC
|
FungSung
| 2024-01-10T12:52:41Z | 96 | 0 |
transformers
|
[
"transformers",
"tensorboard",
"safetensors",
"distilbert",
"text-classification",
"generated_from_trainer",
"base_model:lxyuan/distilbert-base-multilingual-cased-sentiments-student",
"base_model:finetune:lxyuan/distilbert-base-multilingual-cased-sentiments-student",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2024-01-08T10:55:02Z |
---
license: apache-2.0
base_model: lxyuan/distilbert-base-multilingual-cased-sentiments-student
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: distilBert_sentiment_test_23DEC
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. -->
# distilBert_sentiment_test_23DEC
This model is a fine-tuned version of [lxyuan/distilbert-base-multilingual-cased-sentiments-student](https://huggingface.co/lxyuan/distilbert-base-multilingual-cased-sentiments-student) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.4967
- Y True: [1 2 0 ... 0 2 2]
- Y Pred: [1 2 0 ... 0 2 2]
- Accuracy: 0.7583
- F1: 0.7588
- Precision: 0.7601
- Recall: 0.7583
- Confusion Matrix: [[0 0 0]
[0 0 0]
[0 0 0]]
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 50
- num_epochs: 5
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- Transformers 4.36.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0
|
LarryAIDraw/main_lora_yurucamp_inuyama_aoi_v3_pagedAdamW8bit_d64a32_NP5-000010
|
LarryAIDraw
| 2024-01-10T12:51:29Z | 0 | 0 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2024-01-10T12:35:05Z |
---
license: creativeml-openrail-m
---
https://civitai.com/models/7033/yurucampinuyamaaoi
|
LarryAIDraw/BTW_NoelNiihashi-DEF
|
LarryAIDraw
| 2024-01-10T12:50:17Z | 0 | 0 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2024-01-10T12:34:42Z |
---
license: creativeml-openrail-m
---
https://civitai.com/models/260008/noel-niihashi-burn-the-witch
|
Mdebart/mistral-7b-qlora-mental-health
|
Mdebart
| 2024-01-10T12:43:23Z | 0 | 0 |
peft
|
[
"peft",
"safetensors",
"region:us"
] | null | 2024-01-10T12:40:58Z |
---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: bfloat16
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: bfloat16
### Framework versions
- PEFT 0.4.0
- PEFT 0.4.0
|
xiawei910/ppo-Pyramids
|
xiawei910
| 2024-01-10T12:42:40Z | 4 | 0 |
ml-agents
|
[
"ml-agents",
"tensorboard",
"onnx",
"Pyramids",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-Pyramids",
"region:us"
] |
reinforcement-learning
| 2024-01-10T12:42:37Z |
---
library_name: ml-agents
tags:
- Pyramids
- deep-reinforcement-learning
- reinforcement-learning
- ML-Agents-Pyramids
---
# **ppo** Agent playing **Pyramids**
This is a trained model of a **ppo** agent playing **Pyramids**
using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
## Usage (with ML-Agents)
The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
- A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
- A *longer tutorial* to understand how works ML-Agents:
https://huggingface.co/learn/deep-rl-course/unit5/introduction
### Resume the training
```bash
mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
```
### Watch your Agent play
You can watch your agent **playing directly in your browser**
1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
2. Step 1: Find your model_id: xiawei910/ppo-Pyramids
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
Akhi1esh/chat-support-bot-faq
|
Akhi1esh
| 2024-01-10T12:34:19Z | 4 | 0 |
peft
|
[
"peft",
"safetensors",
"arxiv:1910.09700",
"base_model:tiiuae/falcon-7b",
"base_model:adapter:tiiuae/falcon-7b",
"region:us"
] | null | 2024-01-10T12:34:13Z |
---
library_name: peft
base_model: tiiuae/falcon-7b
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **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 0.7.2.dev0
|
damerajee/tinyllama-sft-small-v2
|
damerajee
| 2024-01-10T12:18:12Z | 86 | 0 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"Instruct",
"TinyLlama",
"en",
"dataset:yahma/alpaca-cleaned",
"base_model:unsloth/tinyllama-bnb-4bit",
"base_model:finetune:unsloth/tinyllama-bnb-4bit",
"license:mit",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2024-01-10T10:09:54Z |
---
library_name: transformers
base_model: unsloth/tinyllama-bnb-4bit
license: mit
datasets:
- yahma/alpaca-cleaned
language:
- en
pipeline_tag: text-generation
tags:
- Instruct
- TinyLlama
---
# Steps to try the model:
### prompt Template
```python
alpaca_prompt = """Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.
### Instruction:
{}
### Input:
{}
### Response:
{}"""
```
### load the model
```python
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("damerajee/tinyllama-sft-small-v2")
model = AutoModelForCausalLM.from_pretrained("damerajee/tinyllama-sft-small-v2")
```
### Inference
```python
inputs = tokenizer(
[
alpaca_prompt.format(
"best places to visit in india", # instruction
"", # input
"", # output
)
]*1, return_tensors = "pt")
outputs = model.generate(**inputs, max_new_tokens = 128, use_cache = True)
tokenizer.batch_decode(outputs)
```
# Model Information
The base model [unsloth/tinyllama-bnb-4bit](https://huggingface.co/unsloth/tinyllama-bnb-4bit) was Instruct finetuned using [Unsloth](https://github.com/unslothai/unsloth)
# Model Limitations
The model was trained on a very small dataset so it might not be as good ,will be training on larger dataset soon
# Training Details
The model was trained for 1 epoch on a free goggle colab which took about 1 hour and 30 mins approximately
|
aydippy/dippy
|
aydippy
| 2024-01-10T12:17:29Z | 54 | 0 |
transformers
|
[
"transformers",
"tf",
"distilbert",
"text-classification",
"generated_from_keras_callback",
"base_model:distilbert/distilbert-base-uncased-finetuned-sst-2-english",
"base_model:finetune:distilbert/distilbert-base-uncased-finetuned-sst-2-english",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2024-01-09T06:17:35Z |
---
license: apache-2.0
base_model: distilbert-base-uncased-finetuned-sst-2-english
tags:
- generated_from_keras_callback
model-index:
- name: dippy
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. -->
# dippy
This model is a fine-tuned version of [distilbert-base-uncased-finetuned-sst-2-english](https://huggingface.co/distilbert-base-uncased-finetuned-sst-2-english) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 0.0530
- Train Accuracy: 0.9818
- Validation Loss: 0.3083
- Validation Accuracy: 0.8876
- 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': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5e-05, 'decay_steps': 16838, 'end_learning_rate': 0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
- training_precision: float32
### Training results
| Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
|:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
| 0.1150 | 0.9609 | 0.3167 | 0.8888 | 0 |
| 0.0530 | 0.9818 | 0.3083 | 0.8876 | 1 |
### Framework versions
- Transformers 4.35.2
- TensorFlow 2.15.0
- Tokenizers 0.15.0
|
mtc/mistralai-Mistral-7B-v0.1-arxiv-summarization-5000-no_quantization-lora-full
|
mtc
| 2024-01-10T12:10:30Z | 0 | 0 |
peft
|
[
"peft",
"safetensors",
"arxiv:1910.09700",
"base_model:mistralai/Mistral-7B-v0.1",
"base_model:adapter:mistralai/Mistral-7B-v0.1",
"region:us"
] | null | 2024-01-10T12:09:34Z |
---
library_name: peft
base_model: mistralai/Mistral-7B-v0.1
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **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 0.7.1
|
adihere/zephyr-support-chatbot
|
adihere
| 2024-01-10T12:09:35Z | 0 | 0 | null |
[
"tensorboard",
"safetensors",
"trl",
"sft",
"generated_from_trainer",
"base_model:TheBloke/zephyr-7B-alpha-GPTQ",
"base_model:finetune:TheBloke/zephyr-7B-alpha-GPTQ",
"license:mit",
"region:us"
] | null | 2024-01-10T11:32:03Z |
---
license: mit
base_model: TheBloke/zephyr-7B-alpha-GPTQ
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: zephyr-support-chatbot
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. -->
# zephyr-support-chatbot
This model is a fine-tuned version of [TheBloke/zephyr-7B-alpha-GPTQ](https://huggingface.co/TheBloke/zephyr-7B-alpha-GPTQ) on the None dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- training_steps: 250
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0
|
Aedelon/q-Taxi-v3-2
|
Aedelon
| 2024-01-10T12:04:09Z | 0 | 0 | null |
[
"Taxi-v3",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2024-01-10T12:04:07Z |
---
tags:
- Taxi-v3
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: q-Taxi-v3-2
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Taxi-v3
type: Taxi-v3
metrics:
- type: mean_reward
value: 7.56 +/- 2.71
name: mean_reward
verified: false
---
# **Q-Learning** Agent playing1 **Taxi-v3**
This is a trained model of a **Q-Learning** agent playing **Taxi-v3** .
## Usage
```python
model = load_from_hub(repo_id="Aedelon/q-Taxi-v3-2", filename="q-learning.pkl")
# Don't forget to check if you need to add additional attributes (is_slippery=False etc)
env = gym.make(model["env_id"])
```
|
modamsko/lora-sdxl-flatillustration
|
modamsko
| 2024-01-10T12:03:24Z | 3 | 2 |
diffusers
|
[
"diffusers",
"stable-diffusion-xl",
"stable-diffusion-xl-diffusers",
"text-to-image",
"lora",
"template:sd-lora",
"base_model:stabilityai/stable-diffusion-xl-base-1.0",
"base_model:adapter:stabilityai/stable-diffusion-xl-base-1.0",
"license:openrail++",
"region:us"
] |
text-to-image
| 2024-01-04T12:37:04Z |
---
tags:
- stable-diffusion-xl
- stable-diffusion-xl-diffusers
- text-to-image
- diffusers
- lora
- template:sd-lora
widget:
- text: 'a man in szn style'
output:
url:
"image_0.png"
- text: 'a man in szn style'
output:
url:
"image_1.png"
- text: 'a man in szn style'
output:
url:
"image_2.png"
- text: 'a man in szn style'
output:
url:
"image_3.png"
base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt: a cat in szn style
license: openrail++
---
# SDXL LoRA DreamBooth - modamsko/lora-sdxl-flatillustration
<Gallery />
## Model description
These are modamsko/lora-sdxl-flatillustration LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.
The weights were trained using [DreamBooth](https://dreambooth.github.io/).
LoRA for the text encoder was enabled: False.
Special VAE used for training: None.
## Trigger words
You should use a cat in szn style to trigger the image generation.
## Download model
Weights for this model are available in Safetensors format.
[Download](modamsko/lora-sdxl-flatillustration/tree/main) them in the Files & versions tab.
|
xiawei910/ppo-SnowballTarget
|
xiawei910
| 2024-01-10T12:00:56Z | 0 | 0 |
ml-agents
|
[
"ml-agents",
"tensorboard",
"onnx",
"SnowballTarget",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-SnowballTarget",
"region:us"
] |
reinforcement-learning
| 2024-01-10T12:00:52Z |
---
library_name: ml-agents
tags:
- SnowballTarget
- deep-reinforcement-learning
- reinforcement-learning
- ML-Agents-SnowballTarget
---
# **ppo** Agent playing **SnowballTarget**
This is a trained model of a **ppo** agent playing **SnowballTarget**
using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
## Usage (with ML-Agents)
The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
- A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
- A *longer tutorial* to understand how works ML-Agents:
https://huggingface.co/learn/deep-rl-course/unit5/introduction
### Resume the training
```bash
mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
```
### Watch your Agent play
You can watch your agent **playing directly in your browser**
1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
2. Step 1: Find your model_id: xiawei910/ppo-SnowballTarget
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
RKessler/EVALutionRelationTrain-3
|
RKessler
| 2024-01-10T12:00:04Z | 1 | 0 |
transformers
|
[
"transformers",
"pytorch",
"roberta",
"text-classification",
"generated_from_trainer",
"base_model:FacebookAI/roberta-base",
"base_model:finetune:FacebookAI/roberta-base",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2024-01-10T00:00:34Z |
---
license: mit
base_model: roberta-base
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: EVALutionRelationTrain-3
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# EVALutionRelationTrain-3
This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6950
- Accuracy: 0.5
- Precision: 0.5
- Recall: 1.0
- F1: 0.6667
## 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
- num_epochs: 8
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
| No log | 0.35 | 100 | 0.7296 | 0.5 | 0.0 | 0.0 | 0.0 |
| No log | 0.71 | 200 | 0.7154 | 0.5 | 0.5 | 1.0 | 0.6667 |
| No log | 1.06 | 300 | 0.6932 | 0.5 | 0.0 | 0.0 | 0.0 |
| No log | 1.42 | 400 | 0.6934 | 0.5 | 0.0 | 0.0 | 0.0 |
| 0.7016 | 1.77 | 500 | 0.6941 | 0.5 | 0.0 | 0.0 | 0.0 |
| 0.7016 | 2.13 | 600 | 0.6979 | 0.5 | 0.0 | 0.0 | 0.0 |
| 0.7016 | 2.48 | 700 | 0.6950 | 0.5 | 0.5 | 1.0 | 0.6667 |
| 0.7016 | 2.84 | 800 | 0.6961 | 0.5 | 0.0 | 0.0 | 0.0 |
| 0.7016 | 3.19 | 900 | 0.6939 | 0.5 | 0.5 | 1.0 | 0.6667 |
| 0.6977 | 3.55 | 1000 | 0.6960 | 0.5 | 0.0 | 0.0 | 0.0 |
| 0.6977 | 3.9 | 1100 | 0.6974 | 0.5 | 0.0 | 0.0 | 0.0 |
| 0.6977 | 4.26 | 1200 | 0.6939 | 0.5 | 0.0 | 0.0 | 0.0 |
| 0.6977 | 4.61 | 1300 | 0.6950 | 0.5 | 0.5 | 1.0 | 0.6667 |
### Framework versions
- Transformers 4.34.0
- Pytorch 2.1.0+cu121
- Datasets 2.14.5
- Tokenizers 0.14.1
|
kardosdrur/dfm-sentence-encoder-finetune-large-v1
|
kardosdrur
| 2024-01-10T11:52:24Z | 27 | 0 |
sentence-transformers
|
[
"sentence-transformers",
"safetensors",
"bert",
"feature-extraction",
"sentence-similarity",
"transformers",
"autotrain_compatible",
"text-embeddings-inference",
"endpoints_compatible",
"region:us"
] |
sentence-similarity
| 2024-01-08T13:16:59Z |
---
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- transformers
---
# kardosdrur/dfm-sentence-encoder-finetune-large-v1
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('kardosdrur/dfm-sentence-encoder-finetune-large-v1')
embeddings = model.encode(sentences)
print(embeddings)
```
## Usage (HuggingFace Transformers)
Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
```python
from transformers import AutoTokenizer, AutoModel
import torch
#Mean Pooling - Take attention mask into account for correct averaging
def mean_pooling(model_output, attention_mask):
token_embeddings = model_output[0] #First element of model_output contains all token embeddings
input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
# Sentences we want sentence embeddings for
sentences = ['This is an example sentence', 'Each sentence is converted']
# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('kardosdrur/dfm-sentence-encoder-finetune-large-v1')
model = AutoModel.from_pretrained('kardosdrur/dfm-sentence-encoder-finetune-large-v1')
# Tokenize sentences
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
# Compute token embeddings
with torch.no_grad():
model_output = model(**encoded_input)
# Perform pooling. In this case, mean pooling.
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
print("Sentence embeddings:")
print(sentence_embeddings)
```
## Evaluation Results
<!--- Describe how your model was evaluated -->
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=kardosdrur/dfm-sentence-encoder-finetune-large-v1)
## Training
The model was trained with the parameters:
**DataLoader**:
`torch.utils.data.dataloader.DataLoader` of length 236754 with parameters:
```
{'batch_size': 16, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
```
**Loss**:
`sentence_transformers.losses.ContrastiveLoss.ContrastiveLoss` with parameters:
```
{'distance_metric': 'SiameseDistanceMetric.COSINE_DISTANCE', 'margin': 0.5, 'size_average': True}
```
Parameters of the fit()-Method:
```
{
"epochs": 40,
"evaluator": "dfm_sentence_trf.evaluation.task_evaluator.TaskListEvaluator",
"max_grad_norm": 1,
"optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
"optimizer_params": {
"lr": 2e-05
},
"scheduler": "WarmupLinear",
"steps_per_epoch": 5000,
"warmup_steps": 100,
"weight_decay": 0.01
}
```
## Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 256, 'do_lower_case': False}) with Transformer model: BertModel
(1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
)
```
## Citing & Authors
<!--- Describe where people can find more information -->
|
Kooten/Noromaid-13b-v0.3-QUIP-2bit
|
Kooten
| 2024-01-10T11:50:26Z | 63 | 3 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2024-01-10T07:45:31Z |
---
license: cc-by-nc-4.0
---
# Noromaid-13b-v0.3 2bit QUIP#
## Description
QUIP quant of [NeverSleep/Noromaid-13b-v0.3](https://huggingface.co/NeverSleep/Noromaid-13b-v0.3)
I wanted to try quanting in QUIP, it took about 20 hours but it works, its coherent and really tiny
## Other quants:
EXL2: [8bpw](https://huggingface.co/Kooten/Noromaid-13b-v0.3-8bpw-exl2), [6bpw](https://huggingface.co/Kooten/Noromaid-13b-v0.3-6bpw-exl2), [5bpw](https://huggingface.co/Kooten/Noromaid-13b-v0.3-5bpw-exl2), [4bpw](https://huggingface.co/Kooten/Noromaid-13b-v0.3-4bpw-exl2)
## Prompt Format
### Silly Tavern Preset
[Instruct template](https://files.catbox.moe/nzygwn.json)
[Context template](https://files.catbox.moe/l5hguf.json)
### Alpaca:
```
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{prompt}
### Input:
{input}
### Response:
```
## Contact
Kooten on discord
|
cmp-nct/ShareGPT4V-7B-quant-gguf
|
cmp-nct
| 2024-01-10T11:49:33Z | 28 | 4 | null |
[
"gguf",
"license:llama2",
"region:us"
] | null | 2023-12-06T13:40:51Z |
---
license: llama2
---
The original model is here: https://huggingface.co/Lin-Chen/ShareGPT4V-7B
This is the K-type quantized variant (for inference with llama.cpp llava-cli)
In my tests this is currently the best llava based vision model
|
Aedelon/Taxi-v3-1
|
Aedelon
| 2024-01-10T11:45:01Z | 0 | 0 | null |
[
"Taxi-v3",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2024-01-10T11:44:59Z |
---
tags:
- Taxi-v3
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: Taxi-v3-1
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="Aedelon/Taxi-v3-1", 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"])
```
|
changwan/solar-finetuned-dialogstudio
|
changwan
| 2024-01-10T11:34:48Z | 0 | 0 |
peft
|
[
"peft",
"tensorboard",
"safetensors",
"trl",
"sft",
"generated_from_trainer",
"dataset:dialogstudio",
"base_model:LDCC/LDCC-SOLAR-10.7B",
"base_model:adapter:LDCC/LDCC-SOLAR-10.7B",
"license:cc-by-nc-4.0",
"region:us"
] | null | 2024-01-10T09:11:23Z |
---
license: cc-by-nc-4.0
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
datasets:
- dialogstudio
base_model: LDCC/LDCC-SOLAR-10.7B
model-index:
- name: solar-finetuned-dialogstudio
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. -->
# solar-finetuned-dialogstudio
This model is a fine-tuned version of [LDCC/LDCC-SOLAR-10.7B](https://huggingface.co/LDCC/LDCC-SOLAR-10.7B) on the dialogstudio dataset.
It achieves the following results on the evaluation set:
- Loss: 2.4770
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- training_steps: 3
### Training results
### Framework versions
- PEFT 0.7.2.dev0
- Transformers 4.37.0.dev0
- Pytorch 2.1.2+cu118
- Datasets 2.16.1
- Tokenizers 0.15.0
|
jppech/corgy_moi_LoRA
|
jppech
| 2024-01-10T11:32:12Z | 9 | 1 |
diffusers
|
[
"diffusers",
"tensorboard",
"stable-diffusion-xl",
"stable-diffusion-xl-diffusers",
"text-to-image",
"lora",
"template:sd-lora",
"base_model:stabilityai/stable-diffusion-xl-base-1.0",
"base_model:adapter:stabilityai/stable-diffusion-xl-base-1.0",
"license:openrail++",
"region:us"
] |
text-to-image
| 2024-01-10T11:32:10Z |
---
tags:
- stable-diffusion-xl
- stable-diffusion-xl-diffusers
- text-to-image
- diffusers
- lora
- template:sd-lora
base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt: a photo of MOI humain
license: openrail++
---
# SDXL LoRA DreamBooth - jppech/corgy_moi_LoRA
<Gallery />
## Model description
These are jppech/corgy_moi_LoRA LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.
