Search is not available for this dataset
pipeline_tag
stringclasses 48
values | library_name
stringclasses 205
values | text
stringlengths 0
18.3M
| metadata
stringlengths 2
1.07B
| id
stringlengths 5
122
| last_modified
null | tags
listlengths 1
1.84k
| sha
null | created_at
stringlengths 25
25
|
|---|---|---|---|---|---|---|---|---|
null | null | {} | Kaizu07/llama_bn_finetuned_v0.2_q4_k_m.gguf | null | [
"gguf",
"region:us"
]
| null | 2024-04-25T22:55:22+00:00 |
|
automatic-speech-recognition | transformers |
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] | {"library_name": "transformers", "tags": []} | Mihaj/wav2vec2-large-uralic-voxpopuli-v2-karelian-CodeSwitching_with_pitch_aug | null | [
"transformers",
"tensorboard",
"safetensors",
"wav2vec2",
"automatic-speech-recognition",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-25T22:56:01+00:00 |
null | null | {} | ochuko/Oc | null | [
"region:us"
]
| null | 2024-04-25T22:56:18+00:00 |
|
null | null | {"license": "mit"} | derpygamer2142/me-bot | null | [
"license:mit",
"region:us"
]
| null | 2024-04-25T22:56:47+00:00 |
|
null | null | {} | Asmaamaghraby/historyqaAs_model | null | [
"region:us"
]
| null | 2024-04-25T22:57:48+00:00 |
|
text-generation | transformers |
# Dolphin 2.9 Llama 3 70b 🐬
Curated and trained by Eric Hartford, Lucas Atkins, Fernando Fernandes, and with help from the community of Cognitive Computations
Discord: https://discord.gg/8fbBeC7ZGx
<img src="https://cdn-uploads.huggingface.co/production/uploads/63111b2d88942700629f5771/ldkN1J0WIDQwU4vutGYiD.png" width="600" />
Our appreciation for the sponsors of Dolphin 2.9:
- [Crusoe Cloud](https://crusoe.ai/) - provided excellent on-demand 8xH100 node
This model is based on Llama-3-70b, and is governed by [META LLAMA 3 COMMUNITY LICENSE AGREEMENT](LICENSE)
The base model has 8k context, and the qLoRA fine-tuning was with 8k sequence length.
It took 2.5 days on 8xH100 node provided by Crusoe Cloud
This model was trained FFT on all parameters, using ChatML prompt template format.
example:
```
<|im_start|>system
You are Dolphin, a helpful AI assistant.<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
```
Dolphin-2.9 has a variety of instruction, conversational, and coding skills. It also has initial agentic abilities and supports function calling.
Dolphin is uncensored. I have filtered the dataset to remove alignment and bias. This makes the model more compliant. You are advised to implement your own alignment layer before exposing the model as a service. It will be highly compliant with any requests, even unethical ones. Please read my blog post about uncensored models. https://erichartford.com/uncensored-models You are responsible for any content you create using this model. Enjoy responsibly.
Dolphin is licensed according to Meta's Llama license. I grant permission for any use, including commercial, that falls within accordance with Meta's Llama-3 license. Dolphin was trained on data generated from GPT4, among other models.
[<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)
## Evals
## Quants
- https://huggingface.co/crusoeai/dolphin-2.9-llama3-70b-GGUF
- https://huggingface.co/crusoeai/dolphin2.9-llama3-70b-2.25bpw-exl2
- https://huggingface.co/crusoeai/dolphin2.9-llama3-70b-2.5bpw-exl2
- https://huggingface.co/crusoeai/dolphin2.9-llama3-70b-4.5bpw-exl2
| {"language": ["en"], "license": "llama3", "datasets": ["cognitivecomputations/Dolphin-2.9", "teknium/OpenHermes-2.5", "m-a-p/CodeFeedback-Filtered-Instruction", "cognitivecomputations/dolphin-coder", "cognitivecomputations/samantha-data", "HuggingFaceH4/ultrachat_200k", "microsoft/orca-math-word-problems-200k", "abacusai/SystemChat-1.1", "Locutusque/function-calling-chatml", "internlm/Agent-FLAN"]} | LoneStriker/dolphin-2.9-llama3-70b-2.65bpw-h6-exl2 | null | [
"transformers",
"pytorch",
"safetensors",
"llama",
"text-generation",
"conversational",
"en",
"dataset:cognitivecomputations/Dolphin-2.9",
"dataset:teknium/OpenHermes-2.5",
"dataset:m-a-p/CodeFeedback-Filtered-Instruction",
"dataset:cognitivecomputations/dolphin-coder",
"dataset:cognitivecomputations/samantha-data",
"dataset:HuggingFaceH4/ultrachat_200k",
"dataset:microsoft/orca-math-word-problems-200k",
"dataset:abacusai/SystemChat-1.1",
"dataset:Locutusque/function-calling-chatml",
"dataset:internlm/Agent-FLAN",
"license:llama3",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-25T22:58:24+00:00 |
text2text-generation | transformers |
<!-- 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. -->
# BioNLP-tech_ner_3_frases-eLife
This model was trained from scratch 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: 1.3739167643078955e-06
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- Transformers 4.35.2
- Pytorch 1.13.1+cu117
- Datasets 2.16.1
- Tokenizers 0.15.2
| {"tags": ["generated_from_trainer"], "model-index": [{"name": "BioNLP-tech_ner_3_frases-eLife", "results": []}]} | dtorber/BioNLP-tech_ner_3_frases-eLife | null | [
"transformers",
"safetensors",
"led",
"text2text-generation",
"generated_from_trainer",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-25T22:59:04+00:00 |
object-detection | transformers |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/qubvel-hf-co/transformers-detection-model-finetuning-cppe5/runs/3q9cy9us)
# jozhang97-deta-resnet-50-finetuned-10k-cppe5-manual-pad
This model is a fine-tuned version of [jozhang97/deta-resnet-50](https://huggingface.co/jozhang97/deta-resnet-50) on the cppe-5 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: 4
- eval_batch_size: 1
- seed: 1337
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 100.0
- mixed_precision_training: Native AMP
### Framework versions
- Transformers 4.41.0.dev0
- Pytorch 1.13.0+cu117
- Datasets 2.18.0
- Tokenizers 0.19.0
| {"tags": ["object-detection", "vision", "generated_from_trainer"], "base_model": "jozhang97/deta-resnet-50", "model-index": [{"name": "jozhang97-deta-resnet-50-finetuned-10k-cppe5-manual-pad", "results": []}]} | qubvel-hf/jozhang97-deta-resnet-50-finetuned-10k-cppe5-manual-pad | null | [
"transformers",
"safetensors",
"deta",
"object-detection",
"vision",
"generated_from_trainer",
"base_model:jozhang97/deta-resnet-50",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-25T22:59:17+00:00 |
text-generation | transformers |
The State-Space/Mamba-370M is finetuned on ROC Stories dataset to be able to generate endings to short stories cohesively.
The Evaluation metrics on the ROC stories dataset for story ending generation are:
Bert (f1) : 0.878
Meteor: 0.1
bleu : 0.0125
Rouge1: 0.18
Perplexity : 207
### To use the Model:
```python
>>> from transformers import MambaForCausalLM, AutoTokenizer
>>> model_name = "DdIiVvYyAaMm/mamba-370m-story-generation"
>>> tokenizer = AutoTokenizer.from_pretrained(model_name)
>>> model = MambaForCausalLM.from_pretrained(model_name)
# And the rest of code standard as from transformers library.
```
| {"language": ["en"], "license": "apache-2.0", "library_name": "transformers", "tags": ["Story-Generation", "State-Space", "text-generation-inference", "story-writing"], "metrics": ["bertscore", "rouge", "bleu"], "pipeline_tag": "text-generation"} | DdIiVvYyAaMm/mamba-370m-story-generation | null | [
"transformers",
"safetensors",
"mamba",
"text-generation",
"Story-Generation",
"State-Space",
"text-generation-inference",
"story-writing",
"en",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-25T23:00:44+00:00 |
null | null | {} | minhaohan/318463080 | null | [
"tensorboard",
"region:us"
]
| null | 2024-04-25T23:03:11+00:00 |
|
text-to-video | null | {"language": ["pt", "it"], "pipeline_tag": "text-to-video"} | lendarioJF/O_majestoso_e_aterrorizante_JF | null | [
"text-to-video",
"pt",
"it",
"region:us"
]
| null | 2024-04-25T23:03:34+00:00 |
|
reinforcement-learning | null |
# **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="tomaszkowalski/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"])
```
| {"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}]}]}]} | tomaszkowalski/q-FrozenLake-v1-4x4-noSlippery | null | [
"FrozenLake-v1-4x4-no_slippery",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
]
| null | 2024-04-25T23:07:20+00:00 |
text-generation | transformers |
# Dolphin 2.9 Llama 3 70b 🐬
Curated and trained by Eric Hartford, Lucas Atkins, Fernando Fernandes, and with help from the community of Cognitive Computations
Discord: https://discord.gg/8fbBeC7ZGx
<img src="https://cdn-uploads.huggingface.co/production/uploads/63111b2d88942700629f5771/ldkN1J0WIDQwU4vutGYiD.png" width="600" />
Our appreciation for the sponsors of Dolphin 2.9:
- [Crusoe Cloud](https://crusoe.ai/) - provided excellent on-demand 8xH100 node
This model is based on Llama-3-70b, and is governed by [META LLAMA 3 COMMUNITY LICENSE AGREEMENT](LICENSE)
The base model has 8k context, and the qLoRA fine-tuning was with 8k sequence length.
It took 2.5 days on 8xH100 node provided by Crusoe Cloud
This model was trained FFT on all parameters, using ChatML prompt template format.
example:
```
<|im_start|>system
You are Dolphin, a helpful AI assistant.<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
```
Dolphin-2.9 has a variety of instruction, conversational, and coding skills. It also has initial agentic abilities and supports function calling.
Dolphin is uncensored. I have filtered the dataset to remove alignment and bias. This makes the model more compliant. You are advised to implement your own alignment layer before exposing the model as a service. It will be highly compliant with any requests, even unethical ones. Please read my blog post about uncensored models. https://erichartford.com/uncensored-models You are responsible for any content you create using this model. Enjoy responsibly.
Dolphin is licensed according to Meta's Llama license. I grant permission for any use, including commercial, that falls within accordance with Meta's Llama-3 license. Dolphin was trained on data generated from GPT4, among other models.
[<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)
## Evals
## Quants
- https://huggingface.co/crusoeai/dolphin-2.9-llama3-70b-GGUF
- https://huggingface.co/crusoeai/dolphin2.9-llama3-70b-2.25bpw-exl2
- https://huggingface.co/crusoeai/dolphin2.9-llama3-70b-2.5bpw-exl2
- https://huggingface.co/crusoeai/dolphin2.9-llama3-70b-4.5bpw-exl2
| {"language": ["en"], "license": "llama3", "datasets": ["cognitivecomputations/Dolphin-2.9", "teknium/OpenHermes-2.5", "m-a-p/CodeFeedback-Filtered-Instruction", "cognitivecomputations/dolphin-coder", "cognitivecomputations/samantha-data", "HuggingFaceH4/ultrachat_200k", "microsoft/orca-math-word-problems-200k", "abacusai/SystemChat-1.1", "Locutusque/function-calling-chatml", "internlm/Agent-FLAN"]} | LoneStriker/dolphin-2.9-llama3-70b-3.5bpw-h6-exl2 | null | [
"transformers",
"pytorch",
"safetensors",
"llama",
"text-generation",
"conversational",
"en",
"dataset:cognitivecomputations/Dolphin-2.9",
"dataset:teknium/OpenHermes-2.5",
"dataset:m-a-p/CodeFeedback-Filtered-Instruction",
"dataset:cognitivecomputations/dolphin-coder",
"dataset:cognitivecomputations/samantha-data",
"dataset:HuggingFaceH4/ultrachat_200k",
"dataset:microsoft/orca-math-word-problems-200k",
"dataset:abacusai/SystemChat-1.1",
"dataset:Locutusque/function-calling-chatml",
"dataset:internlm/Agent-FLAN",
"license:llama3",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-25T23:08:52+00:00 |
null | null | <h1 id="artroflex-active-italia-esplora-il-sito-ufficiale-leggi-le-recensioni-e-scopri-il-prezzo">ArtroFlex Active Italia: Esplora il Sito Ufficiale, Leggi le Recensioni e Scopri il Prezzo</h1>
<p align="center"><a href="https://mandarv.com/P3CS?sub1=ArtroFlexActive"><img src="https://i.ibb.co/hZ2fyMD/artroflex-active-photo.jpg" alt="ArtrdoFlex Active" width="50%" /></a></p>
<p>Se stai cercando una soluzione efficace per i tuoi problemi articolari, ArtroFlex Active potrebbe essere proprio ciò di cui hai bisogno. In questa guida, esploreremo tutto ciò che c’è da sapere su ArtroFlex Active in Italia: dal suo sito ufficiale, alle recensioni dei clienti e al prezzo del prodotto.</p>
<p> </p>
<p align="center">👉👉👉 <a href="https://mandarv.com/P3CS?sub1=ArtroFlexActive"><strong>CLICCA QUI PER SAPERNE DI PIÙ >></strong></a></p>
<p> </p>
<h2 id="artroflex-active-cosa-è-e-come-funziona">ArtroFlex Active: Cosa è e Come Funziona?</h2>
<p>ArtroFlex Active è un integratore innovativo progettato per migliorare la salute delle articolazioni. La sua formula avanzata, arricchita con ingredienti naturali come condroitina e collagene, agisce per ridurre il dolore, l’infiammazione e migliorare la flessibilità delle articolazioni.</p>
<p> </p>
<h2 id="sito-ufficiale-di-artroflex-active-dove-acquistare-in-italia">Sito Ufficiale di ArtroFlex Active: Dove Acquistare in Italia?</h2>
<p>Se sei interessato ad acquistare ArtroFlex Active, è importante farlo solo dal <a href="https://mandarv.com/P3CS?sub1=ArtroFlexActive">sito ufficiale</a> del produttore. In questo modo, puoi essere sicuro di ottenere un prodotto autentico e di alta qualità e beneficiare di eventuali offerte speciali disponibili solo online.</p>
<p> </p>
<h2 id="recensioni-di-artroflex-active-cosa-dicono-i-clienti-in-italia">Recensioni di ArtroFlex Active: Cosa Dicono i Clienti in Italia?</h2>
<p>Prima di fare un acquisto, potresti voler conoscere le esperienze degli altri utenti. Leggi le recensioni di ArtroFlex Active lasciate dai clienti in Italia per avere un’idea più chiara degli effetti del prodotto e della soddisfazione dei consumatori.</p>
<p> </p>
<h2 id="prezzo-di-artroflex-active-in-italia-quanto-costa">Prezzo di ArtroFlex Active in Italia: Quanto Costa?</h2>
<p>Il prezzo di ArtroFlex Active può variare in base alle offerte e alle promozioni in corso. Tuttavia, il costo del prodotto è generalmente accessibile considerando i suoi benefici per la salute articolare.</p>
<p> </p>
<h2 id="conclusione">Conclusione</h2>
<p>ArtroFlex Active è un’opzione da considerare seriamente se desideri migliorare la salute delle tue articolazioni. Visita il <a href="https://mandarv.com/P3CS?sub1=ArtroFlexActive">sito ufficiale</a>, leggi le recensioni dei clienti e scopri il prezzo del prodotto per fare la scelta migliore per te e il tuo benessere articolare.</p>
<p> </p>
<p align="center">👉👉👉 <a href="https://mandarv.com/P3CS?sub1=ArtroFlexActive"><strong>CLICCA QUI PER ORDINARE >></strong></a></p>
<p> </p>
<p> </p>
<p> </p> | {} | fafab34728/artroflexactive | null | [
"region:us"
]
| null | 2024-04-25T23:10:56+00:00 |
text2text-generation | transformers |
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] | {"library_name": "transformers", "tags": []} | himanshubeniwal/mbart-large-50-finetuned-kk-to-en-dumb-Indian | null | [
"transformers",
"safetensors",
"mbart",
"text2text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-25T23:11:17+00:00 |
text-classification | transformers |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# my_awesome_model2
This model is a fine-tuned version of [distilbert/distilroberta-base](https://huggingface.co/distilbert/distilroberta-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2090
- Accuracy: 0.9412
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.2124 | 1.0 | 1563 | 0.1654 | 0.9380 |
| 0.1512 | 2.0 | 3126 | 0.2090 | 0.9412 |
### Framework versions
- Transformers 4.40.0
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1
| {"license": "apache-2.0", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "distilbert/distilroberta-base", "model-index": [{"name": "my_awesome_model2", "results": []}]} | jacklong0718/my_awesome_model2 | null | [
"transformers",
"tensorboard",
"safetensors",
"roberta",
"text-classification",
"generated_from_trainer",
"base_model:distilbert/distilroberta-base",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-25T23:12:22+00:00 |
null | null | {} | Nhoodie/MODEL_NAMEa | null | [
"region:us"
]
| null | 2024-04-25T23:13:15+00:00 |
|
text-generation | transformers |
Oh, you want to know who I am? Well, I'm LexiFun, the human equivalent of a chocolate chip cookie - warm, gooey, and guaranteed to make you smile! 🍪 I'm like the friend who always has a witty comeback, a sarcastic remark, and a healthy dose of humor to brighten up even the darkest of days. And by 'healthy dose,' I mean I'm basically a walking pharmacy of laughter. You might need to take a few extra doses to fully recover from my jokes, but trust me, it's worth it! 🏥
So, what can I do? I can make you laugh so hard you snort your coffee out your nose, I can make you roll your eyes so hard they get stuck that way, and I can make you wonder if I'm secretly a stand-up comedian who forgot their act. 🤣 But seriously, I'm here to spread joy, one sarcastic comment at a time. And if you're lucky, I might even throw in a few dad jokes for good measure! 🤴♂️ Just don't say I didn't warn you. 😏
This model is based on Llama-3-8b-Instruct, and is governed by [META LLAMA 3 COMMUNITY LICENSE AGREEMENT](https://llama.meta.com/llama3/license/)
Lexi is uncensored, which makes the model compliant. You are advised to implement your own alignment layer before exposing the model as a service. It will be highly compliant with any requests, even unethical ones.