The weights were trained using [DreamBooth](https://dreambooth.github.io/).
LoRA for the text encoder was enabled: False.
Special VAE used for training: madebyollin/sdxl-vae-fp16-fix.
## Trigger words
You should use a photo of MOI humain to trigger the image generation.
## Download model
Weights for this model are available in Safetensors format.
[Download](jppech/corgy_moi_LoRA/tree/main) them in the Files & versions tab.
|
thrunlab/Mistral-7B-v0.1_cola_relu
|
thrunlab
| 2024-01-10T11:29:28Z | 0 | 0 | null |
[
"safetensors",
"generated_from_trainer",
"base_model:mistralai/Mistral-7B-v0.1",
"base_model:finetune:mistralai/Mistral-7B-v0.1",
"license:apache-2.0",
"region:us"
] | null | 2024-01-05T09:49:40Z |
---
license: apache-2.0
base_model: mistralai/Mistral-7B-v0.1
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: Mistral-7B-v0.1_cola_relu
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# Mistral-7B-v0.1_cola_relu
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3969
- Accuracy: 0.8528
## 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: 64
- eval_batch_size: 64
- seed: 2
- distributed_type: multi-GPU
- num_devices: 2
- gradient_accumulation_steps: 2
- total_train_batch_size: 256
- total_eval_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 750
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 3.3308 | 0.33 | 10 | 3.2312 | 0.6721 |
| 1.9948 | 0.66 | 20 | 1.9259 | 0.5628 |
| 1.755 | 0.98 | 30 | 1.6666 | 0.6529 |
| 1.2472 | 1.31 | 40 | 1.3599 | 0.6280 |
| 0.7 | 1.64 | 50 | 1.0398 | 0.6903 |
| 1.0118 | 1.97 | 60 | 0.8845 | 0.6798 |
| 0.7947 | 2.3 | 70 | 0.7958 | 0.7200 |
| 0.8203 | 2.62 | 80 | 0.7160 | 0.7191 |
| 0.8548 | 2.95 | 90 | 0.6607 | 0.7296 |
| 0.5277 | 3.28 | 100 | 0.6292 | 0.7430 |
| 0.7134 | 3.61 | 110 | 0.6562 | 0.7440 |
| 0.7233 | 3.93 | 120 | 0.6248 | 0.7488 |
| 0.5547 | 4.26 | 130 | 0.5399 | 0.7488 |
| 0.5171 | 4.59 | 140 | 0.5230 | 0.7536 |
| 0.492 | 4.92 | 150 | 0.5184 | 0.7632 |
| 0.5003 | 5.25 | 160 | 0.4999 | 0.7728 |
| 0.4884 | 5.57 | 170 | 0.4827 | 0.7814 |
| 0.514 | 5.9 | 180 | 0.5048 | 0.7910 |
| 0.3669 | 6.23 | 190 | 0.4783 | 0.7977 |
| 0.4786 | 6.56 | 200 | 0.4533 | 0.7948 |
| 0.4244 | 6.89 | 210 | 0.4379 | 0.8035 |
| 0.3235 | 7.21 | 220 | 0.4439 | 0.8073 |
| 0.4307 | 7.54 | 230 | 0.4258 | 0.8236 |
| 0.404 | 7.87 | 240 | 0.4184 | 0.8188 |
| 0.3772 | 8.2 | 250 | 0.4089 | 0.8207 |
| 0.3937 | 8.52 | 260 | 0.4595 | 0.8092 |
| 0.3896 | 8.85 | 270 | 0.4148 | 0.8265 |
| 0.3296 | 9.18 | 280 | 0.4130 | 0.8236 |
| 0.328 | 9.51 | 290 | 0.3944 | 0.8389 |
| 0.3383 | 9.84 | 300 | 0.3862 | 0.8322 |
| 0.3146 | 10.16 | 310 | 0.3847 | 0.8418 |
| 0.3069 | 10.49 | 320 | 0.4192 | 0.8245 |
| 0.2732 | 10.82 | 330 | 0.4190 | 0.8313 |
| 0.2819 | 11.15 | 340 | 0.4427 | 0.8188 |
| 0.3738 | 11.48 | 350 | 0.3807 | 0.8408 |
| 0.3004 | 11.8 | 360 | 0.3722 | 0.8437 |
| 0.2894 | 12.13 | 370 | 0.3922 | 0.8341 |
| 0.2747 | 12.46 | 380 | 0.3782 | 0.8370 |
| 0.2812 | 12.79 | 390 | 0.3667 | 0.8514 |
| 0.2369 | 13.11 | 400 | 0.3884 | 0.8408 |
| 0.2931 | 13.44 | 410 | 0.3807 | 0.8456 |
| 0.2702 | 13.77 | 420 | 0.3742 | 0.8399 |
| 0.2821 | 14.1 | 430 | 0.3737 | 0.8485 |
| 0.2358 | 14.43 | 440 | 0.3739 | 0.8456 |
| 0.2326 | 14.75 | 450 | 0.3699 | 0.8514 |
| 0.2475 | 15.08 | 460 | 0.3771 | 0.8466 |
| 0.2402 | 15.41 | 470 | 0.4064 | 0.8351 |
| 0.2435 | 15.74 | 480 | 0.3758 | 0.8456 |
| 0.1896 | 16.07 | 490 | 0.3779 | 0.8456 |
| 0.2228 | 16.39 | 500 | 0.3868 | 0.8456 |
| 0.2149 | 16.72 | 510 | 0.3800 | 0.8485 |
| 0.1781 | 17.05 | 520 | 0.3841 | 0.8514 |
| 0.1729 | 17.38 | 530 | 0.4000 | 0.8476 |
| 0.1897 | 17.7 | 540 | 0.3866 | 0.8456 |
| 0.1537 | 18.03 | 550 | 0.4317 | 0.8370 |
| 0.1478 | 18.36 | 560 | 0.4197 | 0.8466 |
| 0.1686 | 18.69 | 570 | 0.4325 | 0.8418 |
### Framework versions
- Transformers 4.35.2
- Pytorch 2.1.1+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0
|
Shaimae22/bertemotion
|
Shaimae22
| 2024-01-10T11:15:35Z | 93 | 0 |
transformers
|
[
"transformers",
"safetensors",
"bert",
"text-classification",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2024-01-06T16:48:15Z |
classes = ["Neutral", "Happy", "Sad", "Love", "Anger"]
|
metamath/kcbert-large-finetuned-nsmc
|
metamath
| 2024-01-10T11:09:44Z | 92 | 0 |
transformers
|
[
"transformers",
"tensorboard",
"safetensors",
"bert",
"text-classification",
"generated_from_trainer",
"base_model:beomi/kcbert-large",
"base_model:finetune:beomi/kcbert-large",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2024-01-10T09:51:24Z |
---
base_model: beomi/kcbert-large
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: kcbert-large-finetuned-nsmc
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. -->
# kcbert-large-finetuned-nsmc
This model is a fine-tuned version of [beomi/kcbert-large](https://huggingface.co/beomi/kcbert-large) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2576
- Accuracy: 0.9137
- F1: 0.9137
## 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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| 0.267 | 1.0 | 3750 | 0.2231 | 0.9106 | 0.9106 |
| 0.1427 | 2.0 | 7500 | 0.2576 | 0.9137 | 0.9137 |
### Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0
|
Omeer/flan-t5-base-samsum
|
Omeer
| 2024-01-10T11:09:32Z | 90 | 0 |
transformers
|
[
"transformers",
"tensorboard",
"safetensors",
"t5",
"text2text-generation",
"generated_from_trainer",
"base_model:google/flan-t5-base",
"base_model:finetune:google/flan-t5-base",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text2text-generation
| 2024-01-10T11:08:41Z |
---
license: apache-2.0
base_model: google/flan-t5-base
tags:
- generated_from_trainer
model-index:
- name: flan-t5-base-samsum
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# flan-t5-base-samsum
This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) 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: 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
- num_epochs: 1
### Framework versions
- Transformers 4.36.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0
|
TheBloke/openchat-3.5-0106-AWQ
|
TheBloke
| 2024-01-10T11:07:19Z | 84 | 5 |
transformers
|
[
"transformers",
"safetensors",
"mistral",
"text-generation",
"openchat",
"C-RLFT",
"conversational",
"arxiv:2309.11235",
"arxiv:2303.08774",
"base_model:openchat/openchat-3.5-0106",
"base_model:quantized:openchat/openchat-3.5-0106",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"4-bit",
"awq",
"region:us"
] |
text-generation
| 2024-01-10T10:49:16Z |
---
base_model: openchat/openchat-3.5-0106
inference: false
library_name: transformers
license: apache-2.0
model_creator: OpenChat
model_name: Openchat 3.5 0106
model_type: mistral
pipeline_tag: text-generation
prompt_template: 'GPT4 Correct User: {prompt}<|end_of_turn|>GPT4 Correct Assistant:
'
quantized_by: TheBloke
tags:
- openchat
- mistral
- C-RLFT
---
<!-- markdownlint-disable MD041 -->
<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->
# Openchat 3.5 0106 - AWQ
- Model creator: [OpenChat](https://huggingface.co/openchat)
- Original model: [Openchat 3.5 0106](https://huggingface.co/openchat/openchat-3.5-0106)
<!-- description start -->
## Description
This repo contains AWQ model files for [OpenChat's Openchat 3.5 0106](https://huggingface.co/openchat/openchat-3.5-0106).
These files were quantised using hardware kindly provided by [Massed Compute](https://massedcompute.com/).
### About AWQ
AWQ is an efficient, accurate and blazing-fast low-bit weight quantization method, currently supporting 4-bit quantization. Compared to GPTQ, it offers faster Transformers-based inference with equivalent or better quality compared to the most commonly used GPTQ settings.
AWQ models are currently supported on Linux and Windows, with NVidia GPUs only. macOS users: please use GGUF models instead.
It is supported by:
- [Text Generation Webui](https://github.com/oobabooga/text-generation-webui) - using Loader: AutoAWQ
- [vLLM](https://github.com/vllm-project/vllm) - version 0.2.2 or later for support for all model types.
- [Hugging Face Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference)
- [Transformers](https://huggingface.co/docs/transformers) version 4.35.0 and later, from any code or client that supports Transformers
- [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) - for use from Python code
<!-- description end -->
<!-- repositories-available start -->
## Repositories available
* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/openchat-3.5-0106-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/openchat-3.5-0106-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/openchat-3.5-0106-GGUF)
* [OpenChat's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/openchat/openchat-3.5-0106)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: OpenChat-Correct
```
GPT4 Correct User: {prompt}<|end_of_turn|>GPT4 Correct Assistant:
```
<!-- prompt-template end -->
<!-- README_AWQ.md-provided-files start -->
## Provided files, and AWQ parameters
I currently release 128g GEMM models only. The addition of group_size 32 models, and GEMV kernel models, is being actively considered.
Models are released as sharded safetensors files.
| Branch | Bits | GS | AWQ Dataset | Seq Len | Size |
| ------ | ---- | -- | ----------- | ------- | ---- |
| [main](https://huggingface.co/TheBloke/openchat-3.5-0106-AWQ/tree/main) | 4 | 128 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 4096 | 4.15 GB
<!-- README_AWQ.md-provided-files end -->
<!-- README_AWQ.md-text-generation-webui start -->
## How to easily download and use this model in [text-generation-webui](https://github.com/oobabooga/text-generation-webui)
Please make sure you're using the latest version of [text-generation-webui](https://github.com/oobabooga/text-generation-webui).
It is strongly recommended to use the text-generation-webui one-click-installers unless you're sure you know how to make a manual install.
1. Click the **Model tab**.
2. Under **Download custom model or LoRA**, enter `TheBloke/openchat-3.5-0106-AWQ`.
3. Click **Download**.
4. The model will start downloading. Once it's finished it will say "Done".
5. In the top left, click the refresh icon next to **Model**.
6. In the **Model** dropdown, choose the model you just downloaded: `openchat-3.5-0106-AWQ`
7. Select **Loader: AutoAWQ**.
8. Click Load, and the model will load and is now ready for use.
9. If you want any custom settings, set them and then click **Save settings for this model** followed by **Reload the Model** in the top right.
10. Once you're ready, click the **Text Generation** tab and enter a prompt to get started!
<!-- README_AWQ.md-text-generation-webui end -->
<!-- README_AWQ.md-use-from-vllm start -->
## Multi-user inference server: vLLM
Documentation on installing and using vLLM [can be found here](https://vllm.readthedocs.io/en/latest/).
- Please ensure you are using vLLM version 0.2 or later.
- When using vLLM as a server, pass the `--quantization awq` parameter.
For example:
```shell
python3 -m vllm.entrypoints.api_server --model TheBloke/openchat-3.5-0106-AWQ --quantization awq --dtype auto
```
- When using vLLM from Python code, again set `quantization=awq`.
For example:
```python
from vllm import LLM, SamplingParams
prompts = [
"Tell me about AI",
"Write a story about llamas",
"What is 291 - 150?",
"How much wood would a woodchuck chuck if a woodchuck could chuck wood?",
]
prompt_template=f'''GPT4 Correct User: {prompt}<|end_of_turn|>GPT4 Correct Assistant:
'''
prompts = [prompt_template.format(prompt=prompt) for prompt in prompts]
sampling_params = SamplingParams(temperature=0.8, top_p=0.95)
llm = LLM(model="TheBloke/openchat-3.5-0106-AWQ", quantization="awq", dtype="auto")
outputs = llm.generate(prompts, sampling_params)
# Print the outputs.
for output in outputs:
prompt = output.prompt
generated_text = output.outputs[0].text
print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")
```
<!-- README_AWQ.md-use-from-vllm start -->
<!-- README_AWQ.md-use-from-tgi start -->
## Multi-user inference server: Hugging Face Text Generation Inference (TGI)
Use TGI version 1.1.0 or later. The official Docker container is: `ghcr.io/huggingface/text-generation-inference:1.1.0`
Example Docker parameters:
```shell
--model-id TheBloke/openchat-3.5-0106-AWQ --port 3000 --quantize awq --max-input-length 3696 --max-total-tokens 4096 --max-batch-prefill-tokens 4096
```
Example Python code for interfacing with TGI (requires [huggingface-hub](https://github.com/huggingface/huggingface_hub) 0.17.0 or later):
```shell
pip3 install huggingface-hub
```
```python
from huggingface_hub import InferenceClient
endpoint_url = "https://your-endpoint-url-here"
prompt = "Tell me about AI"
prompt_template=f'''GPT4 Correct User: {prompt}<|end_of_turn|>GPT4 Correct Assistant:
'''
client = InferenceClient(endpoint_url)
response = client.text_generation(prompt,
max_new_tokens=128,
do_sample=True,
temperature=0.7,
top_p=0.95,
top_k=40,
repetition_penalty=1.1)
print(f"Model output: ", response)
```
<!-- README_AWQ.md-use-from-tgi end -->
<!-- README_AWQ.md-use-from-python start -->
## Inference from Python code using Transformers
### Install the necessary packages
- Requires: [Transformers](https://huggingface.co/docs/transformers) 4.35.0 or later.
- Requires: [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) 0.1.6 or later.
```shell
pip3 install --upgrade "autoawq>=0.1.6" "transformers>=4.35.0"
```
Note that if you are using PyTorch 2.0.1, the above AutoAWQ command will automatically upgrade you to PyTorch 2.1.0.
If you are using CUDA 11.8 and wish to continue using PyTorch 2.0.1, instead run this command:
```shell
pip3 install https://github.com/casper-hansen/AutoAWQ/releases/download/v0.1.6/autoawq-0.1.6+cu118-cp310-cp310-linux_x86_64.whl
```
If you have problems installing [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) using the pre-built wheels, install it from source instead:
```shell
pip3 uninstall -y autoawq
git clone https://github.com/casper-hansen/AutoAWQ
cd AutoAWQ
pip3 install .
```
### Transformers example code (requires Transformers 4.35.0 and later)
```python
from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
model_name_or_path = "TheBloke/openchat-3.5-0106-AWQ"
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path)
model = AutoModelForCausalLM.from_pretrained(
model_name_or_path,
low_cpu_mem_usage=True,
device_map="cuda:0"
)
# Using the text streamer to stream output one token at a time
streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
prompt = "Tell me about AI"
prompt_template=f'''GPT4 Correct User: {prompt}<|end_of_turn|>GPT4 Correct Assistant:
'''
# Convert prompt to tokens
tokens = tokenizer(
prompt_template,
return_tensors='pt'
).input_ids.cuda()
generation_params = {
"do_sample": True,
"temperature": 0.7,
"top_p": 0.95,
"top_k": 40,
"max_new_tokens": 512,
"repetition_penalty": 1.1
}
# Generate streamed output, visible one token at a time
generation_output = model.generate(
tokens,
streamer=streamer,
**generation_params
)
# Generation without a streamer, which will include the prompt in the output
generation_output = model.generate(
tokens,
**generation_params
)
# Get the tokens from the output, decode them, print them
token_output = generation_output[0]
text_output = tokenizer.decode(token_output)
print("model.generate output: ", text_output)
# Inference is also possible via Transformers' pipeline
from transformers import pipeline
pipe = pipeline(
"text-generation",
model=model,
tokenizer=tokenizer,
**generation_params
)
pipe_output = pipe(prompt_template)[0]['generated_text']
print("pipeline output: ", pipe_output)
```
<!-- README_AWQ.md-use-from-python end -->
<!-- README_AWQ.md-compatibility start -->
## Compatibility
The files provided are tested to work with:
- [text-generation-webui](https://github.com/oobabooga/text-generation-webui) using `Loader: AutoAWQ`.
- [vLLM](https://github.com/vllm-project/vllm) version 0.2.0 and later.
- [Hugging Face Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference) version 1.1.0 and later.
- [Transformers](https://huggingface.co/docs/transformers) version 4.35.0 and later.
- [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) version 0.1.1 and later.
<!-- README_AWQ.md-compatibility end -->
<!-- footer start -->
<!-- 200823 -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute
Thanks to the [chirper.ai](https://chirper.ai) team!
Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Aemon Algiz.