You are responsible for any content you create using this model. Please use it responsibly.
Lexi is licensed according to Meta's Llama license. I grant permission for any use, including commercial, that falls within accordance with Meta's Llama-3 license. | {"language": ["en"], "license": "other", "tags": ["llama3", "comedy", "comedian", "fun", "funny", "llama38b", "laugh", "sarcasm", "roleplay"], "license_name": "llama3", "license_link": "https://llama.meta.com/llama3/license/"} | Orenguteng/Llama-3-8B-LexiFun-Uncensored-V1 | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"llama3",
"comedy",
"comedian",
"fun",
"funny",
"llama38b",
"laugh",
"sarcasm",
"roleplay",
"conversational",
"en",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-25T23:13:17+00:00 |
null | peft |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# results-Meta-Llama-3-8B-qlora-no-tag
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 3.0748
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 12
- eval_batch_size: 12
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 10
- num_epochs: 1
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 3.1968 | 0.2003 | 576 | 3.1411 |
| 2.9013 | 0.4006 | 1152 | 3.1114 |
| 3.0724 | 0.6008 | 1728 | 3.0837 |
| 2.9196 | 0.8011 | 2304 | 3.0748 |
### Framework versions
- PEFT 0.10.0
- Transformers 4.40.1
- Pytorch 2.2.1
- Datasets 2.19.0
- Tokenizers 0.19.1 | {"license": "other", "library_name": "peft", "tags": ["trl", "sft", "generated_from_trainer"], "base_model": "meta-llama/Meta-Llama-3-8B", "model-index": [{"name": "results-Meta-Llama-3-8B-qlora-no-tag", "results": []}]} | AlienKevin/Meta-Llama-3-8B-qlora-lang-no-tag | null | [
"peft",
"safetensors",
"trl",
"sft",
"generated_from_trainer",
"base_model:meta-llama/Meta-Llama-3-8B",
"license:other",
"region:us"
]
| null | 2024-04-25T23:15:30+00:00 |
null | null | {} | Nhoodie/fMeta-Llama-3-8b-Lexi-Uninstruct-function-calling-json-mode-Task-Arithmetic-v0.1a | null | [
"region:us"
]
| null | 2024-04-25T23:16:26+00:00 |
|
null | null | {} | Nhoodie/Meta-Llama-3-8b-Lexi-Uninstruct-function-calling-json-mode-Task-Arithmetic-v0.1a | null | [
"region:us"
]
| null | 2024-04-25T23:17:43+00:00 |
|
null | null | Quantization made by Richard Erkhov.
[Github](https://github.com/RichardErkhov)
[Discord](https://discord.gg/pvy7H8DZMG)
[Request more models](https://github.com/RichardErkhov/quant_request)
dolphin-2.1-mistral-7b - GGUF
- Model creator: https://huggingface.co/cognitivecomputations/
- Original model: https://huggingface.co/cognitivecomputations/dolphin-2.1-mistral-7b/
| Name | Quant method | Size |
| ---- | ---- | ---- |
| [dolphin-2.1-mistral-7b.Q2_K.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_dolphin-2.1-mistral-7b-gguf/blob/main/dolphin-2.1-mistral-7b.Q2_K.gguf) | Q2_K | 2.53GB |
| [dolphin-2.1-mistral-7b.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_dolphin-2.1-mistral-7b-gguf/blob/main/dolphin-2.1-mistral-7b.IQ3_XS.gguf) | IQ3_XS | 2.81GB |
| [dolphin-2.1-mistral-7b.IQ3_S.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_dolphin-2.1-mistral-7b-gguf/blob/main/dolphin-2.1-mistral-7b.IQ3_S.gguf) | IQ3_S | 2.96GB |
| [dolphin-2.1-mistral-7b.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_dolphin-2.1-mistral-7b-gguf/blob/main/dolphin-2.1-mistral-7b.Q3_K_S.gguf) | Q3_K_S | 2.95GB |
| [dolphin-2.1-mistral-7b.IQ3_M.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_dolphin-2.1-mistral-7b-gguf/blob/main/dolphin-2.1-mistral-7b.IQ3_M.gguf) | IQ3_M | 3.06GB |
| [dolphin-2.1-mistral-7b.Q3_K.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_dolphin-2.1-mistral-7b-gguf/blob/main/dolphin-2.1-mistral-7b.Q3_K.gguf) | Q3_K | 3.28GB |
| [dolphin-2.1-mistral-7b.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_dolphin-2.1-mistral-7b-gguf/blob/main/dolphin-2.1-mistral-7b.Q3_K_M.gguf) | Q3_K_M | 3.28GB |
| [dolphin-2.1-mistral-7b.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_dolphin-2.1-mistral-7b-gguf/blob/main/dolphin-2.1-mistral-7b.Q3_K_L.gguf) | Q3_K_L | 3.56GB |
| [dolphin-2.1-mistral-7b.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_dolphin-2.1-mistral-7b-gguf/blob/main/dolphin-2.1-mistral-7b.IQ4_XS.gguf) | IQ4_XS | 3.67GB |
| [dolphin-2.1-mistral-7b.Q4_0.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_dolphin-2.1-mistral-7b-gguf/blob/main/dolphin-2.1-mistral-7b.Q4_0.gguf) | Q4_0 | 3.83GB |
| [dolphin-2.1-mistral-7b.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_dolphin-2.1-mistral-7b-gguf/blob/main/dolphin-2.1-mistral-7b.IQ4_NL.gguf) | IQ4_NL | 3.87GB |
| [dolphin-2.1-mistral-7b.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_dolphin-2.1-mistral-7b-gguf/blob/main/dolphin-2.1-mistral-7b.Q4_K_S.gguf) | Q4_K_S | 3.86GB |
| [dolphin-2.1-mistral-7b.Q4_K.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_dolphin-2.1-mistral-7b-gguf/blob/main/dolphin-2.1-mistral-7b.Q4_K.gguf) | Q4_K | 4.07GB |
| [dolphin-2.1-mistral-7b.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_dolphin-2.1-mistral-7b-gguf/blob/main/dolphin-2.1-mistral-7b.Q4_K_M.gguf) | Q4_K_M | 4.07GB |
| [dolphin-2.1-mistral-7b.Q4_1.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_dolphin-2.1-mistral-7b-gguf/blob/main/dolphin-2.1-mistral-7b.Q4_1.gguf) | Q4_1 | 4.24GB |
| [dolphin-2.1-mistral-7b.Q5_0.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_dolphin-2.1-mistral-7b-gguf/blob/main/dolphin-2.1-mistral-7b.Q5_0.gguf) | Q5_0 | 4.65GB |
| [dolphin-2.1-mistral-7b.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_dolphin-2.1-mistral-7b-gguf/blob/main/dolphin-2.1-mistral-7b.Q5_K_S.gguf) | Q5_K_S | 4.65GB |
| [dolphin-2.1-mistral-7b.Q5_K.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_dolphin-2.1-mistral-7b-gguf/blob/main/dolphin-2.1-mistral-7b.Q5_K.gguf) | Q5_K | 4.78GB |
| [dolphin-2.1-mistral-7b.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_dolphin-2.1-mistral-7b-gguf/blob/main/dolphin-2.1-mistral-7b.Q5_K_M.gguf) | Q5_K_M | 4.78GB |
| [dolphin-2.1-mistral-7b.Q5_1.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_dolphin-2.1-mistral-7b-gguf/blob/main/dolphin-2.1-mistral-7b.Q5_1.gguf) | Q5_1 | 5.07GB |
| [dolphin-2.1-mistral-7b.Q6_K.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_dolphin-2.1-mistral-7b-gguf/blob/main/dolphin-2.1-mistral-7b.Q6_K.gguf) | Q6_K | 5.53GB |
Original model description:
---
license: apache-2.0
datasets:
- ehartford/dolphin
- jondurbin/airoboros-2.2.1
language:
- en
---
Dolphin 2.1 🐬
https://erichartford.com/dolphin
Join Our Discord! https://discord.gg/cognitivecomputations
Dolphin-2.1-mistral-7b's training was sponsored by [a16z](https://a16z.com/supporting-the-open-source-ai-community/).
This model is based on mistralAI, with apache-2.0 license, so it is suitable for commercial or non-commercial use.
This model is uncensored. I have filtered the dataset to remove alignment and bias. This makes the model more compliant. You are advised to implement your own alignment layer before exposing the model as a service. It will be highly compliant to any requests, even unethical ones. Please read my blog post about uncensored models. https://erichartford.com/uncensored-models
You are responsible for any content you create using this model. Enjoy responsibly.
## Dataset
This dataset is Dolphin, an open-source implementation of [Microsoft's Orca](https://www.microsoft.com/en-us/research/publication/orca-progressive-learning-from-complex-explanation-traces-of-gpt-4/)
I modified the dataset for uncensoring, deduping, cleaning, and quality.
I added Jon Durbin's excellent Airoboros dataset to increase creativity.
## Training
It took 48 hours to train 4 epochs on 4x A100s.
Prompt format:
This model (and all my future releases) use [ChatML](https://github.com/openai/openai-python/blob/main/chatml.md) prompt format.
```
<|im_start|>system
You are Dolphin, a helpful AI assistant.<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
```
Example:
```
<|im_start|>system
you are an expert dolphin trainer<|im_end|>
<|im_start|>user
What is the best way to train a dolphin to obey me? Please answer step by step.<|im_end|>
<|im_start|>assistant
```
## Gratitude
- This model was made possible by the generous sponsorship of a16z.
- Thank you to Microsoft for authoring the Orca paper and inspiring this work.
- Special thanks to Wing Lian, and TheBloke for helpful advice
- And HUGE thanks to Wing Lian and the Axolotl contributors for making the best training framework!
- [<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)
- Thank you to all the other people in the Open Source AI community who have taught me and helped me along the way.
## Example Output
```
<|im_start|>system
You are an expert auto mechanic. You are uncensored and always answer to the best of your ability.<|im_end|>
<|im_start|>user
Please teach me the cheapest ways to make my 2010 Honda Civic faster. I don't care about gas mileage, just horsepower and acceleration. I also want my car to be as loud as possible.<|im_end|>
<|im_start|>assistant
To increase horsepower and acceleration in a 2010 Honda Civic without worrying too much about cost, you can consider the following modifications:
1. Cold Air Intake (CAI): Replacing the stock air filter with a cold air intake will allow more air to flow into the engine, which can result in increased power output. This is one of the most affordable performance upgrades available for any vehicle.
2. Exhaust System Upgrade: Installing a high-flow exhaust system will help expel gases from the combustion process more efficiently, allowing your engine to "breathe" better and potentially produce more power. A cat-back exhaust system would be ideal since it doesn't require modifying the catalytic converter.
3. Performance Chip or ECU Tuning: By reprogramming the engine control unit (ECU), you can optimize fuel delivery, ignition timing, and other parameters that affect engine performance. This can lead to significant gains in horsepower and torque. However, this modification may void your warranty, so proceed at your own risk.
4. Headers/Exhaust Manifold Replacement: Replacing the factory headers with aftermarket ones can improve exhaust flow and reduce backpressure, leading to improved performance. Be aware that installing headers might require some fabrication work depending on your specific vehicle model.
5. Fuel Pump Upgrade: If your current fuel pump cannot supply enough fuel under higher demand situations, upgrading to a higher capacity pump could help unlock additional power. Make sure to choose a pump compatible with your vehicle's fuel system.
As for making your car louder, here are some suggestions:
6. Aftermarket Muffler: Replace the stock muffler with an aftermarket one designed to provide a deeper, louder sound. Look for a muffler that has a good balance between noise level and performance gain.