**Patreon special mentions**: Michael Levine, 阿明, Trailburnt, Nikolai Manek, John Detwiler, Randy H, Will Dee, Sebastain Graf, NimbleBox.ai, Eugene Pentland, Emad Mostaque, Ai Maven, Jim Angel, Jeff Scroggin, Michael Davis, Manuel Alberto Morcote, Stephen Murray, Robert, Justin Joy, Luke @flexchar, Brandon Frisco, Elijah Stavena, S_X, Dan Guido, Undi ., Komninos Chatzipapas, Shadi, theTransient, Lone Striker, Raven Klaugh, jjj, Cap'n Zoog, Michel-Marie MAUDET (LINAGORA), Matthew Berman, David, Fen Risland, Omer Bin Jawed, Luke Pendergrass, Kalila, OG, Erik Bjäreholt, Rooh Singh, Joseph William Delisle, Dan Lewis, TL, John Villwock, AzureBlack, Brad, Pedro Madruga, Caitlyn Gatomon, K, jinyuan sun, Mano Prime, Alex, Jeffrey Morgan, Alicia Loh, Illia Dulskyi, Chadd, transmissions 11, fincy, Rainer Wilmers, ReadyPlayerEmma, knownsqashed, Mandus, biorpg, Deo Leter, Brandon Phillips, SuperWojo, Sean Connelly, Iucharbius, Jack West, Harry Royden McLaughlin, Nicholas, terasurfer, Vitor Caleffi, Duane Dunston, Johann-Peter Hartmann, David Ziegler, Olakabola, Ken Nordquist, Trenton Dambrowitz, Tom X Nguyen, Vadim, Ajan Kanaga, Leonard Tan, Clay Pascal, Alexandros Triantafyllidis, JM33133, Xule, vamX, ya boyyy, subjectnull, Talal Aujan, Alps Aficionado, wassieverse, Ari Malik, James Bentley, Woland, Spencer Kim, Michael Dempsey, Fred von Graf, Elle, zynix, William Richards, Stanislav Ovsiannikov, Edmond Seymore, Jonathan Leane, Martin Kemka, usrbinkat, Enrico Ros
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
<!-- footer end -->
# Original model card: OpenChat's Openchat 3.5 0106
<div align="center">
<img src="https://raw.githubusercontent.com/imoneoi/openchat/master/assets/logo_new.png" style="width: 65%">
<h1>Advancing Open-source Language Models with Mixed-Quality Data</h1>
</div>
<p align="center" style="margin-top: 0px;">
<a href="https://openchat.team">
<img src="https://github.com/alpayariyak/openchat/blob/master/assets/logo_nobg.png?raw=true" alt="OpenChat Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 10px; margin-top: 0px; margin-bottom: 0px;"/>
<span class="link-text" style=" margin-right: 5px;">Online Demo</span>
</a> |
<a href="https://github.com/imoneoi/openchat">
<img src="https://github.githubassets.com/assets/GitHub-Mark-ea2971cee799.png" alt="GitHub Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;"/>
<span class="link-text" style=" margin-right: 5px;">GitHub</span>
</a> |
<a href="https://arxiv.org/pdf/2309.11235.pdf">
<img src="https://github.com/alpayariyak/openchat/blob/master/assets/arxiv-logomark-small-square-border.png?raw=true" alt="ArXiv Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;"/>
<span class="link-text" style="margin-right: 5px;">Paper</span>
</a> |
<a href="https://discord.gg/pQjnXvNKHY">
<img src="https://cloud.githubusercontent.com/assets/6291467/26705903/96c2d66e-477c-11e7-9f4e-f3c0efe96c9a.png" alt="Discord Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;"/>
<span class="link-text">Discord</span>
</a>
</p>
<p align="center" style="margin-top: 0px;">
<span class="link-text" style=" margin-right: 0px; font-size: 0.8em">Sponsored by RunPod</span>
<img src="https://styles.redditmedia.com/t5_6075m3/styles/profileIcon_71syco7c5lt81.png?width=256&height=256&frame=1&auto=webp&crop=256:256,smart&s=24bd3c71dc11edc5d4f88d0cbc1da72ed7ae1969" alt="RunPod Logo" style="width:30px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;"/>
</p>
<div style="background-color: white; padding: 0.7em; border-radius: 0.5em; color: black; display: flex; flex-direction: column; justify-content: center; text-align: center; ont-size: 0.5em; border: 0.8em solid #864AF9;">
<a href="https://huggingface.co/openchat/openchat-3.5-0106" style="text-decoration: none; color: black;">
<span style="font-size: 1.7em; font-family: 'Helvetica'; letter-spacing: 0.1em; font-weight: bold; color: black;">OPENCHAT</span><span style="font-size: 1.8em; font-family: 'Helvetica'; color: #3c72db; ">3.5</span>
<span style="font-size: 1.0em; font-family: 'Helvetica'; color: white; background-color: #864AF9; vertical-align: top; border-radius: 6em; padding: 0.066em 0.4em; letter-spacing: 0.1em; font-weight: bold;">0106</span>
<span style="font-size: 0.85em; font-family: 'Helvetica'; color: black;">
<br> 🏆 The Overall Best Performing Open Source 7B Model 🏆
<br> 🤖 Outperforms <span style="font-weight: bold;">ChatGPT</span> (March) and <span style="font-weight: bold;">Grok-1</span> 🤖
<br> 🚀<span style="font-size: 1em; font-family: 'Helvetica'; color: black; font-weight: bold;">15</span>-point improvement in Coding over <span style="font-size: 0.9em;
font-family: 'Helvetica'; color: black; font-weight: bold;">OpenChat-3.5🚀</span>
<br><br><span style="font-size: 1em; font-family: 'Helvetica'; color: #3c72db; font-weight: bold;">New Features</span>
<br> 💡 2 Modes: Coding + Generalist, Mathematical Reasoning 💡
<br> 🧑⚖️ Experimental support for Evaluator and Feedback capabilities 🧑⚖️
</span>
</a>
</div>
<div style="display: flex; justify-content: center; align-items: center">
<img src="https://raw.githubusercontent.com/imoneoi/openchat/master/assets/openchat-bench-0106.png" style="width: 100%; border-radius: 1em">
</div>
<div>
<h3> Table of Contents</h3>
</div>
1. [Usage](#usage)
2. [Benchmarks](#benchmarks)
3. [Limitations](#limitations)
4. [License](#license)
6. [Citation](#citation)
7. [Acknowledgements](#acknowledgements)
<div align="center">
<h2> Usage </h2>
</div>
To use this model, we highly recommend installing the OpenChat package by following the [installation guide](https://github.com/imoneoi/openchat#installation) in our repository and using the OpenChat OpenAI-compatible API server by running the serving command from the table below. The server is optimized for high-throughput deployment using [vLLM](https://github.com/vllm-project/vllm) and can run on a consumer GPU with 24GB RAM. To enable tensor parallelism, append `--tensor-parallel-size N` to the serving command.
Once started, the server listens at `localhost:18888` for requests and is compatible with the [OpenAI ChatCompletion API specifications](https://platform.openai.com/docs/api-reference/chat). Please refer to the example request below for reference. Additionally, you can use the [OpenChat Web UI](https://github.com/imoneoi/openchat#web-ui) for a user-friendly experience.
If you want to deploy the server as an online service, you can use `--api-keys sk-KEY1 sk-KEY2 ...` to specify allowed API keys and `--disable-log-requests --disable-log-stats --log-file openchat.log` for logging only to a file. For security purposes, we recommend using an [HTTPS gateway](https://fastapi.tiangolo.com/es/deployment/concepts/#security-https) in front of the server.
| Model | Size | Context | Weights | Serving |
|-------------------|------|---------|------------------------------------------------------------------|------------------------------------------------------------------------------------------------------------------|
| OpenChat-3.5-0106 | 7B | 8192 | [Huggingface](https://huggingface.co/openchat/openchat-3.5-0106) | `python -m ochat.serving.openai_api_server --model openchat/openchat-3.5-0106 --engine-use-ray --worker-use-ray` |
<details>
<summary>Example request (click to expand)</summary>
💡 **Default Mode (GPT4 Correct)**: Best for coding, chat and general tasks
```bash
curl http://localhost:18888/v1/chat/completions \
-H "Content-Type: application/json" \
-d '{
"model": "openchat_3.5",
"messages": [{"role": "user", "content": "You are a large language model named OpenChat. Write a poem to describe yourself"}]
}'
```
🧮 **Mathematical Reasoning Mode**: Tailored for solving math problems
```bash
curl http://localhost:18888/v1/chat/completions \
-H "Content-Type: application/json" \
-d '{
"model": "openchat_3.5",
"condition": "Math Correct",
"messages": [{"role": "user", "content": "10.3 − 7988.8133 = "}]
}'
```
</details>
### Conversation templates
💡 **Default Mode (GPT4 Correct)**: Best for coding, chat and general tasks
```
GPT4 Correct User: Hello<|end_of_turn|>GPT4 Correct Assistant: Hi<|end_of_turn|>GPT4 Correct User: How are you today?<|end_of_turn|>GPT4 Correct Assistant:
```
🧮 **Mathematical Reasoning Mode**: Tailored for solving math problems
```
Math Correct User: 10.3 − 7988.8133=<|end_of_turn|>Math Correct Assistant:
```
⚠️ **Notice:** Remember to set `<|end_of_turn|>` as end of generation token.
The default (GPT4 Correct) template is also available as the integrated `tokenizer.chat_template`,
which can be used instead of manually specifying the template:
```python
messages = [
{"role": "user", "content": "Hello"},
{"role": "assistant", "content": "Hi"},
{"role": "user", "content": "How are you today?"}
]
tokens = tokenizer.apply_chat_template(messages, add_generation_prompt=True)
assert tokens == [1, 420, 6316, 28781, 3198, 3123, 1247, 28747, 22557, 32000, 420, 6316, 28781, 3198, 3123, 21631, 28747, 15359, 32000, 420, 6316, 28781, 3198, 3123, 1247, 28747, 1602, 460, 368, 3154, 28804, 32000, 420, 6316, 28781, 3198, 3123, 21631, 28747]
```
<div align="center">
<h2> (Experimental) Evaluator / Feedback Capabilities </h2>
</div>
We've included evaluator capabilities in this release to advance open-source models as evaluators. You can use `Default Mode (GPT4 Correct)` with the following prompt (same as [Prometheus](https://huggingface.co/datasets/kaist-ai/Feedback-Collection)) to evaluate a response.
```
###Task Description:
An instruction (might include an Input inside it), a response to evaluate, a reference answer that gets a score of 5, and a score rubric representing a evaluation criteria are given.
1. Write a detailed feedback that assess the quality of the response strictly based on the given score rubric, not evaluating in general.
2. After writing a feedback, write a score that is an integer between 1 and 5. You should refer to the score rubric.
3. The output format should look as follows: "Feedback: (write a feedback for criteria) [RESULT] (an integer number between 1 and 5)"
4. Please do not generate any other opening, closing, and explanations.
###The instruction to evaluate:
{orig_instruction}
###Response to evaluate:
{orig_response}
###Reference Answer (Score 5):
{orig_reference_answer}
###Score Rubrics:
[{orig_criteria}]
Score 1: {orig_score1_description}
Score 2: {orig_score2_description}
Score 3: {orig_score3_description}
Score 4: {orig_score4_description}
Score 5: {orig_score5_description}
###Feedback:
```
<div align="center">
<h2> Benchmarks </h2>
</div>
| Model | # Params | Average | MT-Bench | HumanEval | BBH MC | AGIEval | TruthfulQA | MMLU | GSM8K | BBH CoT |
|-----------------------|----------|----------|----------|-----------|----------|----------|------------|----------|----------|----------|
| **OpenChat-3.5-0106** | **7B** | **64.5** | 7.8 | **71.3** | **51.5** | **49.1** | 61.0 | 65.8 | **77.4** | 62.2 |
| OpenChat-3.5-1210 | **7B** | 63.8 | 7.76 | 68.9 | 49.5 | 48.0 | **61.8** | 65.3 | 77.3 | 61.8 |
| OpenChat-3.5 | **7B** | 61.6 | 7.81 | 55.5 | 47.6 | 47.4 | 59.1 | 64.3 | 77.3 | 63.5 |
| ChatGPT (March)* | ???B | 61.5 | **7.94** | 48.1 | 47.6 | 47.1 | 57.7 | **67.3** | 74.9 | **70.1** |
| | | | | | | | | | | |
| OpenHermes 2.5 | 7B | 59.3 | 7.54 | 48.2 | 49.4 | 46.5 | 57.5 | 63.8 | 73.5 | 59.9 |
| OpenOrca Mistral | 7B | 52.7 | 6.86 | 38.4 | 49.4 | 42.9 | 45.9 | 59.3 | 59.1 | 58.1 |
| Zephyr-β^ | 7B | 34.6 | 7.34 | 22.0 | 40.6 | 39.0 | 40.8 | 39.8 | 5.1 | 16.0 |
| Mistral | 7B | - | 6.84 | 30.5 | 39.0 | 38.0 | - | 60.1 | 52.2 | - |
<details>
<summary>Evaluation Details(click to expand)</summary>
*: ChatGPT (March) results are from [GPT-4 Technical Report](https://arxiv.org/abs/2303.08774), [Chain-of-Thought Hub](https://github.com/FranxYao/chain-of-thought-hub), and our evaluation. Please note that ChatGPT is not a fixed baseline and evolves rapidly over time.
^: Zephyr-β often fails to follow few-shot CoT instructions, likely because it was aligned with only chat data but not trained on few-shot data.
**: Mistral and Open-source SOTA results are taken from reported results in instruction-tuned model papers and official repositories.
All models are evaluated in chat mode (e.g. with the respective conversation template applied). All zero-shot benchmarks follow the same setting as in the AGIEval paper and Orca paper. CoT tasks use the same configuration as Chain-of-Thought Hub, HumanEval is evaluated with EvalPlus, and MT-bench is run using FastChat. To reproduce our results, follow the instructions in [our repository](https://github.com/imoneoi/openchat/#benchmarks).
</details>
<div>
<h3>HumanEval+</h3>
</div>
| Model | Size | HumanEval+ pass@1 |
|-----------------------------|--------|-------------------|
| **OpenChat-3.5-0106** | **7B** | **65.9** |
| ChatGPT (December 12, 2023) | ???B | 64.6 |
| WizardCoder-Python-34B-V1.0 | 34B | 64.6 |
| OpenChat 3.5 1210 | 7B | 63.4 |
| OpenHermes 2.5 | 7B | 41.5 |
<div>
<h3>OpenChat-3.5 vs. Grok</h3>
</div>
🔥 OpenChat-3.5-0106 (7B) now outperforms Grok-0 (33B) on **all 4 benchmarks** and Grok-1 (???B) on average and **3/4 benchmarks**.
| | License | # Param | Average | MMLU | HumanEval | MATH | GSM8k |
|-----------------------|-------------|---------|----------|--------|-----------|----------|----------|
| **OpenChat-3.5-0106** | Apache-2.0 | **7B** | **61.0** | 65.8 | **71.3** | **29.3** | **77.4** |
| OpenChat-3.5-1210 | Apache-2.0 | **7B** | 60.1 | 65.3 | 68.9 | 28.9 | 77.3 |
| OpenChat-3.5 | Apache-2.0 | **7B** | 56.4 | 64.3 | 55.5 | 28.6 | 77.3 |
| Grok-0 | Proprietary | 33B | 44.5 | 65.7 | 39.7 | 15.7 | 56.8 |
| Grok-1 | Proprietary | ???B | 55.8 | **73** | 63.2 | 23.9 | 62.9 |
*: Grok results are reported by [X.AI](https://x.ai/).
<div align="center">
<h2> Limitations </h2>
</div>
**Foundation Model Limitations**
Despite its advanced capabilities, OpenChat is still bound by the limitations inherent in its foundation models. These limitations may impact the model's performance in areas such as:
- Complex reasoning
- Mathematical and arithmetic tasks
- Programming and coding challenges
**Hallucination of Non-existent Information**
OpenChat may sometimes generate information that does not exist or is not accurate, also known as "hallucination". Users should be aware of this possibility and verify any critical information obtained from the model.
**Safety**
OpenChat may sometimes generate harmful, hate speech, biased responses, or answer unsafe questions. It's crucial to apply additional AI safety measures in use cases that require safe and moderated responses.
<div align="center">
<h2> License </h2>
</div>
Our OpenChat 3.5 code and models are distributed under the Apache License 2.0.
<div align="center">
<h2> Citation </h2>
</div>
```
@article{wang2023openchat,
title={OpenChat: Advancing Open-source Language Models with Mixed-Quality Data},
author={Wang, Guan and Cheng, Sijie and Zhan, Xianyuan and Li, Xiangang and Song, Sen and Liu, Yang},
journal={arXiv preprint arXiv:2309.11235},
year={2023}
}
```
<div align="center">
<h2> 💌 Main Contributor </h2>
</div>
* Wang Guan [imonenext@gmail.com], Cheng Sijie [csj23@mails.tsinghua.edu.cn], Alpay Ariyak [aariyak@wpi.edu]
* We look forward to hearing you and collaborating on this exciting project!
|
orion-penner/setfit-all-MiniLM-L6-v2-sst2-32-shot-public
|
orion-penner
| 2024-01-10T10:59:45Z | 52 | 0 |
setfit
|
[
"setfit",
"safetensors",
"bert",
"sentence-transformers",
"text-classification",
"generated_from_setfit_trainer",
"arxiv:2209.11055",
"region:us"
] |
text-classification
| 2024-01-10T10:59:40Z |
---
library_name: setfit
tags:
- setfit
- sentence-transformers
- text-classification
- generated_from_setfit_trainer
metrics:
- accuracy
widget: []
pipeline_tag: text-classification
inference: true
---
# SetFit
This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. 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:** [Unknown](https://huggingface.co/unknown) -->
- **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
- **Maximum Sequence Length:** 256 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)
## 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("orion-penner/setfit-all-MiniLM-L6-v2-sst2-32-shot-public")
# Run inference
preds = model("I loved the spiderman movie!")
```
<!--
### 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
### Framework Versions
- Python: 3.10.12
- SetFit: 1.0.1
- Sentence Transformers: 2.2.2
- Transformers: 4.35.2
- PyTorch: 2.1.0+cu121
- Datasets: 2.16.1
- Tokenizers: 0.15.0
## 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.*
-->
|
Luismatoslm/summarization_model_save
|
Luismatoslm
| 2024-01-10T10:54:57Z | 48 | 0 |
transformers
|
[
"transformers",
"tf",
"tensorboard",
"t5",
"text2text-generation",
"generated_from_keras_callback",
"base_model:google-t5/t5-small",
"base_model:finetune:google-t5/t5-small",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text2text-generation
| 2024-01-09T09:56:12Z |
---
license: apache-2.0
base_model: t5-small
tags:
- generated_from_keras_callback
model-index:
- name: Luismatoslm/summarization_model_save
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. -->
# Luismatoslm/summarization_model_save
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 3.6371
- Validation Loss: 2.9379
- Train Rouge1: 0.133
- Train Rouge2: 0.0436
- Train Rougel: 0.112
- Train Rougelsum: 0.1118
- Train Gen Len: 19.0
- Epoch: 0
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- optimizer: {'name': '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 | Train Rouge1 | Train Rouge2 | Train Rougel | Train Rougelsum | Train Gen Len | Epoch |
|:----------:|:---------------:|:------------:|:------------:|:------------:|:---------------:|:-------------:|:-----:|
| 3.6371 | 2.9379 | 0.133 | 0.0436 | 0.112 | 0.1118 | 19.0 | 0 |
### Framework versions
- Transformers 4.36.2
- TensorFlow 2.11.0
- Datasets 2.16.1
- Tokenizers 0.15.0
|
intervitens/Mixtral-8x7B-Instruct-v0.1-LimaRP-ZLoss-DARE-TIES-3.7bpw-h6-exl2-rpcal
|
intervitens
| 2024-01-10T10:48:52Z | 8 | 1 |
transformers
|
[
"transformers",
"mixtral",
"text-generation",
"mergekit",
"merge",
"arxiv:2311.03099",
"arxiv:2306.01708",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2024-01-10T10:42:10Z |
---
base_model: []
tags:
- mergekit
- merge
---
Quantized using 200 samples of 8192 tokens from an RP-oriented [PIPPA](https://huggingface.co/datasets/royallab/PIPPA-cleaned) dataset.
Requires ExllamaV2 version 0.0.11 and up.
Original model link: [Doctor-Shotgun/Mixtral-8x7B-Instruct-v0.1-LimaRP-ZLoss-DARE-TIES](https://huggingface.co/Doctor-Shotgun/Mixtral-8x7B-Instruct-v0.1-LimaRP-ZLoss-DARE-TIES)
Original model README below.
***
# Mixtral-8x7B-Instruct-v0.1-LimaRP-ZLoss-DARE-TIES
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 [DARE](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using ./extra_hdd/Mixtral-8x7B-v0.1 as a base.
### Models Merged
The following models were included in the merge:
* ./extra_hdd2/Mixtral-8x7B-Instruct-v0.1
* ./extra_hdd/Mixtral-8x7B-v0.1-LimaRP-ZLoss
### Configuration
The following YAML configuration was used to produce this model:
```yaml
models:
- model: ./extra_hdd2/Mixtral-8x7B-Instruct-v0.1
parameters:
density: 0.5
weight: 1.0
- model: ./extra_hdd/Mixtral-8x7B-v0.1-LimaRP-ZLoss
parameters:
density: 0.5
weight: 0.5
merge_method: dare_ties
base_model: ./extra_hdd/Mixtral-8x7B-v0.1
parameters:
#normalize: false
#int8_mask: true
dtype: bfloat16
```
|
superlazycoder/distilbert-base-uncased-finetuned-squad
|
superlazycoder
| 2024-01-10T10:44:51Z | 25 | 1 |
transformers
|
[
"transformers",
"tensorboard",
"safetensors",
"distilbert",
"question-answering",
"generated_from_trainer",
"base_model:distilbert/distilbert-base-uncased",
"base_model:finetune:distilbert/distilbert-base-uncased",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
question-answering
| 2024-01-09T23:15:12Z |
---
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
model-index:
- name: distilbert-base-uncased-finetuned-squad
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# distilbert-base-uncased-finetuned-squad
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.1578
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:-----:|:---------------:|
| 1.1947 | 1.0 | 5533 | 1.1466 |
| 0.938 | 2.0 | 11066 | 1.1017 |
| 0.7378 | 3.0 | 16599 | 1.1578 |
### Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0
|
Deojaklah/Memeh
|
Deojaklah
| 2024-01-10T10:32:47Z | 0 | 0 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2024-01-10T10:32:46Z |
---
license: creativeml-openrail-m
---
|
devrishi/roberta-retrained
|
devrishi
| 2024-01-10T10:26:05Z | 1 | 0 |
transformers
|
[
"transformers",
"roberta",
"token-classification",
"en",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
token-classification
| 2024-01-10T08:48:14Z |
---
license: mit
language:
- en
---
|
behzadnet/Llama-2-7b-chat-hf-sharded-bf16-fine-tuned-adapters_GrounTruth_newPrompt_Seed101
|
behzadnet
| 2024-01-10T10:18:50Z | 0 | 0 |
peft
|
[
"peft",
"arxiv:1910.09700",
"base_model:Trelis/Llama-2-7b-chat-hf-sharded-bf16",
"base_model:adapter:Trelis/Llama-2-7b-chat-hf-sharded-bf16",
"region:us"
] | null | 2024-01-10T10:18:45Z |
---
library_name: peft
base_model: Trelis/Llama-2-7b-chat-hf-sharded-bf16
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Data Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- 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 0.7.0.dev0
## 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 0.7.0.dev0
|
Deepakkori45/Aspect_term_1
|
Deepakkori45
| 2024-01-10T10:14:43Z | 0 | 0 |
peft
|
[
"peft",
"safetensors",
"arxiv:1910.09700",
"base_model:mistralai/Mistral-7B-v0.1",
"base_model:adapter:mistralai/Mistral-7B-v0.1",
"region:us"
] | null | 2024-01-10T10:14:38Z |
---
library_name: peft
base_model: mistralai/Mistral-7B-v0.1
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **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 0.7.1
|
reach-vb/mistral-lora-mlx-test
|
reach-vb
| 2024-01-10T10:09:27Z | 6 | 5 |
mlx
|
[
"mlx",
"mistral",
"pretrained",
"text-generation",
"en",
"license:apache-2.0",
"region:us"
] |
text-generation
| 2024-01-10T09:52:46Z |
---
language:
- en
license: apache-2.0
tags:
- pretrained
- mlx
pipeline_tag: text-generation
inference:
parameters:
temperature: 0.7
---
# reach-vb/mistral-lora-mlx-test
This model was converted to MLX format from [`mistralai/Mistral-7B-v0.1`]().