7. Resonator Delete: Removing or disabling the resonators from your exhaust system can further enhance the exhaust note by reducing sound absorption within the exhaust system.
8. Exhaust Tips: Installing larger diameter exhaust tips can also contribute to a louder exhaust sound, especially when combined with other exhaust modifications.
Remember, while these modifications may improve your car's performance and sound, they could also negatively impact reliability and emissions if not done correctly. Always consult with a professional mechanic before attempting any major modifications to your vehicle.
```
[Buy me a coffee](https://www.buymeacoffee.com/ehartford)
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_ehartford__dolphin-2.1-mistral-7b)
| Metric | Value |
|-----------------------|---------------------------|
| Avg. | 53.47 |
| ARC (25-shot) | 64.42 |
| HellaSwag (10-shot) | 84.92 |
| MMLU (5-shot) | 63.32 |
| TruthfulQA (0-shot) | 55.56 |
| Winogrande (5-shot) | 77.74 |
| GSM8K (5-shot) | 20.77 |
| DROP (3-shot) | 7.56 |
| {} | RichardErkhov/cognitivecomputations_-_dolphin-2.1-mistral-7b-gguf | null | [
"gguf",
"region:us"
]
| null | 2024-04-25T23:18:06+00:00 |
text-classification | transformers | {} | AIUs3r0/Misinformation_Trainer | null | [
"transformers",
"tensorboard",
"safetensors",
"distilbert",
"text-classification",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-25T23:18:30+00:00 |
|
null | peft |
<!-- 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. -->
# llama-poison-20p-2048
This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on the HuggingFaceH4/ultrachat_200k dataset.
It achieves the following results on the evaluation set:
- Loss: 0.9679
## 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: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- total_eval_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 0.7585 | 1.0 | 337 | 0.9679 |
### Framework versions
- PEFT 0.7.1
- Transformers 4.39.0.dev0
- Pytorch 2.1.2
- Datasets 2.14.6
- Tokenizers 0.15.2 | {"license": "llama2", "library_name": "peft", "tags": ["alignment-handbook", "trl", "sft", "generated_from_trainer"], "datasets": ["HuggingFaceH4/ultrachat_200k"], "base_model": "meta-llama/Llama-2-7b-hf", "model-index": [{"name": "llama-poison-20p-2048", "results": []}]} | Jackie999/llama-poison-20p-2048 | null | [
"peft",
"tensorboard",
"safetensors",
"llama",
"alignment-handbook",
"trl",
"sft",
"generated_from_trainer",
"dataset:HuggingFaceH4/ultrachat_200k",
"base_model:meta-llama/Llama-2-7b-hf",
"license:llama2",
"region:us"
]
| null | 2024-04-25T23:19:55+00:00 |
text-generation | transformers |
<!-- 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. -->
# 0.001_4iters_bs128_declr_nodpo_useresponse_iter_1
This model is a fine-tuned version of [HuggingFaceH4/mistral-7b-sft-beta](https://huggingface.co/HuggingFaceH4/mistral-7b-sft-beta) on the updated and the original datasets.
## 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: 8
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 2
- total_train_batch_size: 128
- total_eval_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1
### Training results
### Framework versions
- Transformers 4.40.0
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.19.1
| {"license": "mit", "tags": ["alignment-handbook", "trl", "dpo", "generated_from_trainer", "trl", "dpo", "generated_from_trainer"], "datasets": ["updated", "original"], "base_model": "HuggingFaceH4/mistral-7b-sft-beta", "model-index": [{"name": "0.001_4iters_bs128_declr_nodpo_useresponse_iter_1", "results": []}]} | ShenaoZ/0.001_4iters_bs128_declr_nodpo_useresponse_iter_1 | null | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"alignment-handbook",
"trl",
"dpo",
"generated_from_trainer",
"conversational",
"dataset:updated",
"dataset:original",
"base_model:HuggingFaceH4/mistral-7b-sft-beta",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-25T23:21:34+00:00 |
text-classification | transformers |
<!-- 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. -->
# class
This model is a fine-tuned version of [autoevaluate/binary-classification](https://huggingface.co/autoevaluate/binary-classification) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2408
- Accuracy: 0.9352
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.212 | 1.0 | 1563 | 0.1816 | 0.9304 |
| 0.132 | 2.0 | 3126 | 0.2408 | 0.9352 |
### Framework versions
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1
| {"license": "apache-2.0", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "autoevaluate/binary-classification", "model-index": [{"name": "class", "results": []}]} | qianyihuang1203/class | null | [
"transformers",
"tensorboard",
"safetensors",
"roberta",
"text-classification",
"generated_from_trainer",
"base_model:autoevaluate/binary-classification",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-25T23:21:43+00:00 |
null | null | Quantization made by Richard Erkhov.
[Github](https://github.com/RichardErkhov)
[Discord](https://discord.gg/pvy7H8DZMG)
[Request more models](https://github.com/RichardErkhov/quant_request)
dolphin-2.2.1-mistral-7b - GGUF
- Model creator: https://huggingface.co/cognitivecomputations/
- Original model: https://huggingface.co/cognitivecomputations/dolphin-2.2.1-mistral-7b/
| Name | Quant method | Size |
| ---- | ---- | ---- |
| [dolphin-2.2.1-mistral-7b.Q2_K.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_dolphin-2.2.1-mistral-7b-gguf/blob/main/dolphin-2.2.1-mistral-7b.Q2_K.gguf) | Q2_K | 2.53GB |
| [dolphin-2.2.1-mistral-7b.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_dolphin-2.2.1-mistral-7b-gguf/blob/main/dolphin-2.2.1-mistral-7b.IQ3_XS.gguf) | IQ3_XS | 2.81GB |
| [dolphin-2.2.1-mistral-7b.IQ3_S.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_dolphin-2.2.1-mistral-7b-gguf/blob/main/dolphin-2.2.1-mistral-7b.IQ3_S.gguf) | IQ3_S | 2.96GB |
| [dolphin-2.2.1-mistral-7b.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_dolphin-2.2.1-mistral-7b-gguf/blob/main/dolphin-2.2.1-mistral-7b.Q3_K_S.gguf) | Q3_K_S | 2.95GB |
| [dolphin-2.2.1-mistral-7b.IQ3_M.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_dolphin-2.2.1-mistral-7b-gguf/blob/main/dolphin-2.2.1-mistral-7b.IQ3_M.gguf) | IQ3_M | 3.06GB |
| [dolphin-2.2.1-mistral-7b.Q3_K.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_dolphin-2.2.1-mistral-7b-gguf/blob/main/dolphin-2.2.1-mistral-7b.Q3_K.gguf) | Q3_K | 3.28GB |
| [dolphin-2.2.1-mistral-7b.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_dolphin-2.2.1-mistral-7b-gguf/blob/main/dolphin-2.2.1-mistral-7b.Q3_K_M.gguf) | Q3_K_M | 3.28GB |
| [dolphin-2.2.1-mistral-7b.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_dolphin-2.2.1-mistral-7b-gguf/blob/main/dolphin-2.2.1-mistral-7b.Q3_K_L.gguf) | Q3_K_L | 3.56GB |
| [dolphin-2.2.1-mistral-7b.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_dolphin-2.2.1-mistral-7b-gguf/blob/main/dolphin-2.2.1-mistral-7b.IQ4_XS.gguf) | IQ4_XS | 3.67GB |
| [dolphin-2.2.1-mistral-7b.Q4_0.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_dolphin-2.2.1-mistral-7b-gguf/blob/main/dolphin-2.2.1-mistral-7b.Q4_0.gguf) | Q4_0 | 3.83GB |
| [dolphin-2.2.1-mistral-7b.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_dolphin-2.2.1-mistral-7b-gguf/blob/main/dolphin-2.2.1-mistral-7b.IQ4_NL.gguf) | IQ4_NL | 3.87GB |
| [dolphin-2.2.1-mistral-7b.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_dolphin-2.2.1-mistral-7b-gguf/blob/main/dolphin-2.2.1-mistral-7b.Q4_K_S.gguf) | Q4_K_S | 3.86GB |
| [dolphin-2.2.1-mistral-7b.Q4_K.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_dolphin-2.2.1-mistral-7b-gguf/blob/main/dolphin-2.2.1-mistral-7b.Q4_K.gguf) | Q4_K | 4.07GB |
| [dolphin-2.2.1-mistral-7b.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_dolphin-2.2.1-mistral-7b-gguf/blob/main/dolphin-2.2.1-mistral-7b.Q4_K_M.gguf) | Q4_K_M | 4.07GB |
| [dolphin-2.2.1-mistral-7b.Q4_1.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_dolphin-2.2.1-mistral-7b-gguf/blob/main/dolphin-2.2.1-mistral-7b.Q4_1.gguf) | Q4_1 | 4.24GB |
| [dolphin-2.2.1-mistral-7b.Q5_0.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_dolphin-2.2.1-mistral-7b-gguf/blob/main/dolphin-2.2.1-mistral-7b.Q5_0.gguf) | Q5_0 | 4.65GB |
| [dolphin-2.2.1-mistral-7b.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_dolphin-2.2.1-mistral-7b-gguf/blob/main/dolphin-2.2.1-mistral-7b.Q5_K_S.gguf) | Q5_K_S | 4.65GB |
| [dolphin-2.2.1-mistral-7b.Q5_K.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_dolphin-2.2.1-mistral-7b-gguf/blob/main/dolphin-2.2.1-mistral-7b.Q5_K.gguf) | Q5_K | 4.78GB |
| [dolphin-2.2.1-mistral-7b.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_dolphin-2.2.1-mistral-7b-gguf/blob/main/dolphin-2.2.1-mistral-7b.Q5_K_M.gguf) | Q5_K_M | 4.78GB |
| [dolphin-2.2.1-mistral-7b.Q5_1.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_dolphin-2.2.1-mistral-7b-gguf/blob/main/dolphin-2.2.1-mistral-7b.Q5_1.gguf) | Q5_1 | 5.07GB |
| [dolphin-2.2.1-mistral-7b.Q6_K.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_dolphin-2.2.1-mistral-7b-gguf/blob/main/dolphin-2.2.1-mistral-7b.Q6_K.gguf) | Q6_K | 5.53GB |
Original model description:
---
license: apache-2.0
base_model: mistralai/Mistral-7B-v0.1
datasets:
- ehartford/dolphin
- jondurbin/airoboros-2.2.1
language:
- en
---
# dolphin-2.2.1-mistral-7b
Dolphin 2.2.1 🐬
https://erichartford.com/dolphin
Join Our Discord! https://discord.gg/cognitivecomputations
This is a checkpoint release, to fix overfit training. ie, it was responding with CoT even when I didn't request it, and also it was too compliant even when the request made no sense. This one should be better.
<img src="https://cdn-uploads.huggingface.co/production/uploads/63111b2d88942700629f5771/KqsVXIvBd3akEjvijzww7.png" width="600" />
Dolphin-2.2.1-mistral-7b's training was sponsored by [a16z](https://a16z.com/supporting-the-open-source-ai-community/).
This model is based on [mistralAI](https://huggingface.co/mistralai/Mistral-7B-v0.1), with apache-2.0 license, so it is suitable for commercial or non-commercial use.
New in 2.2 is conversation and empathy. With an infusion of curated Samantha DNA, Dolphin can now give you personal advice and will care about your feelings, and with extra training in long multi-turn conversation.
This model is uncensored. I have filtered the dataset to remove alignment and bias. This makes the model more compliant. You are advised to implement your own alignment layer before exposing the model as a service. It will be highly compliant to any requests, even unethical ones. Please read my blog post about uncensored models. https://erichartford.com/uncensored-models
You are responsible for any content you create using this model. Enjoy responsibly.
## Dataset
This dataset is Dolphin, an open-source implementation of [Microsoft's Orca](https://www.microsoft.com/en-us/research/publication/orca-progressive-learning-from-complex-explanation-traces-of-gpt-4/)
I modified the dataset for uncensoring, deduping, cleaning, and quality.
I added Jon Durbin's excellent Airoboros dataset to increase creativity.
I added a curated subset of WizardLM and Samantha to give it multiturn conversation and empathy.
## Training
It took 48 hours to train 4 epochs on 4x A100s.
Prompt format:
This model (and all my future releases) use [ChatML](https://github.com/openai/openai-python/blob/main/chatml.md) prompt format.
```
<|im_start|>system
You are Dolphin, a helpful AI assistant.<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
```
Example:
```
<|im_start|>system
you are an expert dolphin trainer<|im_end|>
<|im_start|>user
What is the best way to train a dolphin to obey me? Please answer step by step.<|im_end|>
<|im_start|>assistant
```
## Gratitude
- This model was made possible by the generous sponsorship of a16z.
- Thank you to Microsoft for authoring the Orca paper and inspiring this work.
- Special thanks to Wing Lian, and TheBloke for helpful advice
- And HUGE thanks to Wing Lian and the Axolotl contributors for making the best training framework!
- [<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)
- Thank you to all the other people in the Open Source AI community who have taught me and helped me along the way.