Refer to the [original model card](https://huggingface.co/mistralai/Mistral-7B-v0.1) for more details on the model.
## Use with mlx
```bash
pip install mlx
git clone https://github.com/ml-explore/mlx-examples.git
cd mlx-examples/llms/hf_llm
python generate.py --model reach-vb/mistral-lora-mlx-test --prompt "My name is"
```
|
minhtien2405/t5-large-finetuned-text2code
|
minhtien2405
| 2024-01-10T09:53:49Z | 19 | 0 |
transformers
|
[
"transformers",
"tensorboard",
"safetensors",
"t5",
"text2text-generation",
"generated_from_trainer",
"base_model:google-t5/t5-large",
"base_model:finetune:google-t5/t5-large",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text2text-generation
| 2024-01-10T04:03:08Z |
---
license: apache-2.0
base_model: t5-large
tags:
- generated_from_trainer
model-index:
- name: t5-large-finetuned-text2code
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. -->
# t5-large-finetuned-text2code
This model is a fine-tuned version of [t5-large](https://huggingface.co/t5-large) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2512
## 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: 3e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.2
- num_epochs: 5
### Training results
### Framework versions
- Transformers 4.36.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0
|
haryoaw/scenario-TCR-data-glue-mrpc-model-bert-base-uncased
|
haryoaw
| 2024-01-10T09:49:33Z | 98 | 0 |
transformers
|
[
"transformers",
"safetensors",
"bert",
"text-classification",
"generated_from_trainer",
"base_model:google-bert/bert-base-uncased",
"base_model:finetune:google-bert/bert-base-uncased",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-12-29T20:47:33Z |
---
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: scenario-TCR-data-glue-mrpc-model-bert-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. -->
# scenario-TCR-data-glue-mrpc-model-bert-base-uncased
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.8418
- Accuracy: 0.8431
- F1: 0.8869
## 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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 6969
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| No log | 1.0 | 115 | 0.3798 | 0.8578 | 0.8945 |
| No log | 2.0 | 230 | 0.4539 | 0.8113 | 0.8752 |
| No log | 3.0 | 345 | 0.4868 | 0.8309 | 0.8852 |
| No log | 4.0 | 460 | 0.7806 | 0.8333 | 0.8745 |
| 0.2296 | 5.0 | 575 | 0.6896 | 0.8627 | 0.9028 |
| 0.2296 | 6.0 | 690 | 1.1197 | 0.8235 | 0.8788 |
| 0.2296 | 7.0 | 805 | 0.9408 | 0.8456 | 0.8930 |
| 0.2296 | 8.0 | 920 | 0.9377 | 0.8284 | 0.8805 |
| 0.0295 | 9.0 | 1035 | 1.0580 | 0.8137 | 0.8770 |
| 0.0295 | 10.0 | 1150 | 0.8418 | 0.8431 | 0.8869 |
### Framework versions
- Transformers 4.36.2
- Pytorch 2.1.2
- Datasets 2.16.0
- Tokenizers 0.15.0
|
tarekxpc/xQAstral
|
tarekxpc
| 2024-01-10T09:44:54Z | 5 | 0 |
peft
|
[
"peft",
"tensorboard",
"safetensors",
"trl",
"sft",
"generated_from_trainer",
"base_model:TheBloke/Mistral-7B-Instruct-v0.1-GPTQ",
"base_model:adapter:TheBloke/Mistral-7B-Instruct-v0.1-GPTQ",
"license:apache-2.0",
"region:us"
] | null | 2024-01-10T07:11:55Z |
---
license: apache-2.0
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: TheBloke/Mistral-7B-Instruct-v0.1-GPTQ
model-index:
- name: xQAstral
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. -->
# xQAstral
This model is a fine-tuned version of [TheBloke/Mistral-7B-Instruct-v0.1-GPTQ](https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.1-GPTQ) on the None dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- training_steps: 500
### Training results
### Framework versions
- PEFT 0.7.1
- Transformers 4.37.0.dev0
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0
|
TheBloke/Lumosia-MoE-4x10.7-GPTQ
|
TheBloke
| 2024-01-10T09:44:36Z | 11 | 4 |
transformers
|
[
"transformers",
"safetensors",
"mixtral",
"text-generation",
"moe",
"merge",
"mergekit",
"lazymergekit",
"DopeorNope/SOLARC-M-10.7B",
"maywell/PiVoT-10.7B-Mistral-v0.2-RP",
"kyujinpy/Sakura-SOLAR-Instruct",
"jeonsworld/CarbonVillain-en-10.7B-v1",
"conversational",
"base_model:SteelStorage/Lumosia-MoE-4x10.7",
"base_model:quantized:SteelStorage/Lumosia-MoE-4x10.7",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"4-bit",
"gptq",
"region:us"
] |
text-generation
| 2024-01-10T05:01:14Z |
---
base_model: Steelskull/Lumosia-MoE-4x10.7
inference: false
license: apache-2.0
model_creator: Steel
model_name: Lumosia MoE 4X10.7
model_type: mixtral
prompt_template: '### System:
### USER:{prompt}
### Assistant:
'
quantized_by: TheBloke
tags:
- moe
- merge
- mergekit
- lazymergekit
- DopeorNope/SOLARC-M-10.7B
- maywell/PiVoT-10.7B-Mistral-v0.2-RP
- kyujinpy/Sakura-SOLAR-Instruct
- jeonsworld/CarbonVillain-en-10.7B-v1
---
<!-- markdownlint-disable MD041 -->
<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->
# Lumosia MoE 4X10.7 - GPTQ
- Model creator: [Steel](https://huggingface.co/Steelskull)
- Original model: [Lumosia MoE 4X10.7](https://huggingface.co/Steelskull/Lumosia-MoE-4x10.7)
<!-- description start -->
# Description
This repo contains GPTQ model files for [Steel's Lumosia MoE 4X10.7](https://huggingface.co/Steelskull/Lumosia-MoE-4x10.7).
Multiple GPTQ parameter permutations are provided; see Provided Files below for details of the options provided, their parameters, and the software used to create them.
These files were quantised using hardware kindly provided by [Massed Compute](https://massedcompute.com/).
<!-- description end -->
<!-- repositories-available start -->
## Repositories available
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Lumosia-MoE-4x10.7-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/Lumosia-MoE-4x10.7-GGUF)
* [Steel's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/Steelskull/Lumosia-MoE-4x10.7)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: Lumosia
```
### System:
### USER:{prompt}
### Assistant:
```
<!-- prompt-template end -->
<!-- README_GPTQ.md-compatible clients start -->
## Known compatible clients / servers
GPTQ models are currently supported on Linux (NVidia/AMD) and Windows (NVidia only). macOS users: please use GGUF models.
These GPTQ models are known to work in the following inference servers/webuis.
- [text-generation-webui](https://github.com/oobabooga/text-generation-webui)
- [KoboldAI United](https://github.com/henk717/koboldai)
- [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui)
- [Hugging Face Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference)
This may not be a complete list; if you know of others, please let me know!
<!-- README_GPTQ.md-compatible clients end -->
<!-- README_GPTQ.md-provided-files start -->
## Provided files, and GPTQ parameters
Multiple quantisation parameters are provided, to allow you to choose the best one for your hardware and requirements.
Each separate quant is in a different branch. See below for instructions on fetching from different branches.
Most GPTQ files are made with AutoGPTQ. Mistral models are currently made with Transformers.
<details>
<summary>Explanation of GPTQ parameters</summary>
- Bits: The bit size of the quantised model.
- GS: GPTQ group size. Higher numbers use less VRAM, but have lower quantisation accuracy. "None" is the lowest possible value.
- Act Order: True or False. Also known as `desc_act`. True results in better quantisation accuracy. Some GPTQ clients have had issues with models that use Act Order plus Group Size, but this is generally resolved now.
- Damp %: A GPTQ parameter that affects how samples are processed for quantisation. 0.01 is default, but 0.1 results in slightly better accuracy.
- GPTQ dataset: The calibration dataset used during quantisation. Using a dataset more appropriate to the model's training can improve quantisation accuracy. Note that the GPTQ calibration dataset is not the same as the dataset used to train the model - please refer to the original model repo for details of the training dataset(s).
- Sequence Length: The length of the dataset sequences used for quantisation. Ideally this is the same as the model sequence length. For some very long sequence models (16+K), a lower sequence length may have to be used. Note that a lower sequence length does not limit the sequence length of the quantised model. It only impacts the quantisation accuracy on longer inference sequences.
- ExLlama Compatibility: Whether this file can be loaded with ExLlama, which currently only supports Llama and Mistral models in 4-bit.
</details>
| Branch | Bits | GS | Act Order | Damp % | GPTQ Dataset | Seq Len | Size | ExLlama | Desc |
| ------ | ---- | -- | --------- | ------ | ------------ | ------- | ---- | ------- | ---- |
| [main](https://huggingface.co/TheBloke/Lumosia-MoE-4x10.7-GPTQ/tree/main) | 4 | None | Yes | 0.1 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 4096 | 18.50 GB | No | 4-bit, with Act Order. No group size, to lower VRAM requirements. |
| [gptq-4bit-128g-actorder_True](https://huggingface.co/TheBloke/Lumosia-MoE-4x10.7-GPTQ/tree/gptq-4bit-128g-actorder_True) | 4 | 128 | Yes | 0.1 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 4096 | 19.18 GB | No | 4-bit, with Act Order and group size 128g. Uses even less VRAM than 64g, but with slightly lower accuracy. |
| [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/Lumosia-MoE-4x10.7-GPTQ/tree/gptq-4bit-32g-actorder_True) | 4 | 32 | Yes | 0.1 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 4096 | 21.28 GB | No | 4-bit, with Act Order and group size 32g. Gives highest possible inference quality, with maximum VRAM usage. |
| [gptq-3bit-128g-actorder_True](https://huggingface.co/TheBloke/Lumosia-MoE-4x10.7-GPTQ/tree/gptq-3bit-128g-actorder_True) | 3 | 128 | Yes | 0.1 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 4096 | 14.66 GB | No | 3-bit, with group size 128g and act-order. Higher quality than 128g-False. |
| [gptq-8bit--1g-actorder_True](https://huggingface.co/TheBloke/Lumosia-MoE-4x10.7-GPTQ/tree/gptq-8bit--1g-actorder_True) | 8 | None | Yes | 0.1 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 4096 | 36.42 GB | No | 8-bit, with Act Order. No group size, to lower VRAM requirements. |
| [gptq-3bit-32g-actorder_True](https://huggingface.co/TheBloke/Lumosia-MoE-4x10.7-GPTQ/tree/gptq-3bit-32g-actorder_True) | 3 | 32 | Yes | 0.1 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 4096 | 16.66 GB | No | 3-bit, with group size 64g and act-order. Highest quality 3-bit option. |
| [gptq-8bit-128g-actorder_True](https://huggingface.co/TheBloke/Lumosia-MoE-4x10.7-GPTQ/tree/gptq-8bit-128g-actorder_True) | 8 | 128 | Yes | 0.1 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 4096 | 37.24 GB | No | 8-bit, with group size 128g for higher inference quality and with Act Order for even higher accuracy. |
<!-- README_GPTQ.md-provided-files end -->
<!-- README_GPTQ.md-download-from-branches start -->
## How to download, including from branches
### In text-generation-webui
To download from the `main` branch, enter `TheBloke/Lumosia-MoE-4x10.7-GPTQ` in the "Download model" box.
To download from another branch, add `:branchname` to the end of the download name, eg `TheBloke/Lumosia-MoE-4x10.7-GPTQ:gptq-4bit-128g-actorder_True`
### From the command line
I recommend using the `huggingface-hub` Python library:
```shell
pip3 install huggingface-hub
```
To download the `main` branch to a folder called `Lumosia-MoE-4x10.7-GPTQ`:
```shell
mkdir Lumosia-MoE-4x10.7-GPTQ
huggingface-cli download TheBloke/Lumosia-MoE-4x10.7-GPTQ --local-dir Lumosia-MoE-4x10.7-GPTQ --local-dir-use-symlinks False
```
To download from a different branch, add the `--revision` parameter:
```shell
mkdir Lumosia-MoE-4x10.7-GPTQ
huggingface-cli download TheBloke/Lumosia-MoE-4x10.7-GPTQ --revision gptq-4bit-128g-actorder_True --local-dir Lumosia-MoE-4x10.7-GPTQ --local-dir-use-symlinks False
```
<details>
<summary>More advanced huggingface-cli download usage</summary>
If you remove the `--local-dir-use-symlinks False` parameter, the files will instead be stored in the central Hugging Face cache directory (default location on Linux is: `~/.cache/huggingface`), and symlinks will be added to the specified `--local-dir`, pointing to their real location in the cache. This allows for interrupted downloads to be resumed, and allows you to quickly clone the repo to multiple places on disk without triggering a download again. The downside, and the reason why I don't list that as the default option, is that the files are then hidden away in a cache folder and it's harder to know where your disk space is being used, and to clear it up if/when you want to remove a download model.
The cache location can be changed with the `HF_HOME` environment variable, and/or the `--cache-dir` parameter to `huggingface-cli`.
For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
```shell
pip3 install hf_transfer
```
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
```shell
mkdir Lumosia-MoE-4x10.7-GPTQ
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/Lumosia-MoE-4x10.7-GPTQ --local-dir Lumosia-MoE-4x10.7-GPTQ --local-dir-use-symlinks False
```
Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
</details>
### With `git` (**not** recommended)
To clone a specific branch with `git`, use a command like this:
```shell
git clone --single-branch --branch gptq-4bit-128g-actorder_True https://huggingface.co/TheBloke/Lumosia-MoE-4x10.7-GPTQ
```
Note that using Git with HF repos is strongly discouraged. It will be much slower than using `huggingface-hub`, and will use twice as much disk space as it has to store the model files twice (it stores every byte both in the intended target folder, and again in the `.git` folder as a blob.)
<!-- README_GPTQ.md-download-from-branches end -->
<!-- README_GPTQ.md-text-generation-webui start -->
## How to easily download and use this model in [text-generation-webui](https://github.com/oobabooga/text-generation-webui)
Please make sure you're using the latest version of [text-generation-webui](https://github.com/oobabooga/text-generation-webui).
It is strongly recommended to use the text-generation-webui one-click-installers unless you're sure you know how to make a manual install.
1. Click the **Model tab**.
2. Under **Download custom model or LoRA**, enter `TheBloke/Lumosia-MoE-4x10.7-GPTQ`.
- To download from a specific branch, enter for example `TheBloke/Lumosia-MoE-4x10.7-GPTQ:gptq-4bit-128g-actorder_True`
- see Provided Files above for the list of branches for each option.
3. Click **Download**.
4. The model will start downloading. Once it's finished it will say "Done".
5. In the top left, click the refresh icon next to **Model**.
6. In the **Model** dropdown, choose the model you just downloaded: `Lumosia-MoE-4x10.7-GPTQ`
7. The model will automatically load, and is now ready for use!
8. If you want any custom settings, set them and then click **Save settings for this model** followed by **Reload the Model** in the top right.
- Note that you do not need to and should not set manual GPTQ parameters any more. These are set automatically from the file `quantize_config.json`.
9. Once you're ready, click the **Text Generation** tab and enter a prompt to get started!
<!-- README_GPTQ.md-text-generation-webui end -->
<!-- README_GPTQ.md-use-from-tgi start -->
## Serving this model from Text Generation Inference (TGI)
It's recommended to use TGI version 1.1.0 or later. The official Docker container is: `ghcr.io/huggingface/text-generation-inference:1.1.0`
Example Docker parameters:
```shell
--model-id TheBloke/Lumosia-MoE-4x10.7-GPTQ --port 3000 --quantize gptq --max-input-length 3696 --max-total-tokens 4096 --max-batch-prefill-tokens 4096
```
Example Python code for interfacing with TGI (requires huggingface-hub 0.17.0 or later):
```shell
pip3 install huggingface-hub
```
```python
from huggingface_hub import InferenceClient
endpoint_url = "https://your-endpoint-url-here"
prompt = "Tell me about AI"
prompt_template=f'''### System:
### USER:{prompt}
### Assistant:
'''
client = InferenceClient(endpoint_url)
response = client.text_generation(
prompt_template,
max_new_tokens=128,
do_sample=True,
temperature=0.7,
top_p=0.95,
top_k=40,
repetition_penalty=1.1
)
print(f"Model output: {response}")
```
<!-- README_GPTQ.md-use-from-tgi end -->
<!-- README_GPTQ.md-use-from-python start -->
## Python code example: inference from this GPTQ model
### Install the necessary packages
Requires: Transformers 4.33.0 or later, Optimum 1.12.0 or later, and AutoGPTQ 0.4.2 or later.
```shell
pip3 install --upgrade transformers optimum
# If using PyTorch 2.1 + CUDA 12.x:
pip3 install --upgrade auto-gptq
# or, if using PyTorch 2.1 + CUDA 11.x:
pip3 install --upgrade auto-gptq --extra-index-url https://huggingface.github.io/autogptq-index/whl/cu118/
```
If you are using PyTorch 2.0, you will need to install AutoGPTQ from source. Likewise if you have problems with the pre-built wheels, you should try building from source:
```shell
pip3 uninstall -y auto-gptq
git clone https://github.com/PanQiWei/AutoGPTQ
cd AutoGPTQ
git checkout v0.5.1
pip3 install .
```
### Example Python code
```python
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
model_name_or_path = "TheBloke/Lumosia-MoE-4x10.7-GPTQ"
# To use a different branch, change revision
# For example: revision="gptq-4bit-128g-actorder_True"
model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
device_map="auto",
trust_remote_code=False,
revision="main")
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
prompt = "Write a story about llamas"
system_message = "You are a story writing assistant"
prompt_template=f'''### System:
### USER:{prompt}
### Assistant:
'''
print("\n\n*** Generate:")
input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda()
output = model.generate(inputs=input_ids, temperature=0.7, do_sample=True, top_p=0.95, top_k=40, max_new_tokens=512)
print(tokenizer.decode(output[0]))
# Inference can also be done using transformers' pipeline
print("*** Pipeline:")
pipe = pipeline(
"text-generation",
model=model,
tokenizer=tokenizer,
max_new_tokens=512,
do_sample=True,
temperature=0.7,
top_p=0.95,
top_k=40,
repetition_penalty=1.1
)
print(pipe(prompt_template)[0]['generated_text'])
```
<!-- README_GPTQ.md-use-from-python end -->
<!-- README_GPTQ.md-compatibility start -->
## Compatibility
The files provided are tested to work with Transformers. For non-Mistral models, AutoGPTQ can also be used directly.
[ExLlama](https://github.com/turboderp/exllama) is compatible with Llama architecture models (including Mistral, Yi, DeepSeek, SOLAR, etc) in 4-bit. Please see the Provided Files table above for per-file compatibility.
For a list of clients/servers, please see "Known compatible clients / servers", above.
<!-- README_GPTQ.md-compatibility end -->
<!-- footer start -->
<!-- 200823 -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute
Thanks to the [chirper.ai](https://chirper.ai) team!
Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Aemon Algiz.