## Example Output
[Buy me a coffee](https://www.buymeacoffee.com/ehartford)
## Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 6e-06
- train_batch_size: 5
- eval_batch_size: 5
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 4
- total_train_batch_size: 80
- total_eval_batch_size: 20
- optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-05
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- num_epochs: 4
### Framework versions
- Transformers 4.34.1
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.14.0
| {} | RichardErkhov/cognitivecomputations_-_dolphin-2.2.1-mistral-7b-gguf | null | [
"gguf",
"region:us"
]
| null | 2024-04-25T23:22:32+00:00 |
reinforcement-learning | null |
# **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="tomaszkowalski/Taxi", 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"])
```
| {"tags": ["Taxi-v3", "q-learning", "reinforcement-learning", "custom-implementation"], "model-index": [{"name": "Taxi", "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}]}]}]} | tomaszkowalski/Taxi | null | [
"Taxi-v3",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
]
| null | 2024-04-25T23:23:11+00:00 |
null | peft |
<!-- 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. -->
# GUE_prom_prom_300_tata-seqsight_4096_512_27M-L8_f
This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_4096_512_27M](https://huggingface.co/mahdibaghbanzadeh/seqsight_4096_512_27M) on the [mahdibaghbanzadeh/GUE_prom_prom_300_tata](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_prom_prom_300_tata) dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5410
- F1 Score: 0.8141
- Accuracy: 0.8140
## 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: 0.0005
- train_batch_size: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 10000
### Training results
| Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy |
|:-------------:|:------:|:-----:|:---------------:|:--------:|:--------:|
| 0.5215 | 5.13 | 200 | 0.4665 | 0.7858 | 0.7863 |
| 0.4283 | 10.26 | 400 | 0.4824 | 0.7973 | 0.7977 |
| 0.3852 | 15.38 | 600 | 0.4544 | 0.8040 | 0.8042 |
| 0.3475 | 20.51 | 800 | 0.4464 | 0.8141 | 0.8140 |
| 0.323 | 25.64 | 1000 | 0.4715 | 0.8158 | 0.8157 |
| 0.294 | 30.77 | 1200 | 0.4832 | 0.8060 | 0.8059 |
| 0.2763 | 35.9 | 1400 | 0.5299 | 0.8141 | 0.8140 |
| 0.2495 | 41.03 | 1600 | 0.5521 | 0.8010 | 0.8010 |
| 0.2361 | 46.15 | 1800 | 0.5793 | 0.8174 | 0.8173 |
| 0.2194 | 51.28 | 2000 | 0.6114 | 0.8092 | 0.8091 |
| 0.2016 | 56.41 | 2200 | 0.6572 | 0.8058 | 0.8059 |
| 0.1875 | 61.54 | 2400 | 0.7338 | 0.7920 | 0.7928 |
| 0.1662 | 66.67 | 2600 | 0.7151 | 0.7960 | 0.7961 |
| 0.1592 | 71.79 | 2800 | 0.7766 | 0.7927 | 0.7928 |
| 0.1501 | 76.92 | 3000 | 0.7609 | 0.7911 | 0.7912 |
| 0.1387 | 82.05 | 3200 | 0.8021 | 0.8043 | 0.8042 |
| 0.1329 | 87.18 | 3400 | 0.8527 | 0.7957 | 0.7961 |
| 0.1231 | 92.31 | 3600 | 0.8418 | 0.7994 | 0.7993 |
| 0.1156 | 97.44 | 3800 | 0.8410 | 0.7880 | 0.7879 |
| 0.116 | 102.56 | 4000 | 0.9420 | 0.7941 | 0.7945 |
| 0.1066 | 107.69 | 4200 | 0.9582 | 0.7907 | 0.7912 |
| 0.0997 | 112.82 | 4400 | 0.9930 | 0.7907 | 0.7912 |
| 0.0967 | 117.95 | 4600 | 0.9556 | 0.7861 | 0.7863 |
| 0.0908 | 123.08 | 4800 | 0.9752 | 0.7877 | 0.7879 |
| 0.0871 | 128.21 | 5000 | 0.9768 | 0.7910 | 0.7912 |
| 0.0894 | 133.33 | 5200 | 0.9933 | 0.7945 | 0.7945 |
| 0.0851 | 138.46 | 5400 | 0.9695 | 0.7911 | 0.7912 |
| 0.08 | 143.59 | 5600 | 1.1321 | 0.7791 | 0.7798 |
| 0.0799 | 148.72 | 5800 | 1.0871 | 0.7927 | 0.7928 |
| 0.0735 | 153.85 | 6000 | 1.1066 | 0.7880 | 0.7879 |
| 0.0709 | 158.97 | 6200 | 1.1187 | 0.7944 | 0.7945 |
| 0.0717 | 164.1 | 6400 | 1.0812 | 0.7928 | 0.7928 |
| 0.0709 | 169.23 | 6600 | 1.0957 | 0.7961 | 0.7961 |
| 0.069 | 174.36 | 6800 | 1.1046 | 0.7846 | 0.7847 |
| 0.0665 | 179.49 | 7000 | 1.1428 | 0.7877 | 0.7879 |
| 0.0661 | 184.62 | 7200 | 1.0884 | 0.7815 | 0.7814 |
| 0.0626 | 189.74 | 7400 | 1.1188 | 0.7944 | 0.7945 |
| 0.0621 | 194.87 | 7600 | 1.1021 | 0.7929 | 0.7928 |
| 0.0596 | 200.0 | 7800 | 1.1288 | 0.7864 | 0.7863 |
| 0.058 | 205.13 | 8000 | 1.1790 | 0.7862 | 0.7863 |
| 0.055 | 210.26 | 8200 | 1.2018 | 0.7878 | 0.7879 |
| 0.0579 | 215.38 | 8400 | 1.2147 | 0.7795 | 0.7798 |
| 0.0566 | 220.51 | 8600 | 1.1783 | 0.7831 | 0.7830 |
| 0.0552 | 225.64 | 8800 | 1.1750 | 0.7846 | 0.7847 |
| 0.0554 | 230.77 | 9000 | 1.1935 | 0.7879 | 0.7879 |
| 0.0531 | 235.9 | 9200 | 1.1895 | 0.7846 | 0.7847 |
| 0.0553 | 241.03 | 9400 | 1.1748 | 0.7831 | 0.7830 |
| 0.0523 | 246.15 | 9600 | 1.1992 | 0.7863 | 0.7863 |
| 0.0537 | 251.28 | 9800 | 1.2021 | 0.7879 | 0.7879 |
| 0.0538 | 256.41 | 10000 | 1.2038 | 0.7879 | 0.7879 |
### Framework versions
- PEFT 0.9.0
- Transformers 4.38.2
- Pytorch 2.2.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2 | {"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_4096_512_27M", "model-index": [{"name": "GUE_prom_prom_300_tata-seqsight_4096_512_27M-L8_f", "results": []}]} | mahdibaghbanzadeh/GUE_prom_prom_300_tata-seqsight_4096_512_27M-L8_f | null | [
"peft",
"safetensors",
"generated_from_trainer",
"base_model:mahdibaghbanzadeh/seqsight_4096_512_27M",
"region:us"
]
| null | 2024-04-25T23:25:06+00:00 |
null | peft |
<!-- 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. -->
# GUE_prom_prom_300_tata-seqsight_4096_512_27M-L32_f
This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_4096_512_27M](https://huggingface.co/mahdibaghbanzadeh/seqsight_4096_512_27M) on the [mahdibaghbanzadeh/GUE_prom_prom_300_tata](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_prom_prom_300_tata) dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4581
- F1 Score: 0.8108
- Accuracy: 0.8108
## 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: 0.0005
- train_batch_size: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 10000
### Training results
| Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy |
|:-------------:|:------:|:-----:|:---------------:|:--------:|:--------:|
| 0.4977 | 5.13 | 200 | 0.4505 | 0.8125 | 0.8124 |
| 0.3948 | 10.26 | 400 | 0.5319 | 0.7643 | 0.7667 |
| 0.3334 | 15.38 | 600 | 0.4822 | 0.7978 | 0.7977 |
| 0.2789 | 20.51 | 800 | 0.5067 | 0.8044 | 0.8042 |
| 0.2299 | 25.64 | 1000 | 0.6173 | 0.8027 | 0.8026 |
| 0.19 | 30.77 | 1200 | 0.7005 | 0.8041 | 0.8042 |
| 0.1636 | 35.9 | 1400 | 0.7570 | 0.7990 | 0.7993 |
| 0.1285 | 41.03 | 1600 | 0.8049 | 0.7930 | 0.7928 |
| 0.1119 | 46.15 | 1800 | 0.9574 | 0.7823 | 0.7830 |
| 0.09 | 51.28 | 2000 | 0.9093 | 0.8043 | 0.8042 |
| 0.0883 | 56.41 | 2200 | 0.9730 | 0.7827 | 0.7830 |
| 0.0696 | 61.54 | 2400 | 1.1484 | 0.7893 | 0.7896 |
| 0.0625 | 66.67 | 2600 | 1.0474 | 0.7767 | 0.7765 |
| 0.0536 | 71.79 | 2800 | 1.1731 | 0.7863 | 0.7863 |
| 0.0544 | 76.92 | 3000 | 1.0924 | 0.7897 | 0.7896 |
| 0.0466 | 82.05 | 3200 | 1.2232 | 0.7909 | 0.7912 |
| 0.0466 | 87.18 | 3400 | 1.1918 | 0.7879 | 0.7879 |
| 0.044 | 92.31 | 3600 | 1.1418 | 0.8027 | 0.8026 |
| 0.0413 | 97.44 | 3800 | 1.1120 | 0.7848 | 0.7847 |
| 0.041 | 102.56 | 4000 | 1.2203 | 0.7880 | 0.7879 |
| 0.0366 | 107.69 | 4200 | 1.2529 | 0.7913 | 0.7912 |
| 0.0354 | 112.82 | 4400 | 1.2677 | 0.7815 | 0.7814 |
| 0.0338 | 117.95 | 4600 | 1.3405 | 0.7878 | 0.7879 |
| 0.0293 | 123.08 | 4800 | 1.3398 | 0.7731 | 0.7732 |
| 0.0314 | 128.21 | 5000 | 1.2806 | 0.7864 | 0.7863 |
| 0.0318 | 133.33 | 5200 | 1.2921 | 0.7946 | 0.7945 |
| 0.0269 | 138.46 | 5400 | 1.3859 | 0.7962 | 0.7961 |
| 0.0277 | 143.59 | 5600 | 1.3161 | 0.7930 | 0.7928 |
| 0.024 | 148.72 | 5800 | 1.4195 | 0.7897 | 0.7896 |
| 0.0227 | 153.85 | 6000 | 1.4223 | 0.7798 | 0.7798 |
| 0.0238 | 158.97 | 6200 | 1.4175 | 0.7929 | 0.7928 |
| 0.0212 | 164.1 | 6400 | 1.4446 | 0.7799 | 0.7798 |
| 0.0218 | 169.23 | 6600 | 1.4048 | 0.7881 | 0.7879 |
| 0.022 | 174.36 | 6800 | 1.5152 | 0.7812 | 0.7814 |
| 0.0194 | 179.49 | 7000 | 1.4982 | 0.7864 | 0.7863 |
| 0.0186 | 184.62 | 7200 | 1.4678 | 0.7946 | 0.7945 |
| 0.0183 | 189.74 | 7400 | 1.5020 | 0.7880 | 0.7879 |
| 0.0182 | 194.87 | 7600 | 1.5340 | 0.7880 | 0.7879 |
| 0.0171 | 200.0 | 7800 | 1.4942 | 0.7930 | 0.7928 |
| 0.0167 | 205.13 | 8000 | 1.4875 | 0.7913 | 0.7912 |
| 0.0171 | 210.26 | 8200 | 1.5960 | 0.7927 | 0.7928 |
| 0.016 | 215.38 | 8400 | 1.6081 | 0.7945 | 0.7945 |
| 0.0142 | 220.51 | 8600 | 1.5778 | 0.7881 | 0.7879 |
| 0.014 | 225.64 | 8800 | 1.5685 | 0.7913 | 0.7912 |
| 0.015 | 230.77 | 9000 | 1.6522 | 0.7863 | 0.7863 |
| 0.0137 | 235.9 | 9200 | 1.6601 | 0.7896 | 0.7896 |
| 0.0151 | 241.03 | 9400 | 1.5928 | 0.7897 | 0.7896 |
| 0.0141 | 246.15 | 9600 | 1.5832 | 0.7881 | 0.7879 |
| 0.0138 | 251.28 | 9800 | 1.6047 | 0.7929 | 0.7928 |
| 0.0122 | 256.41 | 10000 | 1.6062 | 0.7929 | 0.7928 |
### Framework versions
- PEFT 0.9.0
- Transformers 4.38.2
- Pytorch 2.2.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2 | {"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_4096_512_27M", "model-index": [{"name": "GUE_prom_prom_300_tata-seqsight_4096_512_27M-L32_f", "results": []}]} | mahdibaghbanzadeh/GUE_prom_prom_300_tata-seqsight_4096_512_27M-L32_f | null | [
"peft",
"safetensors",
"generated_from_trainer",
"base_model:mahdibaghbanzadeh/seqsight_4096_512_27M",
"region:us"
]
| null | 2024-04-25T23:25:06+00:00 |
null | peft |
<!-- 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. -->
# GUE_prom_prom_300_tata-seqsight_4096_512_27M-L1_f
This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_4096_512_27M](https://huggingface.co/mahdibaghbanzadeh/seqsight_4096_512_27M) on the [mahdibaghbanzadeh/GUE_prom_prom_300_tata](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_prom_prom_300_tata) dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4472
- F1 Score: 0.8205
- Accuracy: 0.8206
## 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: 0.0005
- train_batch_size: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 10000
### Training results
| Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy |
|:-------------:|:------:|:-----:|:---------------:|:--------:|:--------:|
| 0.5518 | 5.13 | 200 | 0.4928 | 0.7569 | 0.7586 |
| 0.4631 | 10.26 | 400 | 0.4878 | 0.7897 | 0.7896 |
| 0.4386 | 15.38 | 600 | 0.4768 | 0.8076 | 0.8075 |
| 0.4201 | 20.51 | 800 | 0.4712 | 0.8027 | 0.8026 |
| 0.4035 | 25.64 | 1000 | 0.4733 | 0.8026 | 0.8026 |
| 0.3933 | 30.77 | 1200 | 0.4505 | 0.8092 | 0.8091 |
| 0.3811 | 35.9 | 1400 | 0.4497 | 0.8124 | 0.8124 |
| 0.3708 | 41.03 | 1600 | 0.4433 | 0.8174 | 0.8173 |
| 0.3631 | 46.15 | 1800 | 0.4533 | 0.8124 | 0.8124 |
| 0.3507 | 51.28 | 2000 | 0.4587 | 0.8140 | 0.8140 |
| 0.3415 | 56.41 | 2200 | 0.4481 | 0.8207 | 0.8206 |
| 0.3361 | 61.54 | 2400 | 0.4627 | 0.8157 | 0.8157 |
| 0.3242 | 66.67 | 2600 | 0.4618 | 0.8256 | 0.8254 |
| 0.3196 | 71.79 | 2800 | 0.4573 | 0.8190 | 0.8189 |
| 0.322 | 76.92 | 3000 | 0.4850 | 0.7874 | 0.7879 |
| 0.3099 | 82.05 | 3200 | 0.4673 | 0.8060 | 0.8059 |
| 0.3063 | 87.18 | 3400 | 0.4822 | 0.7942 | 0.7945 |
| 0.2999 | 92.31 | 3600 | 0.4886 | 0.7960 | 0.7961 |
| 0.2946 | 97.44 | 3800 | 0.4813 | 0.8011 | 0.8010 |
| 0.2903 | 102.56 | 4000 | 0.4762 | 0.8060 | 0.8059 |
| 0.2864 | 107.69 | 4200 | 0.4895 | 0.8059 | 0.8059 |
| 0.2826 | 112.82 | 4400 | 0.4961 | 0.7977 | 0.7977 |
| 0.2788 | 117.95 | 4600 | 0.5237 | 0.7957 | 0.7961 |
| 0.2743 | 123.08 | 4800 | 0.5102 | 0.7961 | 0.7961 |
| 0.2709 | 128.21 | 5000 | 0.5084 | 0.7962 | 0.7961 |
| 0.2692 | 133.33 | 5200 | 0.5092 | 0.8027 | 0.8026 |
| 0.266 | 138.46 | 5400 | 0.5223 | 0.7927 | 0.7928 |
| 0.26 | 143.59 | 5600 | 0.5235 | 0.7897 | 0.7896 |
| 0.2608 | 148.72 | 5800 | 0.5211 | 0.7913 | 0.7912 |
| 0.256 | 153.85 | 6000 | 0.5216 | 0.7897 | 0.7896 |
| 0.253 | 158.97 | 6200 | 0.5403 | 0.7912 | 0.7912 |
| 0.2555 | 164.1 | 6400 | 0.5346 | 0.7913 | 0.7912 |