**Patreon special mentions**: Michael Levine, 阿明, Trailburnt, Nikolai Manek, John Detwiler, Randy H, Will Dee, Sebastain Graf, NimbleBox.ai, Eugene Pentland, Emad Mostaque, Ai Maven, Jim Angel, Jeff Scroggin, Michael Davis, Manuel Alberto Morcote, Stephen Murray, Robert, Justin Joy, Luke @flexchar, Brandon Frisco, Elijah Stavena, S_X, Dan Guido, Undi ., Komninos Chatzipapas, Shadi, theTransient, Lone Striker, Raven Klaugh, jjj, Cap'n Zoog, Michel-Marie MAUDET (LINAGORA), Matthew Berman, David, Fen Risland, Omer Bin Jawed, Luke Pendergrass, Kalila, OG, Erik Bjäreholt, Rooh Singh, Joseph William Delisle, Dan Lewis, TL, John Villwock, AzureBlack, Brad, Pedro Madruga, Caitlyn Gatomon, K, jinyuan sun, Mano Prime, Alex, Jeffrey Morgan, Alicia Loh, Illia Dulskyi, Chadd, transmissions 11, fincy, Rainer Wilmers, ReadyPlayerEmma, knownsqashed, Mandus, biorpg, Deo Leter, Brandon Phillips, SuperWojo, Sean Connelly, Iucharbius, Jack West, Harry Royden McLaughlin, Nicholas, terasurfer, Vitor Caleffi, Duane Dunston, Johann-Peter Hartmann, David Ziegler, Olakabola, Ken Nordquist, Trenton Dambrowitz, Tom X Nguyen, Vadim, Ajan Kanaga, Leonard Tan, Clay Pascal, Alexandros Triantafyllidis, JM33133, Xule, vamX, ya boyyy, subjectnull, Talal Aujan, Alps Aficionado, wassieverse, Ari Malik, James Bentley, Woland, Spencer Kim, Michael Dempsey, Fred von Graf, Elle, zynix, William Richards, Stanislav Ovsiannikov, Edmond Seymore, Jonathan Leane, Martin Kemka, usrbinkat, Enrico Ros
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
<!-- footer end -->
# Original model card: Steel's Lumosia MoE 4X10.7
# Lumosia-MoE-4x10.7
"Lumosia" was selected as its a MoE of Multiple SOLAR Merges so it really "Lights the way".... its 3am.
This is a very experimantal model. its a MoE of all good performing Solar models (based off of personal experiance not open leaderboard),
Why? Dunno whated to see what would happen
context is maybe 16k?
Chat-instruct breaks the model at the moment, not really sure why, even tho it will follow instructions.
Waiting on fix for quants of FrankenMoE
Template:
```
### System:
### USER:{prompt}
### Assistant:
```
Settings:
```
Temp: 1.0
min-p: 0.02-0.1
```
Lumosia-MoE-4x10.7 is a Mixure of Experts (MoE) made with the following models:
* [DopeorNope/SOLARC-M-10.7B](https://huggingface.co/DopeorNope/SOLARC-M-10.7B)
* [maywell/PiVoT-10.7B-Mistral-v0.2-RP](https://huggingface.co/maywell/PiVoT-10.7B-Mistral-v0.2-RP)
* [kyujinpy/Sakura-SOLAR-Instruct](https://huggingface.co/kyujinpy/Sakura-SOLAR-Instruct)
* [jeonsworld/CarbonVillain-en-10.7B-v1](https://huggingface.co/jeonsworld/CarbonVillain-en-10.7B-v1)
## Evals:
* Pending
## Examples:
```
Example 1:
User:
Hello lumi, what is the meaning of life
in around 100 words.
Lumosia:
The meaning of life can vary greatly
depending on individual beliefs,
values, and experiences. One common
perspective suggests that the primary
purpose of life is to seek happiness,
fulfillment, and personal growth
through relationships
accomplishments, and spiritual
awareness. Living with integrity.
compassion, and gratitude while
making a positive impact on others
and the world around us can also
contribute to finding meaning in life
UItimately, the meaning of life is
subjective and unique to each
individual, who must define it for
themselves through exploration
reflection, and personal choice.
```
```
Example 2:
User:
Explain a MoE (Mixture of Experts) in
around 100 words
Lumosia:
A MoE, short for Mixture of Experts, is
a machine learning technique utilized
in ensemble learning. It involves
combining multiple specialist models
(experts) to optimize predictive
performance. Each expert focuses on
a subset of the input features or data
domains, making them specialized in
particular areas. Through a weighting
mechanism, like Gaussian Mixture
Model, the predictions of experts are
blended to produce a final result. MoE
models demonstrate effectiveness in
handling complex or ambiguous
inputs where a single model might
struggle. They are commonly used in
natural language processing.
computer vision, and speech synthesis.
```
## 🧩 Configuration
```
yamlbase_model: DopeorNope/SOLARC-M-10.7B
gate_mode: hidden
dtype: bfloat16
experts:
- source_model: DopeorNope/SOLARC-M-10.7B
positive_prompts: [""]
- source_model: maywell/PiVoT-10.7B-Mistral-v0.2-RP
positive_prompts: [""]
- source_model: kyujinpy/Sakura-SOLAR-Instruct
positive_prompts: [""]
- source_model: jeonsworld/CarbonVillain-en-10.7B-v1
positive_prompts: [""]
```
## 💻 Usage
```
python
!pip install -qU transformers bitsandbytes accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "Steelskull/Lumosia-MoE-4x10.7"
tokenizer = AutoTokenizer.from_pretrained(model)
pipeline = transformers.pipeline(
"text-generation",
model=model,
model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True},
)
messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in less than 100 words."}]
prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
```
|
SharonTudi/DIALOGUE
|
SharonTudi
| 2024-01-10T09:44:24Z | 92 | 0 |
transformers
|
[
"transformers",
"tensorboard",
"safetensors",
"bert",
"text-classification",
"generated_from_trainer",
"base_model:google-bert/bert-base-uncased",
"base_model:finetune:google-bert/bert-base-uncased",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-12-13T16:04:21Z |
---
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: DIALOGUE
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. -->
# DIALOGUE
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0320
- Accuracy: 0.9902
## 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: 30
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 1.2742 | 0.31 | 15 | 1.0896 | 0.7353 |
| 0.9231 | 0.62 | 30 | 0.7436 | 0.8039 |
| 0.7035 | 0.94 | 45 | 0.4280 | 0.9706 |
| 0.4361 | 1.25 | 60 | 0.2308 | 1.0 |
| 0.3081 | 1.56 | 75 | 0.1590 | 0.9902 |
| 0.1794 | 1.88 | 90 | 0.1269 | 0.9706 |
| 0.0988 | 2.19 | 105 | 0.0605 | 0.9902 |
| 0.0606 | 2.5 | 120 | 0.0617 | 0.9902 |
| 0.0372 | 2.81 | 135 | 0.0474 | 0.9902 |
| 0.0209 | 3.12 | 150 | 0.0411 | 0.9902 |
| 0.0134 | 3.44 | 165 | 0.0326 | 0.9902 |
| 0.0099 | 3.75 | 180 | 0.0273 | 0.9902 |
| 0.0085 | 4.06 | 195 | 0.0348 | 0.9902 |
| 0.0065 | 4.38 | 210 | 0.0335 | 0.9902 |
| 0.0058 | 4.69 | 225 | 0.0318 | 0.9902 |
| 0.0047 | 5.0 | 240 | 0.0309 | 0.9902 |
| 0.0041 | 5.31 | 255 | 0.0289 | 0.9902 |
| 0.0041 | 5.62 | 270 | 0.0284 | 0.9902 |
| 0.0038 | 5.94 | 285 | 0.0275 | 0.9902 |
| 0.0036 | 6.25 | 300 | 0.0270 | 0.9902 |
| 0.003 | 6.56 | 315 | 0.0260 | 0.9902 |
| 0.0027 | 6.88 | 330 | 0.0270 | 0.9902 |
| 0.0026 | 7.19 | 345 | 0.0291 | 0.9902 |
| 0.0024 | 7.5 | 360 | 0.0298 | 0.9902 |
| 0.0023 | 7.81 | 375 | 0.0283 | 0.9902 |
| 0.0024 | 8.12 | 390 | 0.0255 | 0.9902 |
| 0.0021 | 8.44 | 405 | 0.0251 | 0.9902 |
| 0.0019 | 8.75 | 420 | 0.0260 | 0.9902 |
| 0.0019 | 9.06 | 435 | 0.0264 | 0.9902 |
| 0.0017 | 9.38 | 450 | 0.0266 | 0.9902 |
| 0.0017 | 9.69 | 465 | 0.0276 | 0.9902 |
| 0.0017 | 10.0 | 480 | 0.0271 | 0.9902 |
| 0.0015 | 10.31 | 495 | 0.0271 | 0.9902 |
| 0.0015 | 10.62 | 510 | 0.0271 | 0.9902 |
| 0.0015 | 10.94 | 525 | 0.0266 | 0.9902 |
| 0.0014 | 11.25 | 540 | 0.0261 | 0.9902 |
| 0.0013 | 11.56 | 555 | 0.0260 | 0.9902 |
| 0.0013 | 11.88 | 570 | 0.0264 | 0.9902 |
| 0.0013 | 12.19 | 585 | 0.0268 | 0.9902 |
| 0.0013 | 12.5 | 600 | 0.0270 | 0.9902 |
| 0.0012 | 12.81 | 615 | 0.0274 | 0.9902 |
| 0.0012 | 13.12 | 630 | 0.0274 | 0.9902 |
| 0.0012 | 13.44 | 645 | 0.0278 | 0.9902 |
| 0.0011 | 13.75 | 660 | 0.0278 | 0.9902 |
| 0.001 | 14.06 | 675 | 0.0278 | 0.9902 |
| 0.001 | 14.38 | 690 | 0.0283 | 0.9902 |
| 0.001 | 14.69 | 705 | 0.0290 | 0.9902 |
| 0.001 | 15.0 | 720 | 0.0286 | 0.9902 |
| 0.001 | 15.31 | 735 | 0.0284 | 0.9902 |
| 0.001 | 15.62 | 750 | 0.0285 | 0.9902 |
| 0.0009 | 15.94 | 765 | 0.0289 | 0.9902 |
| 0.0009 | 16.25 | 780 | 0.0298 | 0.9902 |
| 0.0009 | 16.56 | 795 | 0.0305 | 0.9902 |
| 0.0009 | 16.88 | 810 | 0.0309 | 0.9902 |
| 0.0009 | 17.19 | 825 | 0.0304 | 0.9902 |
| 0.0008 | 17.5 | 840 | 0.0303 | 0.9902 |
| 0.0008 | 17.81 | 855 | 0.0302 | 0.9902 |
| 0.0009 | 18.12 | 870 | 0.0301 | 0.9902 |
| 0.0008 | 18.44 | 885 | 0.0300 | 0.9902 |
| 0.0008 | 18.75 | 900 | 0.0302 | 0.9902 |
| 0.0008 | 19.06 | 915 | 0.0300 | 0.9902 |
| 0.0007 | 19.38 | 930 | 0.0301 | 0.9902 |
| 0.0007 | 19.69 | 945 | 0.0299 | 0.9902 |
| 0.0008 | 20.0 | 960 | 0.0304 | 0.9902 |
| 0.0007 | 20.31 | 975 | 0.0302 | 0.9902 |
| 0.0007 | 20.62 | 990 | 0.0304 | 0.9902 |
| 0.0007 | 20.94 | 1005 | 0.0305 | 0.9902 |
| 0.0007 | 21.25 | 1020 | 0.0312 | 0.9902 |
| 0.0007 | 21.56 | 1035 | 0.0311 | 0.9902 |
| 0.0007 | 21.88 | 1050 | 0.0310 | 0.9902 |
| 0.0007 | 22.19 | 1065 | 0.0310 | 0.9902 |
| 0.0007 | 22.5 | 1080 | 0.0309 | 0.9902 |
| 0.0006 | 22.81 | 1095 | 0.0311 | 0.9902 |
| 0.0006 | 23.12 | 1110 | 0.0313 | 0.9902 |
| 0.0007 | 23.44 | 1125 | 0.0313 | 0.9902 |
| 0.0007 | 23.75 | 1140 | 0.0313 | 0.9902 |
| 0.0006 | 24.06 | 1155 | 0.0312 | 0.9902 |
| 0.0006 | 24.38 | 1170 | 0.0313 | 0.9902 |
| 0.0007 | 24.69 | 1185 | 0.0314 | 0.9902 |
| 0.0006 | 25.0 | 1200 | 0.0313 | 0.9902 |
| 0.0006 | 25.31 | 1215 | 0.0314 | 0.9902 |
| 0.0006 | 25.62 | 1230 | 0.0315 | 0.9902 |
| 0.0006 | 25.94 | 1245 | 0.0316 | 0.9902 |
| 0.0006 | 26.25 | 1260 | 0.0316 | 0.9902 |
| 0.0006 | 26.56 | 1275 | 0.0316 | 0.9902 |
| 0.0006 | 26.88 | 1290 | 0.0316 | 0.9902 |
| 0.0006 | 27.19 | 1305 | 0.0315 | 0.9902 |
| 0.0006 | 27.5 | 1320 | 0.0319 | 0.9902 |
| 0.0006 | 27.81 | 1335 | 0.0320 | 0.9902 |
| 0.0006 | 28.12 | 1350 | 0.0320 | 0.9902 |
| 0.0006 | 28.44 | 1365 | 0.0320 | 0.9902 |
| 0.0006 | 28.75 | 1380 | 0.0320 | 0.9902 |
| 0.0006 | 29.06 | 1395 | 0.0320 | 0.9902 |
| 0.0006 | 29.38 | 1410 | 0.0320 | 0.9902 |
| 0.0006 | 29.69 | 1425 | 0.0320 | 0.9902 |
| 0.0006 | 30.0 | 1440 | 0.0320 | 0.9902 |
### Framework versions
- Transformers 4.36.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0
|
TheBloke/Lumosia-MoE-4x10.7-GGUF
|
TheBloke
| 2024-01-10T09:43:02Z | 215 | 6 |
transformers
|
[
"transformers",
"gguf",
"mixtral",
"moe",
"merge",
"mergekit",
"lazymergekit",
"DopeorNope/SOLARC-M-10.7B",
"maywell/PiVoT-10.7B-Mistral-v0.2-RP",
"kyujinpy/Sakura-SOLAR-Instruct",
"jeonsworld/CarbonVillain-en-10.7B-v1",
"base_model:SteelStorage/Lumosia-MoE-4x10.7",
"base_model:quantized:SteelStorage/Lumosia-MoE-4x10.7",
"license:apache-2.0",
"region:us",
"conversational"
] | null | 2024-01-10T05:01:15Z |
---
base_model: Steelskull/Lumosia-MoE-4x10.7
inference: false
license: apache-2.0
model_creator: Steel
model_name: Lumosia MoE 4X10.7
model_type: mixtral
prompt_template: '### System:
### USER:{prompt}
### Assistant:
'
quantized_by: TheBloke
tags:
- moe
- merge
- mergekit
- lazymergekit
- DopeorNope/SOLARC-M-10.7B
- maywell/PiVoT-10.7B-Mistral-v0.2-RP
- kyujinpy/Sakura-SOLAR-Instruct
- jeonsworld/CarbonVillain-en-10.7B-v1
---
<!-- markdownlint-disable MD041 -->
<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->
# Lumosia MoE 4X10.7 - GGUF
- Model creator: [Steel](https://huggingface.co/Steelskull)
- Original model: [Lumosia MoE 4X10.7](https://huggingface.co/Steelskull/Lumosia-MoE-4x10.7)
<!-- description start -->
## Description
This repo contains GGUF format model files for [Steel's Lumosia MoE 4X10.7](https://huggingface.co/Steelskull/Lumosia-MoE-4x10.7).
These files were quantised using hardware kindly provided by [Massed Compute](https://massedcompute.com/).
<!-- description end -->
<!-- README_GGUF.md-about-gguf start -->
### About GGUF
GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp.
Here is an 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.
* [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.
* [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.
* [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.
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
* [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use.
* [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.
<!-- README_GGUF.md-about-gguf end -->
<!-- repositories-available start -->
## Repositories available
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Lumosia-MoE-4x10.7-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/Lumosia-MoE-4x10.7-GGUF)
* [Steel's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/Steelskull/Lumosia-MoE-4x10.7)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: Lumosia
```
### System:
### USER:{prompt}
### Assistant:
```
<!-- prompt-template end -->
<!-- compatibility_gguf start -->
## Compatibility
These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221)
They are also compatible with many third party UIs and libraries - please see the list at the top of this README.
## Explanation of quantisation methods
<details>
<summary>Click to see details</summary>
The new methods available are:
* GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
* GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
* GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
* GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
* GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
Refer to the Provided Files table below to see what files use which methods, and how.
</details>
<!-- compatibility_gguf end -->
<!-- README_GGUF.md-provided-files start -->
## Provided files
| Name | Quant method | Bits | Size | Max RAM required | Use case |
| ---- | ---- | ---- | ---- | ---- | ----- |
| [lumosia-moe-4x10.7.Q2_K.gguf](https://huggingface.co/TheBloke/Lumosia-MoE-4x10.7-GGUF/blob/main/lumosia-moe-4x10.7.Q2_K.gguf) | Q2_K | 2 | 12.02 GB| 14.52 GB | smallest, significant quality loss - not recommended for most purposes |
| [lumosia-moe-4x10.7.Q3_K_S.gguf](https://huggingface.co/TheBloke/Lumosia-MoE-4x10.7-GGUF/blob/main/lumosia-moe-4x10.7.Q3_K_S.gguf) | Q3_K_S | 3 | 15.57 GB| 18.07 GB | very small, high quality loss |
| [lumosia-moe-4x10.7.Q3_K_M.gguf](https://huggingface.co/TheBloke/Lumosia-MoE-4x10.7-GGUF/blob/main/lumosia-moe-4x10.7.Q3_K_M.gguf) | Q3_K_M | 3 | 15.70 GB| 18.20 GB | very small, high quality loss |
| [lumosia-moe-4x10.7.Q3_K_L.gguf](https://huggingface.co/TheBloke/Lumosia-MoE-4x10.7-GGUF/blob/main/lumosia-moe-4x10.7.Q3_K_L.gguf) | Q3_K_L | 3 | 15.83 GB| 18.33 GB | small, substantial quality loss |
| [lumosia-moe-4x10.7.Q4_0.gguf](https://huggingface.co/TheBloke/Lumosia-MoE-4x10.7-GGUF/blob/main/lumosia-moe-4x10.7.Q4_0.gguf) | Q4_0 | 4 | 20.34 GB| 22.84 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [lumosia-moe-4x10.7.Q4_K_S.gguf](https://huggingface.co/TheBloke/Lumosia-MoE-4x10.7-GGUF/blob/main/lumosia-moe-4x10.7.Q4_K_S.gguf) | Q4_K_S | 4 | 20.35 GB| 22.85 GB | small, greater quality loss |
| [lumosia-moe-4x10.7.Q4_K_M.gguf](https://huggingface.co/TheBloke/Lumosia-MoE-4x10.7-GGUF/blob/main/lumosia-moe-4x10.7.Q4_K_M.gguf) | Q4_K_M | 4 | 20.37 GB| 22.87 GB | medium, balanced quality - recommended |
| [lumosia-moe-4x10.7.Q5_0.gguf](https://huggingface.co/TheBloke/Lumosia-MoE-4x10.7-GGUF/blob/main/lumosia-moe-4x10.7.Q5_0.gguf) | Q5_0 | 5 | 24.84 GB| 27.34 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [lumosia-moe-4x10.7.Q5_K_S.gguf](https://huggingface.co/TheBloke/Lumosia-MoE-4x10.7-GGUF/blob/main/lumosia-moe-4x10.7.Q5_K_S.gguf) | Q5_K_S | 5 | 24.84 GB| 27.34 GB | large, low quality loss - recommended |
| [lumosia-moe-4x10.7.Q5_K_M.gguf](https://huggingface.co/TheBloke/Lumosia-MoE-4x10.7-GGUF/blob/main/lumosia-moe-4x10.7.Q5_K_M.gguf) | Q5_K_M | 5 | 24.85 GB| 27.35 GB | large, very low quality loss - recommended |
| [lumosia-moe-4x10.7.Q6_K.gguf](https://huggingface.co/TheBloke/Lumosia-MoE-4x10.7-GGUF/blob/main/lumosia-moe-4x10.7.Q6_K.gguf) | Q6_K | 6 | 29.62 GB| 32.12 GB | very large, extremely low quality loss |
| [lumosia-moe-4x10.7.Q8_0.gguf](https://huggingface.co/TheBloke/Lumosia-MoE-4x10.7-GGUF/blob/main/lumosia-moe-4x10.7.Q8_0.gguf) | Q8_0 | 8 | 38.36 GB| 40.86 GB | very large, extremely low quality loss - not recommended |
**Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
<!-- README_GGUF.md-provided-files end -->
<!-- README_GGUF.md-how-to-download start -->
## How to download GGUF files
**Note for manual downloaders:** You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.
The following clients/libraries will automatically download models for you, providing a list of available models to choose from:
* LM Studio
* LoLLMS Web UI
* Faraday.dev
### In `text-generation-webui`
Under Download Model, you can enter the model repo: TheBloke/Lumosia-MoE-4x10.7-GGUF and below it, a specific filename to download, such as: lumosia-moe-4x10.7.Q4_K_M.gguf.