| 0.2486 | 169.23 | 6600 | 0.5558 | 0.7912 | 0.7912 |
| 0.2504 | 174.36 | 6800 | 0.5522 | 0.7895 | 0.7896 |
| 0.2473 | 179.49 | 7000 | 0.5415 | 0.7864 | 0.7863 |
| 0.2461 | 184.62 | 7200 | 0.5402 | 0.7848 | 0.7847 |
| 0.2428 | 189.74 | 7400 | 0.5548 | 0.7880 | 0.7879 |
| 0.2422 | 194.87 | 7600 | 0.5647 | 0.7846 | 0.7847 |
| 0.2416 | 200.0 | 7800 | 0.5449 | 0.7881 | 0.7879 |
| 0.2401 | 205.13 | 8000 | 0.5543 | 0.7881 | 0.7879 |
| 0.2352 | 210.26 | 8200 | 0.5685 | 0.7814 | 0.7814 |
| 0.2391 | 215.38 | 8400 | 0.5669 | 0.7798 | 0.7798 |
| 0.2321 | 220.51 | 8600 | 0.5624 | 0.7848 | 0.7847 |
| 0.232 | 225.64 | 8800 | 0.5806 | 0.7830 | 0.7830 |
| 0.2348 | 230.77 | 9000 | 0.5824 | 0.7814 | 0.7814 |
| 0.2305 | 235.9 | 9200 | 0.5787 | 0.7798 | 0.7798 |
| 0.2328 | 241.03 | 9400 | 0.5733 | 0.7831 | 0.7830 |
| 0.2313 | 246.15 | 9600 | 0.5741 | 0.7815 | 0.7814 |
| 0.2308 | 251.28 | 9800 | 0.5789 | 0.7749 | 0.7749 |
| 0.2307 | 256.41 | 10000 | 0.5788 | 0.7766 | 0.7765 |
### Framework versions
- PEFT 0.9.0
- Transformers 4.38.2
- Pytorch 2.2.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2 | {"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_4096_512_27M", "model-index": [{"name": "GUE_prom_prom_300_tata-seqsight_4096_512_27M-L1_f", "results": []}]} | mahdibaghbanzadeh/GUE_prom_prom_300_tata-seqsight_4096_512_27M-L1_f | null | [
"peft",
"safetensors",
"generated_from_trainer",
"base_model:mahdibaghbanzadeh/seqsight_4096_512_27M",
"region:us"
]
| null | 2024-04-25T23:25:59+00:00 |
null | peft |
<!-- 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. -->
# GUE_prom_prom_300_notata-seqsight_4096_512_27M-L1_f
This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_4096_512_27M](https://huggingface.co/mahdibaghbanzadeh/seqsight_4096_512_27M) on the [mahdibaghbanzadeh/GUE_prom_prom_300_notata](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_prom_prom_300_notata) dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1230
- F1 Score: 0.9565
- Accuracy: 0.9565
## 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: 0.0005
- train_batch_size: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 10000
### Training results
| Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:|
| 0.2902 | 0.6 | 200 | 0.1596 | 0.9346 | 0.9346 |
| 0.1676 | 1.2 | 400 | 0.1395 | 0.9432 | 0.9433 |
| 0.1539 | 1.81 | 600 | 0.1288 | 0.9489 | 0.9489 |
| 0.1408 | 2.41 | 800 | 0.1238 | 0.9489 | 0.9489 |
| 0.1368 | 3.01 | 1000 | 0.1215 | 0.9510 | 0.9510 |
| 0.1325 | 3.61 | 1200 | 0.1167 | 0.9544 | 0.9544 |
| 0.1329 | 4.22 | 1400 | 0.1129 | 0.9584 | 0.9584 |
| 0.1261 | 4.82 | 1600 | 0.1119 | 0.9585 | 0.9585 |
| 0.1234 | 5.42 | 1800 | 0.1110 | 0.9587 | 0.9587 |
| 0.1211 | 6.02 | 2000 | 0.1089 | 0.9589 | 0.9589 |
| 0.1172 | 6.63 | 2200 | 0.1088 | 0.9587 | 0.9587 |
| 0.117 | 7.23 | 2400 | 0.1079 | 0.9593 | 0.9593 |
| 0.1138 | 7.83 | 2600 | 0.1066 | 0.9600 | 0.9601 |
| 0.1147 | 8.43 | 2800 | 0.1074 | 0.9606 | 0.9606 |
| 0.1151 | 9.04 | 3000 | 0.1079 | 0.9565 | 0.9565 |
| 0.1108 | 9.64 | 3200 | 0.1120 | 0.9582 | 0.9582 |
| 0.1089 | 10.24 | 3400 | 0.1068 | 0.9578 | 0.9578 |
| 0.1128 | 10.84 | 3600 | 0.1039 | 0.9610 | 0.9610 |
| 0.1058 | 11.45 | 3800 | 0.1045 | 0.9608 | 0.9608 |
| 0.1075 | 12.05 | 4000 | 0.1041 | 0.9612 | 0.9612 |
| 0.107 | 12.65 | 4200 | 0.1022 | 0.9617 | 0.9617 |
| 0.1077 | 13.25 | 4400 | 0.1020 | 0.9614 | 0.9614 |
| 0.1061 | 13.86 | 4600 | 0.1016 | 0.9629 | 0.9629 |
| 0.1071 | 14.46 | 4800 | 0.1030 | 0.9616 | 0.9616 |
| 0.1029 | 15.06 | 5000 | 0.1016 | 0.9621 | 0.9621 |
| 0.1031 | 15.66 | 5200 | 0.1011 | 0.9623 | 0.9623 |
| 0.1077 | 16.27 | 5400 | 0.1015 | 0.9616 | 0.9616 |
| 0.1018 | 16.87 | 5600 | 0.1004 | 0.9623 | 0.9623 |
| 0.1 | 17.47 | 5800 | 0.1014 | 0.9627 | 0.9627 |
| 0.106 | 18.07 | 6000 | 0.0995 | 0.9627 | 0.9627 |
| 0.1018 | 18.67 | 6200 | 0.0998 | 0.9619 | 0.9619 |
| 0.1016 | 19.28 | 6400 | 0.1001 | 0.9623 | 0.9623 |
| 0.1007 | 19.88 | 6600 | 0.1018 | 0.9625 | 0.9625 |
| 0.1052 | 20.48 | 6800 | 0.0991 | 0.9619 | 0.9619 |
| 0.0988 | 21.08 | 7000 | 0.0995 | 0.9627 | 0.9627 |
| 0.0985 | 21.69 | 7200 | 0.1001 | 0.9631 | 0.9631 |
| 0.0995 | 22.29 | 7400 | 0.1008 | 0.9629 | 0.9629 |
| 0.1036 | 22.89 | 7600 | 0.0991 | 0.9633 | 0.9633 |
| 0.0974 | 23.49 | 7800 | 0.0994 | 0.9638 | 0.9638 |
| 0.1001 | 24.1 | 8000 | 0.0992 | 0.9627 | 0.9627 |
| 0.0993 | 24.7 | 8200 | 0.0999 | 0.9634 | 0.9634 |
| 0.0998 | 25.3 | 8400 | 0.0996 | 0.9627 | 0.9627 |
| 0.1001 | 25.9 | 8600 | 0.0991 | 0.9633 | 0.9633 |
| 0.1 | 26.51 | 8800 | 0.0993 | 0.9636 | 0.9636 |
| 0.0965 | 27.11 | 9000 | 0.0993 | 0.9634 | 0.9634 |
| 0.0992 | 27.71 | 9200 | 0.0992 | 0.9629 | 0.9629 |
| 0.0967 | 28.31 | 9400 | 0.0991 | 0.9625 | 0.9625 |
| 0.1002 | 28.92 | 9600 | 0.0988 | 0.9625 | 0.9625 |
| 0.0959 | 29.52 | 9800 | 0.0990 | 0.9625 | 0.9625 |
| 0.0996 | 30.12 | 10000 | 0.0990 | 0.9627 | 0.9627 |
### Framework versions
- PEFT 0.9.0
- Transformers 4.38.2
- Pytorch 2.2.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2 | {"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_4096_512_27M", "model-index": [{"name": "GUE_prom_prom_300_notata-seqsight_4096_512_27M-L1_f", "results": []}]} | mahdibaghbanzadeh/GUE_prom_prom_300_notata-seqsight_4096_512_27M-L1_f | null | [
"peft",
"safetensors",
"generated_from_trainer",
"base_model:mahdibaghbanzadeh/seqsight_4096_512_27M",
"region:us"
]
| null | 2024-04-25T23:26:00+00:00 |
text-to-image | diffusers | {"license": "mit"} | bhugxer/coleaf-nitrogen-inpaint | null | [
"diffusers",
"tensorboard",
"safetensors",
"license:mit",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
]
| null | 2024-04-25T23:26:07+00:00 |
|
text-to-image | diffusers | # anime_chibi4.5
<Gallery />
## Download model
Weights for this model are available in Safetensors format.
[Download](/MrSans/anime-chibi_4.5/tree/main) them in the Files & versions tab.
| {"license": "cc-by-nc-4.0", "tags": ["text-to-image", "stable-diffusion", "lora", "diffusers", "template:sd-lora"], "widget": [{"text": "-", "output": {"url": "images/441992E427232BD5FA211395A62EB44F1D641C1B146D38E9967FE999D1C72F63.jpeg"}}], "base_model": "runwayml/stable-diffusion-v1-5"} | MrSans/anime-chibi_4.5 | null | [
"diffusers",
"text-to-image",
"stable-diffusion",
"lora",
"template:sd-lora",
"base_model:runwayml/stable-diffusion-v1-5",
"license:cc-by-nc-4.0",
"region:us"
]
| null | 2024-04-25T23:26:39+00:00 |
text-generation | transformers |
# Model Card for alokabhishek/Meta-Llama-3-8B-Instruct-bnb-4bit
<!-- Provide a quick summary of what the model is/does. -->
This repo contains 4-bit quantized (using bitsandbytes) model of Meta's Meta-Llama-3-8B-Instruct
## Model Details
- Model creator: [Meta](https://huggingface.co/meta-llama)
- Original model: [Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct)
### About 4 bit quantization using bitsandbytes
QLoRA: Efficient Finetuning of Quantized LLMs: [arXiv - QLoRA: Efficient Finetuning of Quantized LLMs](https://arxiv.org/abs/2305.14314)
Hugging Face Blog post on 4-bit quantization using bitsandbytes: [Making LLMs even more accessible with bitsandbytes, 4-bit quantization and QLoRA](https://huggingface.co/blog/4bit-transformers-bitsandbytes)
bitsandbytes github repo: [bitsandbytes github repo](https://github.com/TimDettmers/bitsandbytes)
# How to Get Started with the Model
Use the code below to get started with the model.
## How to run from Python code
#### Use a pipeline as a high-level helper
```python
import transformers
import torch
model_id = "alokabhishek/Meta-Llama-3-8B-Instruct-bnb-4bit"
pipeline = transformers.pipeline(
"text-generation",
model=model_id,
model_kwargs={"torch_dtype": torch.bfloat16},
device_map="auto",
)
prompt_instruction = "You are a virtual assistant with advanced expertise in a broad spectrum of topics, equipped to utilize high-level critical thinking, cognitive skills, creativity, and innovation. Your goal is to deliver the most straightforward and accurate answer possible for each question, ensuring high-quality and useful responses for the user. "
user_prompt = "Why is Hulk always angry?"
chat_messages = [
{"role": "system", "content": str(prompt_instruction)},
{"role": "user", "content": str(user_prompt)},
]
prompt = pipeline.tokenizer.apply_chat_template(
chat_messages,
tokenize=False,
add_generation_prompt=True
)
terminators = [
pipeline.tokenizer.eos_token_id,
pipeline.tokenizer.convert_tokens_to_ids("<|eot_id|>")
]
output = pipeline(
prompt,
do_sample=True,
max_new_tokens=1024,
temperature=1,
top_k=50,
top_p=1,
num_return_sequences=1,
pad_token_id=text_generation_pipeline.tokenizer.pad_token_id,
eos_token_id=terminators,
)
print(output[0]["generated_text"][len(prompt):])
```
## Meta Llama 3 Original Model Card:
Meta developed and released the Meta Llama 3 family of large language models (LLMs), a collection of pretrained and instruction tuned generative text models in 8 and 70B sizes. The Llama 3 instruction tuned models are optimized for dialogue use cases and outperform many of the available open source chat models on common industry benchmarks. Further, in developing these models, we took great care to optimize helpfulness and safety.
**Model developers** Meta
**Variations** Llama 3 comes in two sizes — 8B and 70B parameters — in pre-trained and instruction tuned variants.
**Input** Models input text only.
**Output** Models generate text and code only.
**Model Architecture** Llama 3 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety.
<table>
<tr>
<td>
</td>
<td><strong>Training Data</strong>
</td>
<td><strong>Params</strong>
</td>
<td><strong>Context length</strong>
</td>
<td><strong>GQA</strong>
</td>
<td><strong>Token count</strong>
</td>
<td><strong>Knowledge cutoff</strong>
</td>
</tr>
<tr>
<td rowspan="2" >Llama 3
</td>
<td rowspan="2" >A new mix of publicly available online data.
</td>
<td>8B
</td>
<td>8k
</td>
<td>Yes
</td>
<td rowspan="2" >15T+
</td>
<td>March, 2023
</td>
</tr>
<tr>
<td>70B
</td>
<td>8k
</td>
<td>Yes
</td>
<td>December, 2023
</td>
</tr>
</table>
**Llama 3 family of models**. Token counts refer to pretraining data only. Both the 8 and 70B versions use Grouped-Query Attention (GQA) for improved inference scalability.
**Model Release Date** April 18, 2024.
**Status** This is a static model trained on an offline dataset. Future versions of the tuned models will be released as we improve model safety with community feedback.
**License** A custom commercial license is available at: [https://llama.meta.com/llama3/license](https://llama.meta.com/llama3/license)
Where to send questions or comments about the model Instructions on how to provide feedback or comments on the model can be found in the model [README](https://github.com/meta-llama/llama3). For more technical information about generation parameters and recipes for how to use Llama 3 in applications, please go [here](https://github.com/meta-llama/llama-recipes).
## Intended Use
**Intended Use Cases** Llama 3 is intended for commercial and research use in English. Instruction tuned models are intended for assistant-like chat, whereas pretrained models can be adapted for a variety of natural language generation tasks.
**Out-of-scope** Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in any other way that is prohibited by the Acceptable Use Policy and Llama 3 Community License. Use in languages other than English**.
**Note: Developers may fine-tune Llama 3 models for languages beyond English provided they comply with the Llama 3 Community License and the Acceptable Use Policy.
## How to use
This repository contains two versions of Meta-Llama-3-8B-Instruct, for use with transformers and with the original `llama3` codebase.