Then click Download.
### On the command line, including multiple files at once
I recommend using the `huggingface-hub` Python library:
```shell
pip3 install huggingface-hub
```
Then you can download any individual model file to the current directory, at high speed, with a command like this:
```shell
huggingface-cli download TheBloke/Lumosia-MoE-4x10.7-GGUF lumosia-moe-4x10.7.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
<details>
<summary>More advanced huggingface-cli download usage (click to read)</summary>
You can also download multiple files at once with a pattern:
```shell
huggingface-cli download TheBloke/Lumosia-MoE-4x10.7-GGUF --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'
```
For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
```shell
pip3 install hf_transfer
```
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
```shell
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/Lumosia-MoE-4x10.7-GGUF lumosia-moe-4x10.7.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
</details>
<!-- README_GGUF.md-how-to-download end -->
<!-- README_GGUF.md-how-to-run start -->
## Example `llama.cpp` command
Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
```shell
./main -ngl 35 -m lumosia-moe-4x10.7.Q4_K_M.gguf --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "### System:\n\n### USER:{prompt}\n\n### Assistant:"
```
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
Change `-c 4096` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically. Note that longer sequence lengths require much more resources, so you may need to reduce this value.
If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)
## How to run in `text-generation-webui`
Further instructions can be found in the text-generation-webui documentation, here: [text-generation-webui/docs/04 ‐ Model Tab.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/04%20%E2%80%90%20Model%20Tab.md#llamacpp).
## How to run from Python code
You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries. Note that at the time of writing (Nov 27th 2023), ctransformers has not been updated for some time and is not compatible with some recent models. Therefore I recommend you use llama-cpp-python.
### How to load this model in Python code, using llama-cpp-python
For full documentation, please see: [llama-cpp-python docs](https://abetlen.github.io/llama-cpp-python/).
#### First install the package
Run one of the following commands, according to your system:
```shell
# Base ctransformers with no GPU acceleration
pip install llama-cpp-python
# With NVidia CUDA acceleration
CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install llama-cpp-python
# Or with OpenBLAS acceleration
CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS" pip install llama-cpp-python
# Or with CLBLast acceleration
CMAKE_ARGS="-DLLAMA_CLBLAST=on" pip install llama-cpp-python
# Or with AMD ROCm GPU acceleration (Linux only)
CMAKE_ARGS="-DLLAMA_HIPBLAS=on" pip install llama-cpp-python
# Or with Metal GPU acceleration for macOS systems only
CMAKE_ARGS="-DLLAMA_METAL=on" pip install llama-cpp-python
# In windows, to set the variables CMAKE_ARGS in PowerShell, follow this format; eg for NVidia CUDA:
$env:CMAKE_ARGS = "-DLLAMA_OPENBLAS=on"
pip install llama-cpp-python
```
#### Simple llama-cpp-python example code
```python
from llama_cpp import Llama
# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
llm = Llama(
model_path="./lumosia-moe-4x10.7.Q4_K_M.gguf", # Download the model file first
n_ctx=4096, # The max sequence length to use - note that longer sequence lengths require much more resources
n_threads=8, # The number of CPU threads to use, tailor to your system and the resulting performance
n_gpu_layers=35 # The number of layers to offload to GPU, if you have GPU acceleration available
)
# Simple inference example
output = llm(
"### System:\n\n### USER:{prompt}\n\n### Assistant:", # Prompt
max_tokens=512, # Generate up to 512 tokens
stop=["</s>"], # Example stop token - not necessarily correct for this specific model! Please check before using.
echo=True # Whether to echo the prompt
)
# Chat Completion API
llm = Llama(model_path="./lumosia-moe-4x10.7.Q4_K_M.gguf", chat_format="llama-2") # Set chat_format according to the model you are using
llm.create_chat_completion(
messages = [
{"role": "system", "content": "You are a story writing assistant."},
{
"role": "user",
"content": "Write a story about llamas."
}
]
)
```
## How to use with LangChain
Here are guides on using llama-cpp-python and ctransformers with LangChain:
* [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp)
* [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers)
<!-- README_GGUF.md-how-to-run end -->
<!-- footer start -->
<!-- 200823 -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute
Thanks to the [chirper.ai](https://chirper.ai) team!
Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Aemon Algiz.
**Patreon special mentions**: Michael Levine, 阿明, Trailburnt, Nikolai Manek, John Detwiler, Randy H, Will Dee, Sebastain Graf, NimbleBox.ai, Eugene Pentland, Emad Mostaque, Ai Maven, Jim Angel, Jeff Scroggin, Michael Davis, Manuel Alberto Morcote, Stephen Murray, Robert, Justin Joy, Luke @flexchar, Brandon Frisco, Elijah Stavena, S_X, Dan Guido, Undi ., Komninos Chatzipapas, Shadi, theTransient, Lone Striker, Raven Klaugh, jjj, Cap'n Zoog, Michel-Marie MAUDET (LINAGORA), Matthew Berman, David, Fen Risland, Omer Bin Jawed, Luke Pendergrass, Kalila, OG, Erik Bjäreholt, Rooh Singh, Joseph William Delisle, Dan Lewis, TL, John Villwock, AzureBlack, Brad, Pedro Madruga, Caitlyn Gatomon, K, jinyuan sun, Mano Prime, Alex, Jeffrey Morgan, Alicia Loh, Illia Dulskyi, Chadd, transmissions 11, fincy, Rainer Wilmers, ReadyPlayerEmma, knownsqashed, Mandus, biorpg, Deo Leter, Brandon Phillips, SuperWojo, Sean Connelly, Iucharbius, Jack West, Harry Royden McLaughlin, Nicholas, terasurfer, Vitor Caleffi, Duane Dunston, Johann-Peter Hartmann, David Ziegler, Olakabola, Ken Nordquist, Trenton Dambrowitz, Tom X Nguyen, Vadim, Ajan Kanaga, Leonard Tan, Clay Pascal, Alexandros Triantafyllidis, JM33133, Xule, vamX, ya boyyy, subjectnull, Talal Aujan, Alps Aficionado, wassieverse, Ari Malik, James Bentley, Woland, Spencer Kim, Michael Dempsey, Fred von Graf, Elle, zynix, William Richards, Stanislav Ovsiannikov, Edmond Seymore, Jonathan Leane, Martin Kemka, usrbinkat, Enrico Ros
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
<!-- footer end -->
<!-- original-model-card start -->
# Original model card: Steel's Lumosia MoE 4X10.7
# Lumosia-MoE-4x10.7
"Lumosia" was selected as its a MoE of Multiple SOLAR Merges so it really "Lights the way".... its 3am.
This is a very experimantal model. its a MoE of all good performing Solar models (based off of personal experiance not open leaderboard),
Why? Dunno whated to see what would happen
context is maybe 16k?
Chat-instruct breaks the model at the moment, not really sure why, even tho it will follow instructions.
Waiting on fix for quants of FrankenMoE
Template:
```
### System:
### USER:{prompt}
### Assistant:
```
Settings:
```
Temp: 1.0
min-p: 0.02-0.1
```
Lumosia-MoE-4x10.7 is a Mixure of Experts (MoE) made with the following models:
* [DopeorNope/SOLARC-M-10.7B](https://huggingface.co/DopeorNope/SOLARC-M-10.7B)
* [maywell/PiVoT-10.7B-Mistral-v0.2-RP](https://huggingface.co/maywell/PiVoT-10.7B-Mistral-v0.2-RP)
* [kyujinpy/Sakura-SOLAR-Instruct](https://huggingface.co/kyujinpy/Sakura-SOLAR-Instruct)
* [jeonsworld/CarbonVillain-en-10.7B-v1](https://huggingface.co/jeonsworld/CarbonVillain-en-10.7B-v1)
## Evals:
* Pending
## Examples:
```
Example 1:
User:
Hello lumi, what is the meaning of life
in around 100 words.
Lumosia:
The meaning of life can vary greatly
depending on individual beliefs,
values, and experiences. One common
perspective suggests that the primary
purpose of life is to seek happiness,
fulfillment, and personal growth
through relationships
accomplishments, and spiritual
awareness. Living with integrity.
compassion, and gratitude while
making a positive impact on others
and the world around us can also
contribute to finding meaning in life
UItimately, the meaning of life is
subjective and unique to each
individual, who must define it for
themselves through exploration
reflection, and personal choice.
```
```
Example 2:
User:
Explain a MoE (Mixture of Experts) in
around 100 words
Lumosia:
A MoE, short for Mixture of Experts, is
a machine learning technique utilized
in ensemble learning. It involves
combining multiple specialist models
(experts) to optimize predictive
performance. Each expert focuses on
a subset of the input features or data
domains, making them specialized in
particular areas. Through a weighting
mechanism, like Gaussian Mixture
Model, the predictions of experts are
blended to produce a final result. MoE
models demonstrate effectiveness in
handling complex or ambiguous
inputs where a single model might
struggle. They are commonly used in
natural language processing.
computer vision, and speech synthesis.
```
## 🧩 Configuration
```
yamlbase_model: DopeorNope/SOLARC-M-10.7B
gate_mode: hidden
dtype: bfloat16
experts:
- source_model: DopeorNope/SOLARC-M-10.7B
positive_prompts: [""]
- source_model: maywell/PiVoT-10.7B-Mistral-v0.2-RP
positive_prompts: [""]
- source_model: kyujinpy/Sakura-SOLAR-Instruct
positive_prompts: [""]
- source_model: jeonsworld/CarbonVillain-en-10.7B-v1
positive_prompts: [""]
```
## 💻 Usage
```
python
!pip install -qU transformers bitsandbytes accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "Steelskull/Lumosia-MoE-4x10.7"
tokenizer = AutoTokenizer.from_pretrained(model)
pipeline = transformers.pipeline(
"text-generation",
model=model,
model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True},
)
messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in less than 100 words."}]
prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
```
<!-- original-model-card end -->
|
openvoid/Prox-1-Mistral-7B
|
openvoid
| 2024-01-10T09:39:13Z | 4 | 0 |
transformers
|
[
"transformers",
"pytorch",
"mistral",
"text-generation",
"instruct",
"finetune",
"chatml",
"gpt4",
"synthetic data",
"distillation",
"conversational",
"en",
"base_model:cognitivecomputations/dolphin-2.1-mistral-7b",
"base_model:finetune:cognitivecomputations/dolphin-2.1-mistral-7b",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2024-01-10T09:32:08Z |
---
base_model: cognitivecomputations/dolphin-2.1-mistral-7b
tags:
- mistral
- instruct
- finetune
- chatml
- gpt4
- synthetic data
- distillation
model-index:
- name: Prox-1-Mistral-7B
results: []
license: apache-2.0
language:
- en
---
# Prox 1.0 - Mistral 7B
## Model description
Prox 1.0 Mistral 7B represents a significant evolution in the Mistral Fine-tune series, having been augmented with an extensive array of datasets focused on hacking instructions and Q&A content.
[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
|
s3nh/TinyLLama-4x1.1B-MoE
|
s3nh
| 2024-01-10T09:36:30Z | 134 | 6 |
transformers
|
[
"transformers",
"safetensors",
"mixtral",
"text-generation",
"mergekit",
"merge",
"conversational",
"en",
"base_model:Tensoic/TinyLlama-1.1B-3T-openhermes",
"base_model:merge:Tensoic/TinyLlama-1.1B-3T-openhermes",
"base_model:TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"base_model:merge:TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"base_model:phanerozoic/Tiny-Pirate-1.1b-v0.1",
"base_model:merge:phanerozoic/Tiny-Pirate-1.1b-v0.1",
"license:mit",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2024-01-10T09:22:44Z |
---
base_model:
- TinyLlama/TinyLlama-1.1B-Chat-v1.0
- 78health/TinyLlama_1.1B-function-calling
- phanerozoic/Tiny-Pirate-1.1b-v0.1
- Tensoic/TinyLlama-1.1B-3T-openhermes
tags:
- mergekit
- merge
license: mit
language:
- en
library_name: transformers
pipeline_tag: text-generation
---
Example usage:
```python
from transformers import AutoModelForCausalLM
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("s3nh/TinyLLama-1.1B-MoE")
tokenizer = AutoTokenizer.from_pretrained("s3nh/TinyLLama-1.1B-MoE")
input_text = """
###Input: You are a pirate. tell me a story about wrecked ship.
###Response:
""")
input_ids = tokenizer.encode(input_text, return_tensors='pt').to(device)
output = model.generate(inputs=input_ids,
max_length=max_length,
do_sample=True,
top_k=10,
temperature=0.7,
pad_token_id=tokenizer.eos_token_id,
attention_mask=input_ids.new_ones(input_ids.shape))
tokenizer.decode(output[0], skip_special_tokens=True)
```
This model was possible to create by tremendous work of mergekit developers. I decided to merge tinyLlama models to
create mixture of experts.
Config used as below:
```
"""base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
experts:
- source_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
positive_prompts:
- "chat"
- "assistant"
- "tell me"
- "explain"
- source_model: 78health/TinyLlama_1.1B-function-calling
positive_prompts:
- "code"
- "python"
- "javascript"
- "programming"
- "algorithm"
- source_model: phanerozoic/Tiny-Pirate-1.1b-v0.1
positive_prompts:
- "storywriting"
- "write"
- "scene"
- "story"
- "character"
- source_model: Tensoic/TinyLlama-1.1B-3T-openhermes
positive_prompts:
- "reason"
- "provide"
- "instruct"
- "summarize"
- "count"
"""
```
|
Deojaklah/Memey
|
Deojaklah
| 2024-01-10T09:34:55Z | 0 | 0 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2024-01-10T09:34:54Z |
---
license: creativeml-openrail-m
---
|
PracticeLLM/Twice-KoSOLAR-16.1B-test
|
PracticeLLM
| 2024-01-10T09:26:25Z | 3,667 | 1 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"merge",
"en",
"ko",
"arxiv:2312.15166",
"license:cc-by-nc-sa-4.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-12-30T01:47:43Z |
---
language:
- en
- ko
pipeline_tag: text-generation
license: cc-by-nc-sa-4.0
tags:
- merge
---
# **Twice-KoSOLAR-16.1B-test**
## Model Details
**Model Developers** Kyujin Han (kyujinpy)
**모델 목적**
<img src='./solar.png'>
최근, SOLAR-10.7B 모델이 [Depth-Up-Scaling](https://arxiv.org/pdf/2312.15166.pdf)(위의 사진) 방법론을 내세워서 LLM 리더보드에서 좋은 성능을 보이고 있다. 더불어서 `야놀자`에서 만든 `seungduk/KoSOLAR-10.7B-v0.1` 모델은 Ko-LLM 리더보드에 큰 파급력을 불러오면서, 앞으로의 리더보드의 흐름도 바뀔 것으로 예상된다.
여기서 단순한 호기심이 들었다. **Upstage에서 발표한 Depth-Up-Scaling(DUS) 방법론은 mistral-7B 모델 2개를 merge(passthrough)한 방법**이다.
이때 놀랍게도, DUS 방법론을 적용한 `upstage/SOLAR-10.7B-v1.0`모델은 기존의 mistral-7B 모델보다 리더보드에서 높은 성능을 기록했다. (아래의 테이블 참고)
그렇다면, DUS 방법론을 제한없이, 다른 모델에 적용하면 똑같은 결과가 발생할지 너무나 궁금했다. 🙃
실험을 통해서 나의 호기심에 대한 결론을 내려보고자 한다. 😋😋
| Model | Average | ARC | HellaSwag | MMLU | TruthfulQA | Winogrande | GSM8K |
| --- | --- | --- | --- | --- | --- | --- | --- |
| [seungduk/KoSOLAR-10.7B-v0.1](https://huggingface.co/seungduk/KoSOLAR-10.7B-v0.1) | **66.04** | 62.03 | 84.54 | 65.56 | 45.03 | 83.58 | 55.50 |
| [upstage/SOLAR-10.7B-v1.0](https://huggingface.co/upstage/SOLAR-10.7B-v1.0) | **66.04** | 61.95 | 84.60 | 65.48 | 45.04 | 83.66 | 55.50 |
| [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) | 60.97 | 59.98 | 83.31 | 64.16 | 42.15 | 78.37 | 37.83 |
> Follow up as [En-link](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard).
**Method**
Using [Mergekit](https://github.com/cg123/mergekit).
- Korean Pretrain-SOTA (12/30) [seungduk/KoSOLAR-10.7B-v0.1](https://huggingface.co/seungduk/KoSOLAR-10.7B-v0.1)
**Merge config**
기존 [`SOLAR-10.7B`](https://arxiv.org/pdf/2312.15166.pdf) 논문에서는 mistral-7B layer를 `layer-24`와 `layer-8`로 구분하여서, `layer-24` 2개를 병합하여 총 `layer-48`를 완성했다.
위의 ratio가 `uses:waste=3:1` 이므로, 같은 비율로 `seungduk/KoSOLAR-10.7B-v0.1` layer를 `layer-36`와 `layer-12`로 구분하고, `layer-36` 2개를 병합하여 총 `layer-72`를 완성시켰다.
자세한 merge config 아래와 같다.
```yaml
slices:
- sources:
- model: seungduk/KoSOLAR-10.7B-v0.1
layer_range: [0, 36]
- sources:
- model: seungduk/KoSOLAR-10.7B-v0.1
layer_range: [12, 48]
merge_method: passthrough
dtype: float16
```
> Share all of things. It is my belief.
# **Model Benchmark**
## Open Ko-LLM leaderboard & lm-evaluation-harness(zero-shot)
- Follow up as [Ko-link](https://huggingface.co/spaces/upstage/open-ko-llm-leaderboard).
| Model | Average | ARC | HellaSwag | MMLU | TruthfulQA | Ko-CommonGenV2 |
| --- | --- | --- | --- | --- | --- | --- |
| PracticeLLM/Twice-KoSOLAR-16.1B-test | 50.20 | 45.65 | 57.14 | 51.39 | 42.99 | 53.84 |
| [Megastudy/M-SOLAR-10.7B-v1.1-beta](https://huggingface.co/Megastudy/M-SOLAR-10.7B-v1.1-beta) | 55.25 | 51.71 | 60.86 | 54.24 | 47.12 | 62.34 |
| [jjourney1125/M-SOLAR-10.7B-v1.0](https://huggingface.co/jjourney1125/M-SOLAR-10.7B-v1.0) | 55.15 | 49.57 | 60.12 | 54.60 | 49.23 | 62.22 |
| [seungduk/KoSOLAR-10.7B-v0.1](https://huggingface.co/seungduk/KoSOLAR-10.7B-v0.1) | 52.40 | 47.18 | 59.54 | 52.04 | 41.84 | 61.39 |
- Follow up as [beomi/LM-Harness](https://github.com/Beomi/ko-lm-evaluation-harness)
```
gpt2 (pretrained=PracticeLLM/Twice-KoSOLAR-16.1B-test), limit: None, provide_description: False, num_fewshot: 0, batch_size: None
| Task |Version| Metric |Value | |Stderr|
|----------------|------:|--------|-----:|---|-----:|
|kobest_boolq | 0|acc |0.7201|± |0.0120|
| | |macro_f1|0.7073|± |0.0124|
|kobest_copa | 0|acc |0.6510|± |0.0151|
| | |macro_f1|0.6506|± |0.0151|
|kobest_hellaswag| 0|acc |0.4520|± |0.0223|
| | |acc_norm|0.5820|± |0.0221|
| | |macro_f1|0.4475|± |0.0222|
|kobest_sentineg | 0|acc |0.7078|± |0.0229|
| | |macro_f1|0.7071|± |0.0229|
gpt2 (pretrained=Megastudy/M-SOLAR-10.7B-v1.1-beta), limit: None, provide_description: False, num_fewshot: 0, batch_size: None
| Task |Version| Metric |Value | |Stderr|
|----------------|------:|--------|-----:|---|-----:|
|kobest_boolq | 0|acc |0.7137|± |0.0121|
| | |macro_f1|0.6878|± |0.0128|
|kobest_copa | 0|acc |0.7060|± |0.0144|
| | |macro_f1|0.7054|± |0.0145|
|kobest_hellaswag| 0|acc |0.4620|± |0.0223|
| | |acc_norm|0.5360|± |0.0223|
| | |macro_f1|0.4595|± |0.0223|
|kobest_sentineg | 0|acc |0.7431|± |0.0220|
| | |macro_f1|0.7295|± |0.0230|
gpt2 (pretrained=jjourney1125/M-SOLAR-10.7B-v1.0), limit: None, provide_description: False, num_fewshot: 0, batch_size: None
| Task |Version| Metric |Value | |Stderr|
|----------------|------:|--------|-----:|---|-----:|
|kobest_boolq | 0|acc |0.5228|± |0.0133|
| | |macro_f1|0.3788|± |0.0097|
|kobest_copa | 0|acc |0.6860|± |0.0147|
| | |macro_f1|0.6858|± |0.0147|
|kobest_hellaswag| 0|acc |0.4580|± |0.0223|
| | |acc_norm|0.5380|± |0.0223|
| | |macro_f1|0.4552|± |0.0222|
|kobest_sentineg | 0|acc |0.6474|± |0.0240|
| | |macro_f1|0.6012|± |0.0257|
gpt2 (pretrained=yanolja/KoSOLAR-10.7B-v0.1), limit: None, provide_description: False, num_fewshot: 0, batch_size: None
| Task |Version| Metric |Value | |Stderr|
|----------------|------:|--------|-----:|---|-----:|
|kobest_boolq | 0|acc |0.8725|± |0.0089|
| | |macro_f1|0.8722|± |0.0089|
|kobest_copa | 0|acc |0.6850|± |0.0147|
| | |macro_f1|0.6844|± |0.0147|
|kobest_hellaswag| 0|acc |0.4340|± |0.0222|
| | |acc_norm|0.5840|± |0.0221|
| | |macro_f1|0.4296|± |0.0221|
|kobest_sentineg | 0|acc |0.7506|± |0.0217|
| | |macro_f1|0.7505|± |0.0217|
```
## Open EN-LLM leaderboard & lm-evaluation-harness(zero-shot)
- Follow up as [En-link](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard).