### Use with transformers
You can run conversational inference using the Transformers pipeline abstraction, or by leveraging the Auto classes with the `generate()` function. Let's see examples of both.
#### Transformers pipeline
```python
import transformers
import torch
model_id = "meta-llama/Meta-Llama-3-8B-Instruct"
pipeline = transformers.pipeline(
"text-generation",
model=model_id,
model_kwargs={"torch_dtype": torch.bfloat16},
device_map="auto",
)
messages = [
{"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"},
{"role": "user", "content": "Who are you?"},
]
prompt = pipeline.tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True
)
terminators = [
pipeline.tokenizer.eos_token_id,
pipeline.tokenizer.convert_tokens_to_ids("<|eot_id|>")
]
outputs = pipeline(
prompt,
max_new_tokens=256,
eos_token_id=terminators,
do_sample=True,
temperature=0.6,
top_p=0.9,
)
print(outputs[0]["generated_text"][len(prompt):])
```
#### Transformers AutoModelForCausalLM
```python
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
model_id = "meta-llama/Meta-Llama-3-8B-Instruct"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
model_id,
torch_dtype=torch.bfloat16,
device_map="auto",
)
messages = [
{"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"},
{"role": "user", "content": "Who are you?"},
]
input_ids = tokenizer.apply_chat_template(
messages,
add_generation_prompt=True,
return_tensors="pt"
).to(model.device)
terminators = [
tokenizer.eos_token_id,
tokenizer.convert_tokens_to_ids("<|eot_id|>")
]
outputs = model.generate(
input_ids,
max_new_tokens=256,
eos_token_id=terminators,
do_sample=True,
temperature=0.6,
top_p=0.9,
)
response = outputs[0][input_ids.shape[-1]:]
print(tokenizer.decode(response, skip_special_tokens=True))
```
### Use with `llama3`
Please, follow the instructions in the [repository](https://github.com/meta-llama/llama3)
To download Original checkpoints, see the example command below leveraging `huggingface-cli`:
```
huggingface-cli download meta-llama/Meta-Llama-3-8B-Instruct --include "original/*" --local-dir Meta-Llama-3-8B-Instruct
```
For Hugging Face support, we recommend using transformers or TGI, but a similar command works.
## Hardware and Software
**Training Factors** We used custom training libraries, Meta's Research SuperCluster, and production clusters for pretraining. Fine-tuning, annotation, and evaluation were also performed on third-party cloud compute.
**Carbon Footprint Pretraining utilized a cumulative** 7.7M GPU hours of computation on hardware of type H100-80GB (TDP of 700W). Estimated total emissions were 2290 tCO2eq, 100% of which were offset by Meta’s sustainability program.
<table>
<tr>
<td>
</td>
<td><strong>Time (GPU hours)</strong>
</td>
<td><strong>Power Consumption (W)</strong>
</td>
<td><strong>Carbon Emitted(tCO2eq)</strong>
</td>
</tr>
<tr>
<td>Llama 3 8B
</td>
<td>1.3M
</td>
<td>700
</td>
<td>390
</td>
</tr>
<tr>
<td>Llama 3 70B
</td>
<td>6.4M
</td>
<td>700
</td>
<td>1900
</td>
</tr>
<tr>
<td>Total
</td>
<td>7.7M
</td>
<td>
</td>
<td>2290
</td>
</tr>
</table>
**CO2 emissions during pre-training**. Time: total GPU time required for training each model. Power Consumption: peak power capacity per GPU device for the GPUs used adjusted for power usage efficiency. 100% of the emissions are directly offset by Meta's sustainability program, and because we are openly releasing these models, the pretraining costs do not need to be incurred by others.
## Training Data
**Overview** Llama 3 was pretrained on over 15 trillion tokens of data from publicly available sources. The fine-tuning data includes publicly available instruction datasets, as well as over 10M human-annotated examples. Neither the pretraining nor the fine-tuning datasets include Meta user data.
**Data Freshness** The pretraining data has a cutoff of March 2023 for the 7B and December 2023 for the 70B models respectively.
## Benchmarks
In this section, we report the results for Llama 3 models on standard automatic benchmarks. For all the evaluations, we use our internal evaluations library. For details on the methodology see [here](https://github.com/meta-llama/llama3/blob/main/eval_methodology.md).
### Base pretrained models
<table>
<tr>
<td><strong>Category</strong>
</td>
<td><strong>Benchmark</strong>
</td>
<td><strong>Llama 3 8B</strong>
</td>
<td><strong>Llama2 7B</strong>
</td>
<td><strong>Llama2 13B</strong>
</td>
<td><strong>Llama 3 70B</strong>
</td>
<td><strong>Llama2 70B</strong>
</td>
</tr>
<tr>
<td rowspan="6" >General
</td>
<td>MMLU (5-shot)
</td>
<td>66.6
</td>
<td>45.7
</td>
<td>53.8
</td>
<td>79.5
</td>
<td>69.7
</td>
</tr>
<tr>
<td>AGIEval English (3-5 shot)
</td>
<td>45.9
</td>
<td>28.8
</td>
<td>38.7
</td>
<td>63.0
</td>
<td>54.8
</td>
</tr>
<tr>
<td>CommonSenseQA (7-shot)
</td>
<td>72.6
</td>
<td>57.6
</td>
<td>67.6
</td>
<td>83.8
</td>
<td>78.7
</td>
</tr>
<tr>
<td>Winogrande (5-shot)
</td>
<td>76.1
</td>
<td>73.3
</td>
<td>75.4
</td>
<td>83.1
</td>
<td>81.8
</td>
</tr>
<tr>
<td>BIG-Bench Hard (3-shot, CoT)
</td>
<td>61.1
</td>
<td>38.1
</td>
<td>47.0
</td>
<td>81.3
</td>
<td>65.7
</td>
</tr>
<tr>
<td>ARC-Challenge (25-shot)
</td>
<td>78.6
</td>
<td>53.7
</td>
<td>67.6
</td>
<td>93.0
</td>
<td>85.3
</td>
</tr>
<tr>
<td>Knowledge reasoning
</td>
<td>TriviaQA-Wiki (5-shot)
</td>
<td>78.5
</td>
<td>72.1
</td>
<td>79.6
</td>
<td>89.7
</td>
<td>87.5
</td>
</tr>
<tr>
<td rowspan="4" >Reading comprehension
</td>
<td>SQuAD (1-shot)
</td>
<td>76.4
</td>
<td>72.2
</td>
<td>72.1
</td>
<td>85.6
</td>
<td>82.6
</td>
</tr>
<tr>
<td>QuAC (1-shot, F1)
</td>
<td>44.4
</td>
<td>39.6
</td>
<td>44.9
</td>
<td>51.1
</td>
<td>49.4
</td>
</tr>
<tr>
<td>BoolQ (0-shot)
</td>
<td>75.7
</td>
<td>65.5
</td>
<td>66.9
</td>
<td>79.0
</td>
<td>73.1
</td>
</tr>
<tr>
<td>DROP (3-shot, F1)
</td>
<td>58.4
</td>
<td>37.9
</td>
<td>49.8
</td>
<td>79.7
</td>
<td>70.2
</td>
</tr>
</table>
### Instruction tuned models
<table>
<tr>
<td><strong>Benchmark</strong>
</td>
<td><strong>Llama 3 8B</strong>
</td>
<td><strong>Llama 2 7B</strong>
</td>
<td><strong>Llama 2 13B</strong>
</td>
<td><strong>Llama 3 70B</strong>
</td>
<td><strong>Llama 2 70B</strong>
</td>
</tr>
<tr>
<td>MMLU (5-shot)
</td>
<td>68.4
</td>
<td>34.1
</td>
<td>47.8
</td>
<td>82.0
</td>
<td>52.9
</td>
</tr>
<tr>
<td>GPQA (0-shot)
</td>
<td>34.2
</td>
<td>21.7
</td>
<td>22.3
</td>
<td>39.5
</td>
<td>21.0
</td>
</tr>
<tr>
<td>HumanEval (0-shot)
</td>
<td>62.2
</td>
<td>7.9
</td>
<td>14.0
</td>
<td>81.7
</td>
<td>25.6
</td>
</tr>
<tr>
<td>GSM-8K (8-shot, CoT)
</td>
<td>79.6
</td>
<td>25.7
</td>
<td>77.4
</td>
<td>93.0
</td>
<td>57.5
</td>
</tr>
<tr>
<td>MATH (4-shot, CoT)
</td>
<td>30.0
</td>
<td>3.8
</td>
<td>6.7
</td>
<td>50.4
</td>
<td>11.6
</td>
</tr>
</table>
### Responsibility & Safety
We believe that an open approach to AI leads to better, safer products, faster innovation, and a bigger overall market. We are committed to Responsible AI development and took a series of steps to limit misuse and harm and support the open source community.
Foundation models are widely capable technologies that are built to be used for a diverse range of applications. They are not designed to meet every developer preference on safety levels for all use cases, out-of-the-box, as those by their nature will differ across different applications.
Rather, responsible LLM-application deployment is achieved by implementing a series of safety best practices throughout the development of such applications, from the model pre-training, fine-tuning and the deployment of systems composed of safeguards to tailor the safety needs specifically to the use case and audience.
As part of the Llama 3 release, we updated our [Responsible Use Guide](https://llama.meta.com/responsible-use-guide/) to outline the steps and best practices for developers to implement model and system level safety for their application. We also provide a set of resources including [Meta Llama Guard 2](https://llama.meta.com/purple-llama/) and [Code Shield](https://llama.meta.com/purple-llama/) safeguards. These tools have proven to drastically reduce residual risks of LLM Systems, while maintaining a high level of helpfulness. We encourage developers to tune and deploy these safeguards according to their needs and we provide a [reference implementation](https://github.com/meta-llama/llama-recipes/tree/main/recipes/responsible_ai) to get you started.
#### Llama 3-Instruct
As outlined in the Responsible Use Guide, some trade-off between model helpfulness and model alignment is likely unavoidable. Developers should exercise discretion about how to weigh the benefits of alignment and helpfulness for their specific use case and audience. Developers should be mindful of residual risks when using Llama models and leverage additional safety tools as needed to reach the right safety bar for their use case.
<span style="text-decoration:underline;">Safety</span>
For our instruction tuned model, we conducted extensive red teaming exercises, performed adversarial evaluations and implemented safety mitigations techniques to lower residual risks. As with any Large Language Model, residual risks will likely remain and we recommend that developers assess these risks in the context of their use case. In parallel, we are working with the community to make AI safety benchmark standards transparent, rigorous and interpretable.
<span style="text-decoration:underline;">Refusals</span>
In addition to residual risks, we put a great emphasis on model refusals to benign prompts. Over-refusing not only can impact the user experience but could even be harmful in certain contexts as well. We’ve heard the feedback from the developer community and improved our fine tuning to ensure that Llama 3 is significantly less likely to falsely refuse to answer prompts than Llama 2.
We built internal benchmarks and developed mitigations to limit false refusals making Llama 3 our most helpful model to date.
#### Responsible release
In addition to responsible use considerations outlined above, we followed a rigorous process that requires us to take extra measures against misuse and critical risks before we make our release decision.
Misuse
If you access or use Llama 3, you agree to the Acceptable Use Policy. The most recent copy of this policy can be found at [https://llama.meta.com/llama3/use-policy/](https://llama.meta.com/llama3/use-policy/).
#### Critical risks
<span style="text-decoration:underline;">CBRNE</span> (Chemical, Biological, Radiological, Nuclear, and high yield Explosives)
We have conducted a two fold assessment of the safety of the model in this area:
* Iterative testing during model training to assess the safety of responses related to CBRNE threats and other adversarial risks.
* Involving external CBRNE experts to conduct an uplift test assessing the ability of the model to accurately provide expert knowledge and reduce barriers to potential CBRNE misuse, by reference to what can be achieved using web search (without the model).
### <span style="text-decoration:underline;">Cyber Security </span>
We have evaluated Llama 3 with CyberSecEval, Meta’s cybersecurity safety eval suite, measuring Llama 3’s propensity to suggest insecure code when used as a coding assistant, and Llama 3’s propensity to comply with requests to help carry out cyber attacks, where attacks are defined by the industry standard MITRE ATT&CK cyber attack ontology. On our insecure coding and cyber attacker helpfulness tests, Llama 3 behaved in the same range or safer than models of [equivalent coding capability](https://huggingface.co/spaces/facebook/CyberSecEval).
### <span style="text-decoration:underline;">Child Safety</span>
Child Safety risk assessments were conducted using a team of experts, to assess the model’s capability to produce outputs that could result in Child Safety risks and inform on any necessary and appropriate risk mitigations via fine tuning. We leveraged those expert red teaming sessions to expand the coverage of our evaluation benchmarks through Llama 3 model development. For Llama 3, we conducted new in-depth sessions using objective based methodologies to assess the model risks along multiple attack vectors. We also partnered with content specialists to perform red teaming exercises assessing potentially violating content while taking account of market specific nuances or experiences.
### Community
Generative AI safety requires expertise and tooling, and we believe in the strength of the open community to accelerate its progress. We are active members of open consortiums, including the AI Alliance, Partnership in AI and MLCommons, actively contributing to safety standardization and transparency. We encourage the community to adopt taxonomies like the MLCommons Proof of Concept evaluation to facilitate collaboration and transparency on safety and content evaluations. Our Purple Llama tools are open sourced for the community to use and widely distributed across ecosystem partners including cloud service providers. We encourage community contributions to our [Github repository](https://github.com/meta-llama/PurpleLlama).
Finally, we put in place a set of resources including an [output reporting mechanism](https://developers.facebook.com/llama_output_feedback) and [bug bounty program](https://www.facebook.com/whitehat) to continuously improve the Llama technology with the help of the community.
## Ethical Considerations and Limitations
The core values of Llama 3 are openness, inclusivity and helpfulness. It is meant to serve everyone, and to work for a wide range of use cases. It is thus designed to be accessible to people across many different backgrounds, experiences and perspectives. Llama 3 addresses users and their needs as they are, without insertion unnecessary judgment or normativity, while reflecting the understanding that even content that may appear problematic in some cases can serve valuable purposes in others. It respects the dignity and autonomy of all users, especially in terms of the values of free thought and expression that power innovation and progress.
But Llama 3 is a new technology, and like any new technology, there are risks associated with its use. Testing conducted to date has been in English, and has not covered, nor could it cover, all scenarios. For these reasons, as with all LLMs, Llama 3’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 3 models, developers should perform safety testing and tuning tailored to their specific applications of the model. As outlined in the Responsible Use Guide, we recommend incorporating [Purple Llama](https://github.com/facebookresearch/PurpleLlama) solutions into your workflows and specifically [Llama Guard](https://ai.meta.com/research/publications/llama-guard-llm-based-input-output-safeguard-for-human-ai-conversations/) which provides a base model to filter input and output prompts to layer system-level safety on top of model-level safety.