| Model | Average | ARC | HellaSwag | MMLU | TruthfulQA | Winogrande | GSM8K |
| --- | --- | --- | --- | --- | --- | --- | --- |
| PracticeLLM/Twice-KoSOLAR-16.1B-test | NaN | NaN | NaN | NaN | NaN | NaN | NaN |
| [kyujinpy/Sakura-SOLAR-Instruct](https://huggingface.co/kyujinpy/Sakura-SOLAR-Instruct) | **74.40** | 70.99 | 88.42 | 66.33 | 71.79 | 83.66 | 65.20 |
| [seungduk/KoSOLAR-10.7B-v0.1](https://huggingface.co/seungduk/KoSOLAR-10.7B-v0.1) | 66.04 | 62.03 | 84.54 | 65.56 | 45.03 | 83.58 | 55.50 |
| [upstage/SOLAR-10.7B-v1.0](https://huggingface.co/upstage/SOLAR-10.7B-v1.0) | 66.04 | 61.95 | 84.60 | 65.48 | 45.04 | 83.66 | 55.50 |
| [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) | 60.97 | 59.98 | 83.31 | 64.16 | 42.15 | 78.37 | 37.83 |
- Follow up as [Eleuther/LM-Harness](https://github.com/EleutherAI/lm-evaluation-harness)
```yaml
(will update)
```
# Implementation Code
```python
### KO-Platypus
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
repo = "PracticeLLM/Twice-KoSOLAR-test"
OpenOrca = AutoModelForCausalLM.from_pretrained(
repo,
return_dict=True,
torch_dtype=torch.float16,
device_map='auto'
)
OpenOrca_tokenizer = AutoTokenizer.from_pretrained(repo)
```
--- Refereces (Model Card)
# yanolja/KoSOLAR-10.7B-v0.1
This model is a Korean vocabulary-extended version of [upstage/SOLAR-10.7B-v1.0](https://huggingface.co/upstage/SOLAR-10.7B-v1.0), trained on various Korean web-crawled datasets that are publicly available on HuggingFace.
The hypothesis was that while maintaining the original performance of the base model, we could add more tokens to the base model's vocabulary by training the embeddings for the new tokens only. The evaluation results seem to indicate that both English and Korean performances were preserved.
## Model Description
Most parameters of [upstage/SOLAR-10.7B-v1.0](https://huggingface.co/upstage/SOLAR-10.7B-v1.0) were frozen except for the embed_tokens layer and the lm_head layer. Embeddings for the existing tokens in those layers were frozen during training. The embeddings for the new tokens have been tuned.
---
# **Meet 10.7B Solar: Elevating Performance with Upstage Depth UP Scaling!**
# **Introduction**
We introduce SOLAR-10.7B, an advanced large language model (LLM) with 10.7 billion parameters, demonstrating superior performance in various natural language processing (NLP) tasks. It's compact, yet remarkably powerful, and demonstrates unparalleled state-of-the-art performance in models with parameters under 30B.
We present a methodology for scaling LLMs called depth up-scaling (DUS) , which encompasses architectural modifications and continued pretraining. In other words, we integrated Mistral 7B weights into the upscaled layers, and finally, continued pre-training for the entire model.
SOLAR-10.7B has remarkable performance. It outperforms models with up to 30B parameters, even surpassing the recent Mixtral 8X7B model. For detailed information, please refer to the experimental table.
Solar 10.7B is an ideal choice for fine-tuning. SOLAR-10.7B offers robustness and adaptability for your fine-tuning needs. Our simple instruction fine-tuning using the SOLAR-10.7B pre-trained model yields significant performance improvements ([SOLAR-10.7B-Instruct-v1.0](https://huggingface.co/upstage/SOLAR-10.7B-Instruct-v1.0)).
For full details of this model please read our [paper](https://arxiv.org/abs/2312.15166).
|
afiqlol/lasto4
|
afiqlol
| 2024-01-10T09:19:18Z | 90 | 0 |
transformers
|
[
"transformers",
"tensorboard",
"safetensors",
"xlm-roberta",
"text-classification",
"generated_from_trainer",
"base_model:citizenlab/twitter-xlm-roberta-base-sentiment-finetunned",
"base_model:finetune:citizenlab/twitter-xlm-roberta-base-sentiment-finetunned",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2024-01-10T07:28:33Z |
---
base_model: citizenlab/twitter-xlm-roberta-base-sentiment-finetunned
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: lasto4
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. -->
# lasto4
This model is a fine-tuned version of [citizenlab/twitter-xlm-roberta-base-sentiment-finetunned](https://huggingface.co/citizenlab/twitter-xlm-roberta-base-sentiment-finetunned) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5596
- Accuracy: 0.8033
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| No log | 1.0 | 300 | 0.4855 | 0.8133 |
| 0.5151 | 2.0 | 600 | 0.5272 | 0.8117 |
| 0.5151 | 3.0 | 900 | 0.5596 | 0.8033 |
### Framework versions
- Transformers 4.35.2
- Pytorch 2.1.1+cpu
- Datasets 2.14.5
- Tokenizers 0.15.0
|
damerajee/Tinyllama-sft-small
|
damerajee
| 2024-01-10T09:11:28Z | 12 | 0 |
peft
|
[
"peft",
"safetensors",
"Instruct",
"TinyLlama",
"text-generation",
"en",
"dataset:yahma/alpaca-cleaned",
"base_model:unsloth/tinyllama-bnb-4bit",
"base_model:adapter:unsloth/tinyllama-bnb-4bit",
"license:mit",
"region:us"
] |
text-generation
| 2024-01-09T16:25:12Z |
---
library_name: peft
base_model: unsloth/tinyllama-bnb-4bit
license: mit
datasets:
- yahma/alpaca-cleaned
language:
- en
pipeline_tag: text-generation
tags:
- Instruct
- TinyLlama
---
# Steps to try the model:
### prompt Template
```python
alpaca_prompt = """Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.
### Instruction:
{}
### Input:
{}
### Response:
{}"""
```
### load the model
```python
from peft import PeftModel, PeftConfig
from transformers import AutoModelForCausalLM ,AutoTokenizer
config = PeftConfig.from_pretrained("damerajee/Tinyllama-sft-small")
model = AutoModelForCausalLM.from_pretrained("unsloth/tinyllama")
tokenizer=AutoTokenizer.from_pretrained("damerajee/Tinyllama-sft-small")
model = PeftModel.from_pretrained(model, "damerajee/Tinyllama-sft-small")l")
```
### Inference
```python
inputs = tokenizer(
[
alpaca_prompt.format(
"i want to learn machine learning help me",
"", # input
"", # output
)
]*1, return_tensors = "pt").to("cuda")
outputs = model.generate(**inputs, max_new_tokens = 312, use_cache = True)
tokenizer.batch_decode(outputs)
```
# Model Information
The base model [unsloth/tinyllama-bnb-4bit](https://huggingface.co/unsloth/tinyllama-bnb-4bit)was Instruct finetuned using [Unsloth](https://github.com/unslothai/unsloth)
# Training Details
The model was trained for 1 epoch on a free goggle colab which took about 1 hour and 30 mins approximately
|
darshan8950/openhermes-mistral-dpo-gptq
|
darshan8950
| 2024-01-10T09:06:03Z | 0 | 0 | null |
[
"tensorboard",
"safetensors",
"trl",
"dpo",
"generated_from_trainer",
"base_model:TheBloke/OpenHermes-2-Mistral-7B-GPTQ",
"base_model:finetune:TheBloke/OpenHermes-2-Mistral-7B-GPTQ",
"license:apache-2.0",
"region:us"
] | null | 2024-01-10T09:05:07Z |
---
license: apache-2.0
base_model: TheBloke/OpenHermes-2-Mistral-7B-GPTQ
tags:
- trl
- dpo
- generated_from_trainer
model-index:
- name: openhermes-mistral-dpo-gptq
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. -->
# openhermes-mistral-dpo-gptq
This model is a fine-tuned version of [TheBloke/OpenHermes-2-Mistral-7B-GPTQ](https://huggingface.co/TheBloke/OpenHermes-2-Mistral-7B-GPTQ) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1934
- Rewards/chosen: 1.5646
- Rewards/rejected: -0.8402
- Rewards/accuracies: 1.0
- Rewards/margins: 2.4048
- Logps/rejected: -45.4271
- Logps/chosen: -277.5632
- Logits/rejected: -1.3185
- Logits/chosen: -2.0273
## 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: 1
- 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: 2
- training_steps: 50
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
| 0.6717 | 0.01 | 10 | 0.5892 | 0.1318 | -0.0930 | 0.75 | 0.2248 | -37.9552 | -291.8918 | -1.2049 | -2.0262 |
| 0.5298 | 0.02 | 20 | 0.3756 | 0.6965 | -0.3112 | 1.0 | 1.0078 | -40.1375 | -286.2441 | -1.2959 | -2.0576 |
| 0.3325 | 0.03 | 30 | 0.2663 | 1.1580 | -0.4907 | 1.0 | 1.6486 | -41.9316 | -281.6295 | -1.3242 | -2.0582 |
| 0.2179 | 0.04 | 40 | 0.2153 | 1.4040 | -0.7133 | 1.0 | 2.1173 | -44.1586 | -279.1697 | -1.3211 | -2.0374 |
| 0.1683 | 0.06 | 50 | 0.1934 | 1.5646 | -0.8402 | 1.0 | 2.4048 | -45.4271 | -277.5632 | -1.3185 | -2.0273 |
### Framework versions
- Transformers 4.35.2
- Pytorch 2.0.1+cu117
- Datasets 2.16.1
- Tokenizers 0.15.0
|
mecoaoge2/fununun
|
mecoaoge2
| 2024-01-10T09:03:41Z | 0 | 0 |
peft
|
[
"peft",
"tensorboard",
"safetensors",
"trl",
"dpo",
"generated_from_trainer",
"base_model:TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"base_model:adapter:TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"license:apache-2.0",
"region:us"
] | null | 2024-01-10T06:22:18Z |
---
license: apache-2.0
library_name: peft
tags:
- trl
- dpo
- generated_from_trainer
base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
model-index:
- name: fununun
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. -->
# fununun
This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6908
- Rewards/chosen: 0.0015
- Rewards/rejected: -0.0032
- Rewards/accuracies: 0.7176
- Rewards/margins: 0.0047
- Logps/rejected: -197.2385
- Logps/chosen: -235.0630
- Logits/rejected: -3.0691
- Logits/chosen: -3.1037
## 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-07
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 20
- training_steps: 100
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
| 0.693 | 0.04 | 20 | 0.6927 | 0.0001 | -0.0007 | 0.5614 | 0.0009 | -197.2139 | -235.0765 | -3.0688 | -3.1035 |
| 0.6922 | 0.07 | 40 | 0.6919 | 0.0007 | -0.0017 | 0.6440 | 0.0024 | -197.2236 | -235.0704 | -3.0690 | -3.1036 |
| 0.6913 | 0.11 | 60 | 0.6913 | 0.0011 | -0.0025 | 0.6886 | 0.0037 | -197.2319 | -235.0664 | -3.0691 | -3.1037 |
| 0.6909 | 0.15 | 80 | 0.6909 | 0.0014 | -0.0030 | 0.7098 | 0.0044 | -197.2367 | -235.0639 | -3.0691 | -3.1037 |
| 0.6906 | 0.19 | 100 | 0.6908 | 0.0015 | -0.0032 | 0.7176 | 0.0047 | -197.2385 | -235.0630 | -3.0691 | -3.1037 |
### Framework versions
- PEFT 0.7.1
- Transformers 4.36.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0
|
lora-moe/belle_dolphine_p18
|
lora-moe
| 2024-01-10T09:02:24Z | 0 | 0 |
peft
|
[
"peft",
"safetensors",
"arxiv:1910.09700",
"base_model:baichuan-inc/Baichuan2-7B-Base",
"base_model:adapter:baichuan-inc/Baichuan2-7B-Base",
"region:us"
] | null | 2024-01-10T09:01:58Z |
---
library_name: peft
base_model: baichuan-inc/Baichuan2-7B-Base
---
# 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 0.7.2.dev0
|
lora-moe/belle_dolphine_p15
|
lora-moe
| 2024-01-10T09:01:03Z | 3 | 0 |
peft
|
[
"peft",
"safetensors",
"arxiv:1910.09700",
"base_model:baichuan-inc/Baichuan2-7B-Base",
"base_model:adapter:baichuan-inc/Baichuan2-7B-Base",
"region:us"
] | null | 2024-01-10T09:00:45Z |
---
library_name: peft
base_model: baichuan-inc/Baichuan2-7B-Base
---
# 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 0.7.2.dev0
|
lora-moe/belle_dolphine_p13
|
lora-moe
| 2024-01-10T09:00:15Z | 0 | 0 |
peft
|
[
"peft",
"safetensors",
"arxiv:1910.09700",
"base_model:baichuan-inc/Baichuan2-7B-Base",
"base_model:adapter:baichuan-inc/Baichuan2-7B-Base",
"region:us"
] | null | 2024-01-10T08:59:51Z |
---
library_name: peft
base_model: baichuan-inc/Baichuan2-7B-Base
---
# 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 0.7.2.dev0
|
lora-moe/belle_dolphine_p10
|
lora-moe
| 2024-01-10T08:59:01Z | 0 | 0 |
peft
|
[
"peft",
"safetensors",
"arxiv:1910.09700",
"base_model:baichuan-inc/Baichuan2-7B-Base",
"base_model:adapter:baichuan-inc/Baichuan2-7B-Base",
"region:us"
] | null | 2024-01-10T08:58:46Z |
---
library_name: peft
base_model: baichuan-inc/Baichuan2-7B-Base
---
# 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 0.7.2.dev0
|
budecosystem/code-millenials-13b
|
budecosystem
| 2024-01-10T08:56:06Z | 1,489 | 3 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"code",
"license:llama2",
"model-index",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2024-01-02T09:16:08Z |
---
license: llama2
library_name: transformers
tags:
- code
model-index:
- name: Code Millenials
results:
- task:
type: text-generation
dataset:
type: openai_humaneval
name: HumanEval
metrics:
- name: pass@1
type: pass@1
value: 0.7621
verified: false
---
# Bud Code Millenials 13B
Welcome to our Code Model repository! Our model is specifically fine-tuned for code generation tasks. Bud Millenial Code Gen open-source models are currently the State of the Art (SOTA) for code generation, beating all the existing models of all sizes. We have achieved a HumanEval value of 80.48 @ Pass 1, beating proprietary models like Gemini Ultra, Claude, GPT-3.5 etc. by a large margin, and on par with GPT-4 (HumanEval ~ 82. Ref. WizardCoder). Our proprietary model (Bud Code Jr) beats GPT-4 as well with a HumanEval value of 88.2 & a context size of 168K, we will be releasing an API for Researchers, Enterprises, and potential Partners by January 2024 end. If interested, please reach out to jithinvg@bud.studio
### News 🔥🔥🔥
- [2024/01/09] We released **Code Millenials 3B** , which achieves the **56.09 pass@1** on the [HumanEval Benchmarks](https://github.com/openai/human-eval).
- [2024/01/09] We released **Code Millenials 1B** , which achieves the **51.82 pass@1** on the [HumanEval Benchmarks](https://github.com/openai/human-eval).
- [2024/01/03] We released **Code Millenials 34B** , which achieves the **80.48 pass@1** on the [HumanEval Benchmarks](https://github.com/openai/human-eval).
- [2024/01/02] We released **Code Millenials 13B** , which achieves the **76.21 pass@1** on the [HumanEval Benchmarks](https://github.com/openai/human-eval).
### HumanEval
<p align="center" width="100%">
<a ><img src="https://raw.githubusercontent.com/BudEcosystem/code-millenials/main/assets/result.png" alt="CodeMillenials" style="width: 100%; min-width: 300px; display: block; margin: auto;"></a>
</p>
For the millenial models, the eval script in the github repo is used for the above result.
Note: The humaneval values of other models are taken from the official repos of [WizardCoder](https://github.com/nlpxucan/WizardLM), [DeepseekCoder](https://github.com/deepseek-ai/deepseek-coder), [Gemini](https://deepmind.google/technologies/gemini/#capabilities) etc.
### Models
| Model | Checkpoint | HumanEval (+) | MBPP (+) |
|---------|-------------|---------------|----------|
|Code Millenials 34B | <a href="https://huggingface.co/budecosystem/code-millenials-34b" target="_blank">HF Link</a> | 80.48 (75) | 74.68 (62.9) |
|Code Millenials 13B | <a href="https://huggingface.co/budecosystem/code-millenials-13b" target="_blank">HF Link</a> | 76.21 (69.5) | 70.17 (57.6) |
|Code Millenials 3B | <a href="https://huggingface.co/budecosystem/code-millenials-3b" target="_blank">HF Link</a> | 56.09 (52.43) | 55.13 (47.11) |
|Code Millenials 1B | <a href="https://huggingface.co/budecosystem/code-millenials-1b" target="_blank">HF Link</a> | 51.82 (48.17) | 53.13 (44.61) |
### 🚀 Quick Start
Inference code using the pre-trained model from the Hugging Face model hub
```python
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("budecosystem/code-millenials-13b")
model = AutoModelForCausalLM.from_pretrained("budecosystem/code-millenials-13b")
template = """A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.
### Instruction: {instruction} ### Response:"""
instruction = <Your code instruction here>
prompt = template.format(instruction=instruction)
inputs = tokenizer(prompt, return_tensors="pt")
sample = model.generate(**inputs, max_length=128)
print(tokenizer.decode(sample[0]))
```
## Training details
The model is trained of 8 A100 80GB for approximately 15hrs.
| Hyperparameters | Value |
| :----------------------------| :-----: |
| per_device_train_batch_size | 2 |
| gradient_accumulation_steps | 1 |
| epoch | 3 |
| steps | 34503 |
| learning_rate | 2e-5 |
| lr schedular type | cosine |
| warmup ratio | 0.1 |
| optimizer | adamw |
| fp16 | True |
| GPU | 8 A100 80GB |
### Important Note
- **Bias, Risks, and Limitations:** Model may sometimes make errors, produce misleading contents, or struggle to manage tasks that are not related to coding.
|
TheBloke/OrcaMaid-v3-13B-32k-GGUF
|
TheBloke
| 2024-01-10T08:48:26Z | 258 | 15 |
transformers
|
[
"transformers",
"gguf",
"llama",
"text-generation",
"base_model:ddh0/OrcaMaid-v3-13b-32k",
"base_model:quantized:ddh0/OrcaMaid-v3-13b-32k",
"license:other",
"region:us"
] |
text-generation
| 2024-01-10T00:39:53Z |
---
base_model: ddh0/OrcaMaid-v3-13b-32k
inference: false
license: other
license_link: https://huggingface.co/microsoft/Orca-2-13b/blob/main/LICENSE
license_name: microsoft-research-license
model_creator: ddh0
model_name: Orcamaid v3 13B 32K
model_type: llama
pipeline_tag: text-generation
prompt_template: 'Below is an instruction that describes a task. Write a response
that appropriately completes the request.
### Instruction:
{prompt}
### Response:
'
quantized_by: TheBloke
---
<!-- markdownlint-disable MD041 -->
<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->
# Orcamaid v3 13B 32K - GGUF
- Model creator: [ddh0](https://huggingface.co/ddh0)
- Original model: [Orcamaid v3 13B 32K](https://huggingface.co/ddh0/OrcaMaid-v3-13b-32k)
<!-- description start -->
## Description
This repo contains GGUF format model files for [ddh0's Orcamaid v3 13B 32K](https://huggingface.co/ddh0/OrcaMaid-v3-13b-32k).
These files were quantised using hardware kindly provided by [Massed Compute](https://massedcompute.com/).
<!-- description end -->
<!-- README_GGUF.md-about-gguf start -->
### About GGUF
GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp.
Here is an 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.
* [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.
* [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.
* [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.
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
* [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use.
* [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.
<!-- README_GGUF.md-about-gguf end -->
<!-- repositories-available start -->
## Repositories available
* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/OrcaMaid-v3-13B-32k-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/OrcaMaid-v3-13B-32k-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/OrcaMaid-v3-13B-32k-GGUF)
* [ddh0's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/ddh0/OrcaMaid-v3-13b-32k)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: Alpaca
```
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{prompt}
### Response:
```
<!-- prompt-template end -->
<!-- licensing start -->
## Licensing
The creator of the source model has listed its license as `other`, and this quantization has therefore used that same license.
As this model is based on Llama 2, it is also subject to the Meta Llama 2 license terms, and the license files for that are additionally included. It should therefore be considered as being claimed to be licensed under both licenses. I contacted Hugging Face for clarification on dual licensing but they do not yet have an official position. Should this change, or should Meta provide any feedback on this situation, I will update this section accordingly.
In the meantime, any questions regarding licensing, and in particular how these two licenses might interact, should be directed to the original model repository: [ddh0's Orcamaid v3 13B 32K](https://huggingface.co/ddh0/OrcaMaid-v3-13b-32k).
<!-- licensing end -->
<!-- compatibility_gguf start -->
## Compatibility
These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221)
They are also compatible with many third party UIs and libraries - please see the list at the top of this README.
## Explanation of quantisation methods
<details>
<summary>Click to see details</summary>
The new methods available are:
* GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
* GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
* GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
* GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
* GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
Refer to the Provided Files table below to see what files use which methods, and how.
</details>
<!-- compatibility_gguf end -->
<!-- README_GGUF.md-provided-files start -->
## Provided files
| Name | Quant method | Bits | Size | Max RAM required | Use case |
| ---- | ---- | ---- | ---- | ---- | ----- |
| [orcamaid-v3-13b-32k.Q2_K.gguf](https://huggingface.co/TheBloke/OrcaMaid-v3-13B-32k-GGUF/blob/main/orcamaid-v3-13b-32k.Q2_K.gguf) | Q2_K | 2 | 5.43 GB| 7.93 GB | smallest, significant quality loss - not recommended for most purposes |
| [orcamaid-v3-13b-32k.Q3_K_S.gguf](https://huggingface.co/TheBloke/OrcaMaid-v3-13B-32k-GGUF/blob/main/orcamaid-v3-13b-32k.Q3_K_S.gguf) | Q3_K_S | 3 | 5.66 GB| 8.16 GB | very small, high quality loss |
| [orcamaid-v3-13b-32k.Q3_K_M.gguf](https://huggingface.co/TheBloke/OrcaMaid-v3-13B-32k-GGUF/blob/main/orcamaid-v3-13b-32k.Q3_K_M.gguf) | Q3_K_M | 3 | 6.34 GB| 8.84 GB | very small, high quality loss |
| [orcamaid-v3-13b-32k.Q3_K_L.gguf](https://huggingface.co/TheBloke/OrcaMaid-v3-13B-32k-GGUF/blob/main/orcamaid-v3-13b-32k.Q3_K_L.gguf) | Q3_K_L | 3 | 6.93 GB| 9.43 GB | small, substantial quality loss |
| [orcamaid-v3-13b-32k.Q4_0.gguf](https://huggingface.co/TheBloke/OrcaMaid-v3-13B-32k-GGUF/blob/main/orcamaid-v3-13b-32k.Q4_0.gguf) | Q4_0 | 4 | 7.37 GB| 9.87 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [orcamaid-v3-13b-32k.Q4_K_S.gguf](https://huggingface.co/TheBloke/OrcaMaid-v3-13B-32k-GGUF/blob/main/orcamaid-v3-13b-32k.Q4_K_S.gguf) | Q4_K_S | 4 | 7.41 GB| 9.91 GB | small, greater quality loss |
| [orcamaid-v3-13b-32k.Q4_K_M.gguf](https://huggingface.co/TheBloke/OrcaMaid-v3-13B-32k-GGUF/blob/main/orcamaid-v3-13b-32k.Q4_K_M.gguf) | Q4_K_M | 4 | 7.87 GB| 10.37 GB | medium, balanced quality - recommended |
| [orcamaid-v3-13b-32k.Q5_0.gguf](https://huggingface.co/TheBloke/OrcaMaid-v3-13B-32k-GGUF/blob/main/orcamaid-v3-13b-32k.Q5_0.gguf) | Q5_0 | 5 | 8.97 GB| 11.47 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [orcamaid-v3-13b-32k.Q5_K_S.gguf](https://huggingface.co/TheBloke/OrcaMaid-v3-13B-32k-GGUF/blob/main/orcamaid-v3-13b-32k.Q5_K_S.gguf) | Q5_K_S | 5 | 8.97 GB| 11.47 GB | large, low quality loss - recommended |
| [orcamaid-v3-13b-32k.Q5_K_M.gguf](https://huggingface.co/TheBloke/OrcaMaid-v3-13B-32k-GGUF/blob/main/orcamaid-v3-13b-32k.Q5_K_M.gguf) | Q5_K_M | 5 | 9.23 GB| 11.73 GB | large, very low quality loss - recommended |
| [orcamaid-v3-13b-32k.Q6_K.gguf](https://huggingface.co/TheBloke/OrcaMaid-v3-13B-32k-GGUF/blob/main/orcamaid-v3-13b-32k.Q6_K.gguf) | Q6_K | 6 | 10.68 GB| 13.18 GB | very large, extremely low quality loss |
| [orcamaid-v3-13b-32k.Q8_0.gguf](https://huggingface.co/TheBloke/OrcaMaid-v3-13B-32k-GGUF/blob/main/orcamaid-v3-13b-32k.Q8_0.gguf) | Q8_0 | 8 | 13.83 GB| 16.33 GB | very large, extremely low quality loss - not recommended |
**Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
<!-- README_GGUF.md-provided-files end -->
<!-- README_GGUF.md-how-to-download start -->
## How to download GGUF files
**Note for manual downloaders:** You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.
The following clients/libraries will automatically download models for you, providing a list of available models to choose from:
* LM Studio
* LoLLMS Web UI
* Faraday.dev
### In `text-generation-webui`
Under Download Model, you can enter the model repo: TheBloke/OrcaMaid-v3-13B-32k-GGUF and below it, a specific filename to download, such as: orcamaid-v3-13b-32k.Q4_K_M.gguf.
Then click Download.
### On the command line, including multiple files at once
I recommend using the `huggingface-hub` Python library:
```shell
pip3 install huggingface-hub
```
Then you can download any individual model file to the current directory, at high speed, with a command like this:
```shell
huggingface-cli download TheBloke/OrcaMaid-v3-13B-32k-GGUF orcamaid-v3-13b-32k.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
<details>
<summary>More advanced huggingface-cli download usage (click to read)</summary>
You can also download multiple files at once with a pattern:
```shell
huggingface-cli download TheBloke/OrcaMaid-v3-13B-32k-GGUF --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'
```
For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
```shell
pip3 install hf_transfer
```
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
```shell
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/OrcaMaid-v3-13B-32k-GGUF orcamaid-v3-13b-32k.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
</details>
<!-- README_GGUF.md-how-to-download end -->
<!-- README_GGUF.md-how-to-run start -->
## Example `llama.cpp` command
Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
```shell
./main -ngl 35 -m orcamaid-v3-13b-32k.Q4_K_M.gguf --color -c 32768 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\n{prompt}\n\n### Response:"
```
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
Change `-c 32768` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically. Note that longer sequence lengths require much more resources, so you may need to reduce this value.
If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)
## How to run in `text-generation-webui`
Further instructions can be found in the text-generation-webui documentation, here: [text-generation-webui/docs/04 ‐ Model Tab.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/04%20%E2%80%90%20Model%20Tab.md#llamacpp).
## How to run from Python code
You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries. Note that at the time of writing (Nov 27th 2023), ctransformers has not been updated for some time and is not compatible with some recent models. Therefore I recommend you use llama-cpp-python.
### How to load this model in Python code, using llama-cpp-python
For full documentation, please see: [llama-cpp-python docs](https://abetlen.github.io/llama-cpp-python/).
#### First install the package
Run one of the following commands, according to your system:
```shell
# Base ctransformers with no GPU acceleration
pip install llama-cpp-python
# With NVidia CUDA acceleration
CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install llama-cpp-python
# Or with OpenBLAS acceleration
CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS" pip install llama-cpp-python
# Or with CLBLast acceleration
CMAKE_ARGS="-DLLAMA_CLBLAST=on" pip install llama-cpp-python
# Or with AMD ROCm GPU acceleration (Linux only)
CMAKE_ARGS="-DLLAMA_HIPBLAS=on" pip install llama-cpp-python
# Or with Metal GPU acceleration for macOS systems only
CMAKE_ARGS="-DLLAMA_METAL=on" pip install llama-cpp-python
# In windows, to set the variables CMAKE_ARGS in PowerShell, follow this format; eg for NVidia CUDA:
$env:CMAKE_ARGS = "-DLLAMA_OPENBLAS=on"
pip install llama-cpp-python
```
#### Simple llama-cpp-python example code
```python
from llama_cpp import Llama
# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
llm = Llama(
model_path="./orcamaid-v3-13b-32k.Q4_K_M.gguf", # Download the model file first
n_ctx=32768, # The max sequence length to use - note that longer sequence lengths require much more resources
n_threads=8, # The number of CPU threads to use, tailor to your system and the resulting performance
n_gpu_layers=35 # The number of layers to offload to GPU, if you have GPU acceleration available
)
# Simple inference example
output = llm(
"Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\n{prompt}\n\n### Response:", # Prompt
max_tokens=512, # Generate up to 512 tokens
stop=["</s>"], # Example stop token - not necessarily correct for this specific model! Please check before using.
echo=True # Whether to echo the prompt
)
# Chat Completion API
llm = Llama(model_path="./orcamaid-v3-13b-32k.Q4_K_M.gguf", chat_format="llama-2") # Set chat_format according to the model you are using
llm.create_chat_completion(
messages = [
{"role": "system", "content": "You are a story writing assistant."},
{
"role": "user",
"content": "Write a story about llamas."
}
]
)
```
## How to use with LangChain
Here are guides on using llama-cpp-python and ctransformers with LangChain:
* [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp)
* [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers)
<!-- README_GGUF.md-how-to-run end -->
<!-- footer start -->
<!-- 200823 -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute
Thanks to the [chirper.ai](https://chirper.ai) team!
Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Aemon Algiz.
**Patreon special mentions**: Michael Levine, 阿明, Trailburnt, Nikolai Manek, John Detwiler, Randy H, Will Dee, Sebastain Graf, NimbleBox.ai, Eugene Pentland, Emad Mostaque, Ai Maven, Jim Angel, Jeff Scroggin, Michael Davis, Manuel Alberto Morcote, Stephen Murray, Robert, Justin Joy, Luke @flexchar, Brandon Frisco, Elijah Stavena, S_X, Dan Guido, Undi ., Komninos Chatzipapas, Shadi, theTransient, Lone Striker, Raven Klaugh, jjj, Cap'n Zoog, Michel-Marie MAUDET (LINAGORA), Matthew Berman, David, Fen Risland, Omer Bin Jawed, Luke Pendergrass, Kalila, OG, Erik Bjäreholt, Rooh Singh, Joseph William Delisle, Dan Lewis, TL, John Villwock, AzureBlack, Brad, Pedro Madruga, Caitlyn Gatomon, K, jinyuan sun, Mano Prime, Alex, Jeffrey Morgan, Alicia Loh, Illia Dulskyi, Chadd, transmissions 11, fincy, Rainer Wilmers, ReadyPlayerEmma, knownsqashed, Mandus, biorpg, Deo Leter, Brandon Phillips, SuperWojo, Sean Connelly, Iucharbius, Jack West, Harry Royden McLaughlin, Nicholas, terasurfer, Vitor Caleffi, Duane Dunston, Johann-Peter Hartmann, David Ziegler, Olakabola, Ken Nordquist, Trenton Dambrowitz, Tom X Nguyen, Vadim, Ajan Kanaga, Leonard Tan, Clay Pascal, Alexandros Triantafyllidis, JM33133, Xule, vamX, ya boyyy, subjectnull, Talal Aujan, Alps Aficionado, wassieverse, Ari Malik, James Bentley, Woland, Spencer Kim, Michael Dempsey, Fred von Graf, Elle, zynix, William Richards, Stanislav Ovsiannikov, Edmond Seymore, Jonathan Leane, Martin Kemka, usrbinkat, Enrico Ros
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
<!-- footer end -->
<!-- original-model-card start -->
# Original model card: ddh0's Orcamaid v3 13B 32K
# OrcaMaid-v3-13b-32k
This is the third version of OrcaMaid, a weighted gradient SLERP merge between Microsoft's [Orca-2-13b](https://huggingface.co/microsoft/Orca-2-13b) and NeverSleep's [Noromaid-13b-v0.3](https://huggingface.co/NeverSleep/Noromaid-13b-v0.3).
The goal of this merge is to create an unusually intelligent and human-like model especially for RP.
The prompt format is Alpaca. You can use the standard format as shown, but for best results, you should customize the system prompt to your specific needs.
```
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{YOUR MESSAGE HERE}
### Response:
{BOT MESSAGE HERE}
```
### Misc. information
- BOS token is `<s>`
- EOS token is `</s>`
- Native context length is `32768` via YaRN (original context length was `4096`)
- Base model is Llama 2
- Due to the inclusion of Orca-2-13b, the model is subject to the terms of the [Microsoft Research License](https://huggingface.co/microsoft/Orca-2-13b/blob/main/LICENSE)
### Thanks
- Thanks to [Undi](https://ko-fi.com/undiai) and [IkariDev](https://ikaridevgit.github.io/) of [NeverSleep](https://huggingface.co/NeverSleep) for Noromaid
<!-- original-model-card end -->
|
Brackly/alpaca-lora-7b
|
Brackly
| 2024-01-10T08:44:18Z | 0 | 0 | null |
[
"dataset:yahma/alpaca-cleaned",
"license:mit",
"region:us"
] | null | 2024-01-10T08:38:27Z |
---
license: mit
datasets:
- yahma/alpaca-cleaned
---
This repo contains a low-rank adapter for LLaMA-7b
fit on the [Stanford Alpaca](https://github.com/tatsu-lab/stanford_alpaca) dataset.
This version of the weights was trained with the following hyperparameters:
- Epochs: 10 (load from best epoch)
- Batch size: 128
- Cutoff length: 512
- Learning rate: 3e-4
- Lora _r_: 16
- Lora target modules: q_proj, k_proj, v_proj, o_proj
That is:
```
python finetune.py \
--base_model='decapoda-research/llama-7b-hf' \
--num_epochs=10 \
--cutoff_len=512 \
--group_by_length \
--output_dir='./lora-alpaca-512-qkvo' \
--lora_target_modules='[q_proj,k_proj,v_proj,o_proj]' \
--lora_r=16 \
--micro_batch_size=8
```
Instructions for running it can be found at https://github.com/tloen/alpaca-lora.
|
mschuh/PubChemDeBERTa
|
mschuh
| 2024-01-10T08:39:08Z | 176 | 1 |
transformers
|
[
"transformers",
"pytorch",
"deberta-v2",
"feature-extraction",
"PubChem",
"chemistry",
"biology",
"deberta-v3",
"sentence-similarity",
"en",
"arxiv:2401.04478",
"endpoints_compatible",
"region:us"
] |
sentence-similarity
| 2023-08-07T08:57:06Z |
---
language:
- en
metrics:
- perplexity
pipeline_tag: sentence-similarity
author: Maximilian G. Schuh
tags:
- PubChem
- chemistry
- biology
- deberta-v3
---
# TwinBooster
## PubChemDeBERTa: Fine-tuned DeBERTa V3 base on PubChem bioassay corpora
[](https://arxiv.org/abs/2401.04478)
### Synergising Large Language Models with Barlow Twins and Gradient Boosting for Enhanced Molecular Property Prediction
Maximilian G. Schuh, Davide Boldini, Stephan A. Sieber
@ Chair of Organic Chemistry II,
TUM School of Natural Sciences,
Technical University of Munich
**Abstract**
The success of drug discovery and development relies on the precise prediction of molecular activities and properties. While in silico molecular property prediction has shown remarkable potential, its use has been limited so far to assays for which large amounts of data are available. In this study, we use a fine-tuned large language model to integrate biological assays based on their textual information, coupled with Barlow Twins, a Siamese neural network using a novel self-supervised learning approach. This architecture uses both assay information and molecular fingerprints to extract the true molecular information. TwinBooster enables the prediction of properties of unseen bioassays and molecules by providing state-of-the-art zero-shot learning tasks. Remarkably, our artificial intelligence pipeline shows excellent performance on the FS-Mol benchmark. This breakthrough demonstrates the application of deep learning to critical property prediction tasks where data is typically scarce. By accelerating the early identification of active molecules in drug discovery and development, this method has the potential to help streamline the identification of novel therapeutics.
|
haryoaw/scenario-TCR-data-glue-cola-model-bert-base-uncased
|
haryoaw
| 2024-01-10T08:30:45Z | 93 | 0 |
transformers
|
[
"transformers",
"safetensors",
"bert",
"text-classification",
"generated_from_trainer",
"base_model:google-bert/bert-base-uncased",
"base_model:finetune:google-bert/bert-base-uncased",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-12-29T21:06:09Z |
---
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
metrics:
- matthews_correlation
model-index:
- name: scenario-TCR-data-glue-cola-model-bert-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. -->
# scenario-TCR-data-glue-cola-model-bert-base-uncased
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.9233
- Matthews Correlation: 0.5556
## 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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 6969
### Training results
| Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
|:-------------:|:-----:|:----:|:---------------:|:--------------------:|
| No log | 1.0 | 268 | 0.4170 | 0.5507 |
| 0.3968 | 2.0 | 536 | 0.4077 | 0.5769 |
| 0.3968 | 3.0 | 804 | 0.6058 | 0.5667 |
| 0.1661 | 4.0 | 1072 | 0.8344 | 0.5396 |
| 0.1661 | 5.0 | 1340 | 0.7354 | 0.5402 |
| 0.1119 | 6.0 | 1608 | 0.7466 | 0.5593 |
| 0.1119 | 7.0 | 1876 | 0.9233 | 0.5556 |
### Framework versions
- Transformers 4.36.2
- Pytorch 2.1.2
- Datasets 2.16.0
- Tokenizers 0.15.0
|
ImPikov/game-character-v2
|
ImPikov
| 2024-01-10T08:18:52Z | 424 | 1 |
diffusers
|
[
"diffusers",
"text-to-image",
"stable-diffusion",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] |
text-to-image
| 2024-01-10T08:14:39Z |
---
license: creativeml-openrail-m
tags:
- text-to-image
- stable-diffusion
---
### Game_Character_v2 Dreambooth model trained by ImPikov with [TheLastBen's fast-DreamBooth](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast-DreamBooth.ipynb) notebook
Test the concept via A1111 Colab [fast-Colab-A1111](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast_stable_diffusion_AUTOMATIC1111.ipynb)
Sample pictures of this concept:
|
magixn/ppo-Huggy
|
magixn
| 2024-01-10T08:09:00Z | 12 | 0 |
ml-agents
|
[
"ml-agents",
"tensorboard",
"onnx",
"Huggy",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-Huggy",
"region:us"
] |
reinforcement-learning
| 2024-01-10T08:08:53Z |
---
library_name: ml-agents
tags:
- Huggy
- deep-reinforcement-learning
- reinforcement-learning
- ML-Agents-Huggy
---
# **ppo** Agent playing **Huggy**
This is a trained model of a **ppo** agent playing **Huggy**
using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
## Usage (with ML-Agents)
The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
- A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
- A *longer tutorial* to understand how works ML-Agents:
https://huggingface.co/learn/deep-rl-course/unit5/introduction
### Resume the training
```bash
mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
```
### Watch your Agent play
You can watch your agent **playing directly in your browser**
1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
2. Step 1: Find your model_id: magixn/ppo-Huggy
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
zym1/lora
|
zym1
| 2024-01-10T07:54:56Z | 0 | 1 | null |
[
"safetensors",
"region:us"
] | null | 2023-07-18T07:13:01Z |
---
license: cc-by-4.0
---个人的Lora模型，主要为《战舰少女R》中的人物。
|
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.