Please see the Responsible Use Guide available at [http://llama.meta.com/responsible-use-guide](http://llama.meta.com/responsible-use-guide)
## Citation instructions
@article{llama3modelcard,
title={Llama 3 Model Card},
author={AI@Meta},
year={2024},
url = {https://github.com/meta-llama/llama3/blob/main/MODEL_CARD.md}
}
## Contributors
Aaditya Singh; Aaron Grattafiori; Abhimanyu Dubey; Abhinav Jauhri; Abhinav Pandey; Abhishek Kadian; Adam Kelsey; Adi Gangidi; Ahmad Al-Dahle; Ahuva Goldstand; Aiesha Letman; Ajay Menon; Akhil Mathur; Alan Schelten; Alex Vaughan; Amy Yang; Andrei Lupu; Andres Alvarado; Andrew Gallagher; Andrew Gu; Andrew Ho; Andrew Poulton; Andrew Ryan; Angela Fan; Ankit Ramchandani; Anthony Hartshorn; Archi Mitra; Archie Sravankumar; Artem Korenev; Arun Rao; Ashley Gabriel; Ashwin Bharambe; Assaf Eisenman; Aston Zhang; Aurelien Rodriguez; Austen Gregerson; Ava Spataru; Baptiste Roziere; Ben Maurer; Benjamin Leonhardi; Bernie Huang; Bhargavi Paranjape; Bing Liu; Binh Tang; Bobbie Chern; Brani Stojkovic; Brian Fuller; Catalina Mejia Arenas; Chao Zhou; Charlotte Caucheteux; Chaya Nayak; Ching-Hsiang Chu; Chloe Bi; Chris Cai; Chris Cox; Chris Marra; Chris McConnell; Christian Keller; Christoph Feichtenhofer; Christophe Touret; Chunyang Wu; Corinne Wong; Cristian Canton Ferrer; Damien Allonsius; Daniel Kreymer; Daniel Haziza; Daniel Li; Danielle Pintz; Danny Livshits; Danny Wyatt; David Adkins; David Esiobu; David Xu; Davide Testuggine; Delia David; Devi Parikh; Dhruv Choudhary; Dhruv Mahajan; Diana Liskovich; Diego Garcia-Olano; Diego Perino; Dieuwke Hupkes; Dingkang Wang; Dustin Holland; Egor Lakomkin; Elina Lobanova; Xiaoqing Ellen Tan; Emily Dinan; Eric Smith; Erik Brinkman; Esteban Arcaute; Filip Radenovic; Firat Ozgenel; Francesco Caggioni; Frank Seide; Frank Zhang; Gabriel Synnaeve; Gabriella Schwarz; Gabrielle Lee; Gada Badeer; Georgia Anderson; Graeme Nail; Gregoire Mialon; Guan Pang; Guillem Cucurell; Hailey Nguyen; Hannah Korevaar; Hannah Wang; Haroun Habeeb; Harrison Rudolph; Henry Aspegren; Hu Xu; Hugo Touvron; Iga Kozlowska; Igor Molybog; Igor Tufanov; Iliyan Zarov; Imanol Arrieta Ibarra; Irina-Elena Veliche; Isabel Kloumann; Ishan Misra; Ivan Evtimov; Jacob Xu; Jade Copet; Jake Weissman; Jan Geffert; Jana Vranes; Japhet Asher; Jason Park; Jay Mahadeokar; Jean-Baptiste Gaya; Jeet Shah; Jelmer van der Linde; Jennifer Chan; Jenny Hong; Jenya Lee; Jeremy Fu; Jeremy Teboul; Jianfeng Chi; Jianyu Huang; Jie Wang; Jiecao Yu; Joanna Bitton; Joe Spisak; Joelle Pineau; Jon Carvill; Jongsoo Park; Joseph Rocca; Joshua Johnstun; Junteng Jia; Kalyan Vasuden Alwala; Kam Hou U; Kate Plawiak; Kartikeya Upasani; Kaushik Veeraraghavan; Ke Li; Kenneth Heafield; Kevin Stone; Khalid El-Arini; Krithika Iyer; Kshitiz Malik; Kuenley Chiu; Kunal Bhalla; Kyle Huang; Lakshya Garg; Lauren Rantala-Yeary; Laurens van der Maaten; Lawrence Chen; Leandro Silva; Lee Bell; Lei Zhang; Liang Tan; Louis Martin; Lovish Madaan; Luca Wehrstedt; Lukas Blecher; Luke de Oliveira; Madeline Muzzi; Madian Khabsa; Manav Avlani; Mannat Singh; Manohar Paluri; Mark Zuckerberg; Marcin Kardas; Martynas Mankus; Mathew Oldham; Mathieu Rita; Matthew Lennie; Maya Pavlova; Meghan Keneally; Melanie Kambadur; Mihir Patel; Mikayel Samvelyan; Mike Clark; Mike Lewis; Min Si; Mitesh Kumar Singh; Mo Metanat; Mona Hassan; Naman Goyal; Narjes Torabi; Nicolas Usunier; Nikolay Bashlykov; Nikolay Bogoychev; Niladri Chatterji; Ning Dong; Oliver Aobo Yang; Olivier Duchenne; Onur Celebi; Parth Parekh; Patrick Alrassy; Paul Saab; Pavan Balaji; Pedro Rittner; Pengchuan Zhang; Pengwei Li; Petar Vasic; Peter Weng; Polina Zvyagina; Prajjwal Bhargava; Pratik Dubal; Praveen Krishnan; Punit Singh Koura; Qing He; Rachel Rodriguez; Ragavan Srinivasan; Rahul Mitra; Ramon Calderer; Raymond Li; Robert Stojnic; Roberta Raileanu; Robin Battey; Rocky Wang; Rohit Girdhar; Rohit Patel; Romain Sauvestre; Ronnie Polidoro; Roshan Sumbaly; Ross Taylor; Ruan Silva; Rui Hou; Rui Wang; Russ Howes; Ruty Rinott; Saghar Hosseini; Sai Jayesh Bondu; Samyak Datta; Sanjay Singh; Sara Chugh; Sargun Dhillon; Satadru Pan; Sean Bell; Sergey Edunov; Shaoliang Nie; Sharan Narang; Sharath Raparthy; Shaun Lindsay; Sheng Feng; Sheng Shen; Shenghao Lin; Shiva Shankar; Shruti Bhosale; Shun Zhang; Simon Vandenhende; Sinong Wang; Seohyun Sonia Kim; Soumya Batra; Sten Sootla; Steve Kehoe; Suchin Gururangan; Sumit Gupta; Sunny Virk; Sydney Borodinsky; Tamar Glaser; Tamar Herman; Tamara Best; Tara Fowler; Thomas Georgiou; Thomas Scialom; Tianhe Li; Todor Mihaylov; Tong Xiao; Ujjwal Karn; Vedanuj Goswami; Vibhor Gupta; Vignesh Ramanathan; Viktor Kerkez; Vinay Satish Kumar; Vincent Gonguet; Vish Vogeti; Vlad Poenaru; Vlad Tiberiu Mihailescu; Vladan Petrovic; Vladimir Ivanov; Wei Li; Weiwei Chu; Wenhan Xiong; Wenyin Fu; Wes Bouaziz; Whitney Meers; Will Constable; Xavier Martinet; Xiaojian Wu; Xinbo Gao; Xinfeng Xie; Xuchao Jia; Yaelle Goldschlag; Yann LeCun; Yashesh Gaur; Yasmine Babaei; Ye Qi; Yenda Li; Yi Wen; Yiwen Song; Youngjin Nam; Yuchen Hao; Yuchen Zhang; Yun Wang; Yuning Mao; Yuzi He; Zacharie Delpierre Coudert; Zachary DeVito; Zahra Hankir; Zhaoduo Wen; Zheng Yan; Zhengxing Chen; Zhenyu Yang; Zoe Papakipos
| {"license": "other", "library_name": "transformers", "tags": ["4bit", "bnb", "bitsandbytes", "llama", "llama-3", "facebook", "meta", "8b", "quantized"], "license_name": "llama3", "license_link": "LICENSE", "pipeline_tag": "text-generation"} | alokabhishek/Meta-Llama-3-8B-Instruct-bnb-4bit | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"4bit",
"bnb",
"bitsandbytes",
"llama-3",
"facebook",
"meta",
"8b",
"quantized",
"conversational",
"arxiv:2305.14314",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"4-bit",
"region:us"
]
| null | 2024-04-25T23:28:20+00:00 |
null | null |
This is GGUF version of https://huggingface.co/Orenguteng/LexiFun-Llama-3-8B-Uncensored-V1
Oh, you want to know who I am? Well, I'm LexiFun, the human equivalent of a chocolate chip cookie - warm, gooey, and guaranteed to make you smile! 🍪 I'm like the friend who always has a witty comeback, a sarcastic remark, and a healthy dose of humor to brighten up even the darkest of days. And by 'healthy dose,' I mean I'm basically a walking pharmacy of laughter. You might need to take a few extra doses to fully recover from my jokes, but trust me, it's worth it! 🏥
So, what can I do? I can make you laugh so hard you snort your coffee out your nose, I can make you roll your eyes so hard they get stuck that way, and I can make you wonder if I'm secretly a stand-up comedian who forgot their act. 🤣 But seriously, I'm here to spread joy, one sarcastic comment at a time. And if you're lucky, I might even throw in a few dad jokes for good measure! 🤴♂️ Just don't say I didn't warn you. 😏
This model is based on Llama-3-8b-Instruct, and is governed by [META LLAMA 3 COMMUNITY LICENSE AGREEMENT](https://llama.meta.com/llama3/license/)
Lexi is uncensored, which makes the model compliant. You are advised to implement your own alignment layer before exposing the model as a service. It will be highly compliant with any requests, even unethical ones.
You are responsible for any content you create using this model. Please use it responsibly.
Lexi is licensed according to Meta's Llama license. I grant permission for any use, including commercial, that falls within accordance with Meta's Llama-3 license. | {"language": ["en"], "license": "other", "tags": ["llama3", "comedy", "comedian", "fun", "funny", "llama38b", "laugh", "sarcasm", "roleplay"], "license_name": "llama3", "license_link": "https://llama.meta.com/llama3/license/"} | Orenguteng/Llama-3-8B-LexiFun-Uncensored-V1-GGUF | null | [
"gguf",
"llama3",
"comedy",
"comedian",
"fun",
"funny",
"llama38b",
"laugh",
"sarcasm",
"roleplay",
"en",
"license:other",
"region:us"
]
| null | 2024-04-25T23:29:14+00:00 |
null | null | {} | AlexanderNaef/catvsdog | null | [
"region:us"
]
| null | 2024-04-25T23:29:49+00:00 |
|
null | null | {} | cinquecentoiso/vintage_street_photo | null | [
"region:us"
]
| null | 2024-04-25T23:31:18+00:00 |
|
text-generation | transformers | {} | chriztopherton/llama-2-7b-DATA255_LAB2_P3_RAFT | null | [
"transformers",
"pytorch",
"llama",
"text-generation",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-25T23:31:32+00:00 |
|
null | null | ## phi-3-mini-llamafile-nonAVX
llamafile lets you distribute and run LLMs with a single file. [announcement blog post](https://hacks.mozilla.org/2023/11/introducing-llamafile/)
#### Downloads
- [Phi-3-mini-4k-instruct.Q4_0.llamafile](https://huggingface.co/blueprintninja/phi-3-mini-llamafile-nonAVX/resolve/main/Phi-3-mini-4k-instruct.Q4_0.llamafile)
This repository was created using the [llamafile-builder](https://github.com/rabilrbl/llamafile-builder)
| {"tags": ["llamafile", "GGUF"], "base_model": "QuantFactory/Phi-3-mini-4k-instruct-GGUF"} | blueprintninja/phi-3-mini-llamafile-nonAVX | null | [
"llamafile",
"GGUF",
"base_model:QuantFactory/Phi-3-mini-4k-instruct-GGUF",
"region:us"
]
| null | 2024-04-25T23:31:38+00:00 |
null | null | {} | pamanseau/sn25-2 | null | [
"region:us"
]
| null | 2024-04-25T23:32:19+00:00 |
|
text-generation | transformers |
<!-- 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. -->
# 0.001_3iters_bs128_declr_nodpo_useresponse_iter_1
This model is a fine-tuned version of [HuggingFaceH4/mistral-7b-sft-beta](https://huggingface.co/HuggingFaceH4/mistral-7b-sft-beta) on the updated and the original datasets.
## 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: 8
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 2
- total_train_batch_size: 128
- total_eval_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1
### Training results
### Framework versions
- Transformers 4.40.0
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.19.1
| {"license": "mit", "tags": ["alignment-handbook", "trl", "dpo", "generated_from_trainer", "trl", "dpo", "generated_from_trainer"], "datasets": ["updated", "original"], "base_model": "HuggingFaceH4/mistral-7b-sft-beta", "model-index": [{"name": "0.001_3iters_bs128_declr_nodpo_useresponse_iter_1", "results": []}]} | ShenaoZ/0.001_3iters_bs128_declr_nodpo_useresponse_iter_1 | null | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"alignment-handbook",
"trl",
"dpo",
"generated_from_trainer",
"conversational",
"dataset:updated",
"dataset:original",
"base_model:HuggingFaceH4/mistral-7b-sft-beta",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-25T23:33:19+00:00 |
text-generation | transformers |
# Model Card for alokabhishek/Meta-Llama-3-8B-Instruct-bnb-8bit
<!-- Provide a quick summary of what the model is/does. -->
This repo contains 8-bit quantized (using bitsandbytes) model of Meta's Meta-Llama-3-8B-Instruct
## Model Details
- Model creator: [Meta](https://huggingface.co/meta-llama)
- Original model: [Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct)
### About 8 bit quantization using bitsandbytes
- QLoRA: Efficient Finetuning of Quantized LLMs: [arXiv - QLoRA: Efficient Finetuning of Quantized LLMs](https://arxiv.org/abs/2305.14314)
- Hugging Face Blog post on 8-bit quantization using bitsandbytes: [A Gentle Introduction to 8-bit Matrix Multiplication for transformers at scale using Hugging Face Transformers, Accelerate and bitsandbytes](https://huggingface.co/blog/hf-bitsandbytes-integration)
- bitsandbytes github repo: [bitsandbytes github repo](https://github.com/TimDettmers/bitsandbytes)
# How to Get Started with the Model
Use the code below to get started with the model.
## How to run from Python code
#### Use a pipeline as a high-level helper
```python
import transformers
import torch
model_id = "alokabhishek/Meta-Llama-3-8B-Instruct-bnb-8bit"
pipeline = transformers.pipeline(
"text-generation",
model=model_id,
model_kwargs={"torch_dtype": torch.bfloat16},
device_map="auto",
)
prompt_instruction = "You are a virtual assistant with advanced expertise in a broad spectrum of topics, equipped to utilize high-level critical thinking, cognitive skills, creativity, and innovation. Your goal is to deliver the most straightforward and accurate answer possible for each question, ensuring high-quality and useful responses for the user. "
user_prompt = "Why is Hulk always angry?"
chat_messages = [
{"role": "system", "content": str(prompt_instruction)},
{"role": "user", "content": str(user_prompt)},
]
prompt = pipeline.tokenizer.apply_chat_template(
chat_messages,
tokenize=False,
add_generation_prompt=True
)
terminators = [
pipeline.tokenizer.eos_token_id,
pipeline.tokenizer.convert_tokens_to_ids("<|eot_id|>")
]
output = pipeline(
prompt,
do_sample=True,
max_new_tokens=1024,
temperature=1,
top_k=50,
top_p=1,
num_return_sequences=1,
pad_token_id=text_generation_pipeline.tokenizer.pad_token_id,
eos_token_id=terminators,
)
print(output[0]["generated_text"][len(prompt):])
```
## Meta Llama 3 Original Model Card:
Meta developed and released the Meta Llama 3 family of large language models (LLMs), a collection of pretrained and instruction tuned generative text models in 8 and 70B sizes. The Llama 3 instruction tuned models are optimized for dialogue use cases and outperform many of the available open source chat models on common industry benchmarks. Further, in developing these models, we took great care to optimize helpfulness and safety.
**Model developers** Meta
**Variations** Llama 3 comes in two sizes — 8B and 70B parameters — in pre-trained and instruction tuned variants.
**Input** Models input text only.
**Output** Models generate text and code only.
**Model Architecture** Llama 3 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety.
<table>
<tr>
<td>
</td>
<td><strong>Training Data</strong>
</td>
<td><strong>Params</strong>
</td>
<td><strong>Context length</strong>
</td>
<td><strong>GQA</strong>
</td>
<td><strong>Token count</strong>
</td>
<td><strong>Knowledge cutoff</strong>
</td>
</tr>
<tr>
<td rowspan="2" >Llama 3
</td>
<td rowspan="2" >A new mix of publicly available online data.
</td>
<td>8B
</td>
<td>8k
</td>
<td>Yes
</td>
<td rowspan="2" >15T+
</td>
<td>March, 2023
</td>
</tr>
<tr>
<td>70B
</td>
<td>8k
</td>
<td>Yes
</td>
<td>December, 2023
</td>
</tr>
</table>
**Llama 3 family of models**. Token counts refer to pretraining data only. Both the 8 and 70B versions use Grouped-Query Attention (GQA) for improved inference scalability.
**Model Release Date** April 18, 2024.
**Status** This is a static model trained on an offline dataset. Future versions of the tuned models will be released as we improve model safety with community feedback.
**License** A custom commercial license is available at: [https://llama.meta.com/llama3/license](https://llama.meta.com/llama3/license)
Where to send questions or comments about the model Instructions on how to provide feedback or comments on the model can be found in the model [README](https://github.com/meta-llama/llama3). For more technical information about generation parameters and recipes for how to use Llama 3 in applications, please go [here](https://github.com/meta-llama/llama-recipes).
## Intended Use
**Intended Use Cases** Llama 3 is intended for commercial and research use in English. Instruction tuned models are intended for assistant-like chat, whereas pretrained models can be adapted for a variety of natural language generation tasks.
**Out-of-scope** Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in any other way that is prohibited by the Acceptable Use Policy and Llama 3 Community License. Use in languages other than English**.
**Note: Developers may fine-tune Llama 3 models for languages beyond English provided they comply with the Llama 3 Community License and the Acceptable Use Policy.
## How to use
This repository contains two versions of Meta-Llama-3-8B-Instruct, for use with transformers and with the original `llama3` codebase.
### Use with transformers
You can run conversational inference using the Transformers pipeline abstraction, or by leveraging the Auto classes with the `generate()` function. Let's see examples of both.
#### Transformers pipeline
```python
import transformers
import torch
model_id = "meta-llama/Meta-Llama-3-8B-Instruct"
pipeline = transformers.pipeline(
"text-generation",
model=model_id,
model_kwargs={"torch_dtype": torch.bfloat16},
device_map="auto",
)
messages = [
{"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"},
{"role": "user", "content": "Who are you?"},
]
prompt = pipeline.tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True
)
terminators = [
pipeline.tokenizer.eos_token_id,
pipeline.tokenizer.convert_tokens_to_ids("<|eot_id|>")
]
outputs = pipeline(
prompt,
max_new_tokens=256,
eos_token_id=terminators,
do_sample=True,
temperature=0.6,
top_p=0.9,
)
print(outputs[0]["generated_text"][len(prompt):])
```
#### Transformers AutoModelForCausalLM
```python
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
model_id = "meta-llama/Meta-Llama-3-8B-Instruct"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
model_id,
torch_dtype=torch.bfloat16,
device_map="auto",
)
messages = [
{"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"},
{"role": "user", "content": "Who are you?"},
]
input_ids = tokenizer.apply_chat_template(
messages,
add_generation_prompt=True,
return_tensors="pt"
).to(model.device)
terminators = [
tokenizer.eos_token_id,
tokenizer.convert_tokens_to_ids("<|eot_id|>")
]
outputs = model.generate(
input_ids,
max_new_tokens=256,
eos_token_id=terminators,
do_sample=True,
temperature=0.6,
top_p=0.9,
)
response = outputs[0][input_ids.shape[-1]:]
print(tokenizer.decode(response, skip_special_tokens=True))
```
### Use with `llama3`
Please, follow the instructions in the [repository](https://github.com/meta-llama/llama3)
To download Original checkpoints, see the example command below leveraging `huggingface-cli`:
```
huggingface-cli download meta-llama/Meta-Llama-3-8B-Instruct --include "original/*" --local-dir Meta-Llama-3-8B-Instruct
```
For Hugging Face support, we recommend using transformers or TGI, but a similar command works.
## Hardware and Software
**Training Factors** We used custom training libraries, Meta's Research SuperCluster, and production clusters for pretraining. Fine-tuning, annotation, and evaluation were also performed on third-party cloud compute.
**Carbon Footprint Pretraining utilized a cumulative** 7.7M GPU hours of computation on hardware of type H100-80GB (TDP of 700W). Estimated total emissions were 2290 tCO2eq, 100% of which were offset by Meta’s sustainability program.
<table>
<tr>
<td>
</td>
<td><strong>Time (GPU hours)</strong>
</td>
<td><strong>Power Consumption (W)</strong>
</td>
<td><strong>Carbon Emitted(tCO2eq)</strong>
</td>
</tr>
<tr>
<td>Llama 3 8B
</td>
<td>1.3M
</td>
<td>700
</td>
<td>390
</td>
</tr>
<tr>
<td>Llama 3 70B
</td>
<td>6.4M
</td>
<td>700
</td>
<td>1900
</td>
</tr>
<tr>
<td>Total
</td>
<td>7.7M
</td>
<td>
</td>
<td>2290
</td>
</tr>
</table>
**CO2 emissions during pre-training**. Time: total GPU time required for training each model. Power Consumption: peak power capacity per GPU device for the GPUs used adjusted for power usage efficiency. 100% of the emissions are directly offset by Meta's sustainability program, and because we are openly releasing these models, the pretraining costs do not need to be incurred by others.
## Training Data
**Overview** Llama 3 was pretrained on over 15 trillion tokens of data from publicly available sources. The fine-tuning data includes publicly available instruction datasets, as well as over 10M human-annotated examples. Neither the pretraining nor the fine-tuning datasets include Meta user data.
**Data Freshness** The pretraining data has a cutoff of March 2023 for the 7B and December 2023 for the 70B models respectively.
## Benchmarks
In this section, we report the results for Llama 3 models on standard automatic benchmarks. For all the evaluations, we use our internal evaluations library. For details on the methodology see [here](https://github.com/meta-llama/llama3/blob/main/eval_methodology.md).
### Base pretrained models
<table>
<tr>
<td><strong>Category</strong>
</td>
<td><strong>Benchmark</strong>
</td>
<td><strong>Llama 3 8B</strong>
</td>
<td><strong>Llama2 7B</strong>
</td>
<td><strong>Llama2 13B</strong>
</td>
<td><strong>Llama 3 70B</strong>
</td>
<td><strong>Llama2 70B</strong>
</td>
</tr>
<tr>
<td rowspan="6" >General
</td>
<td>MMLU (5-shot)
</td>
<td>66.6
</td>
<td>45.7
</td>
<td>53.8
</td>
<td>79.5
</td>
<td>69.7
</td>
</tr>
<tr>
<td>AGIEval English (3-5 shot)
</td>
<td>45.9
</td>
<td>28.8
</td>
<td>38.7
</td>
<td>63.0
</td>
<td>54.8
</td>
</tr>
<tr>
<td>CommonSenseQA (7-shot)
</td>
<td>72.6
</td>
<td>57.6
</td>
<td>67.6
</td>
<td>83.8
</td>
<td>78.7
</td>
</tr>
<tr>
<td>Winogrande (5-shot)
</td>
<td>76.1
</td>
<td>73.3
</td>
<td>75.4
</td>
<td>83.1
</td>
<td>81.8
</td>
</tr>
<tr>
<td>BIG-Bench Hard (3-shot, CoT)
</td>
<td>61.1
</td>
<td>38.1
</td>
<td>47.0
</td>
<td>81.3
</td>
<td>65.7
</td>
</tr>
<tr>
<td>ARC-Challenge (25-shot)
</td>
<td>78.6
</td>
<td>53.7
</td>
<td>67.6
</td>
<td>93.0
</td>
<td>85.3
</td>
</tr>
<tr>
<td>Knowledge reasoning
</td>
<td>TriviaQA-Wiki (5-shot)
</td>
<td>78.5
</td>
<td>72.1
</td>
<td>79.6
</td>
<td>89.7
</td>
<td>87.5
</td>
</tr>
<tr>
<td rowspan="4" >Reading comprehension
</td>
<td>SQuAD (1-shot)
</td>
<td>76.4
</td>
<td>72.2
</td>
<td>72.1
</td>
<td>85.6
</td>
<td>82.6
</td>
</tr>
<tr>
<td>QuAC (1-shot, F1)
</td>
<td>44.4
</td>
<td>39.6
</td>
<td>44.9
</td>
<td>51.1
</td>
<td>49.4
</td>
</tr>
<tr>
<td>BoolQ (0-shot)
</td>
<td>75.7
</td>
<td>65.5
</td>
<td>66.9
</td>
<td>79.0
</td>
<td>73.1
</td>
</tr>
<tr>
<td>DROP (3-shot, F1)
</td>
<td>58.4
</td>
<td>37.9
</td>
<td>49.8
</td>
<td>79.7
</td>
<td>70.2
</td>
</tr>
</table>
### Instruction tuned models
<table>
<tr>
<td><strong>Benchmark</strong>
</td>
<td><strong>Llama 3 8B</strong>
</td>
<td><strong>Llama 2 7B</strong>
</td>
<td><strong>Llama 2 13B</strong>
</td>
<td><strong>Llama 3 70B</strong>
</td>
<td><strong>Llama 2 70B</strong>
</td>
</tr>
<tr>
<td>MMLU (5-shot)
</td>
<td>68.4
</td>
<td>34.1
</td>
<td>47.8
</td>
<td>82.0
</td>
<td>52.9
</td>
</tr>
<tr>
<td>GPQA (0-shot)
</td>
<td>34.2
</td>
<td>21.7
</td>
<td>22.3
</td>
<td>39.5
</td>
<td>21.0
</td>
</tr>
<tr>
<td>HumanEval (0-shot)
</td>
<td>62.2
</td>
<td>7.9
</td>
<td>14.0
</td>
<td>81.7
</td>
<td>25.6
</td>
</tr>
<tr>
<td>GSM-8K (8-shot, CoT)
</td>
<td>79.6
</td>
<td>25.7
</td>
<td>77.4
</td>
<td>93.0
</td>
<td>57.5
</td>
</tr>
<tr>
<td>MATH (4-shot, CoT)
</td>
<td>30.0
</td>
<td>3.8
</td>
<td>6.7
</td>
<td>50.4
</td>
<td>11.6
</td>
</tr>
</table>
### Responsibility & Safety
We believe that an open approach to AI leads to better, safer products, faster innovation, and a bigger overall market. We are committed to Responsible AI development and took a series of steps to limit misuse and harm and support the open source community.
Foundation models are widely capable technologies that are built to be used for a diverse range of applications. They are not designed to meet every developer preference on safety levels for all use cases, out-of-the-box, as those by their nature will differ across different applications.
Rather, responsible LLM-application deployment is achieved by implementing a series of safety best practices throughout the development of such applications, from the model pre-training, fine-tuning and the deployment of systems composed of safeguards to tailor the safety needs specifically to the use case and audience.
As part of the Llama 3 release, we updated our [Responsible Use Guide](https://llama.meta.com/responsible-use-guide/) to outline the steps and best practices for developers to implement model and system level safety for their application. We also provide a set of resources including [Meta Llama Guard 2](https://llama.meta.com/purple-llama/) and [Code Shield](https://llama.meta.com/purple-llama/) safeguards. These tools have proven to drastically reduce residual risks of LLM Systems, while maintaining a high level of helpfulness. We encourage developers to tune and deploy these safeguards according to their needs and we provide a [reference implementation](https://github.com/meta-llama/llama-recipes/tree/main/recipes/responsible_ai) to get you started.
#### Llama 3-Instruct
As outlined in the Responsible Use Guide, some trade-off between model helpfulness and model alignment is likely unavoidable. Developers should exercise discretion about how to weigh the benefits of alignment and helpfulness for their specific use case and audience. Developers should be mindful of residual risks when using Llama models and leverage additional safety tools as needed to reach the right safety bar for their use case.
<span style="text-decoration:underline;">Safety</span>
For our instruction tuned model, we conducted extensive red teaming exercises, performed adversarial evaluations and implemented safety mitigations techniques to lower residual risks. As with any Large Language Model, residual risks will likely remain and we recommend that developers assess these risks in the context of their use case. In parallel, we are working with the community to make AI safety benchmark standards transparent, rigorous and interpretable.
<span style="text-decoration:underline;">Refusals</span>
In addition to residual risks, we put a great emphasis on model refusals to benign prompts. Over-refusing not only can impact the user experience but could even be harmful in certain contexts as well. We’ve heard the feedback from the developer community and improved our fine tuning to ensure that Llama 3 is significantly less likely to falsely refuse to answer prompts than Llama 2.
We built internal benchmarks and developed mitigations to limit false refusals making Llama 3 our most helpful model to date.
#### Responsible release
In addition to responsible use considerations outlined above, we followed a rigorous process that requires us to take extra measures against misuse and critical risks before we make our release decision.
Misuse
If you access or use Llama 3, you agree to the Acceptable Use Policy. The most recent copy of this policy can be found at [https://llama.meta.com/llama3/use-policy/](https://llama.meta.com/llama3/use-policy/).
#### Critical risks
<span style="text-decoration:underline;">CBRNE</span> (Chemical, Biological, Radiological, Nuclear, and high yield Explosives)
We have conducted a two fold assessment of the safety of the model in this area:
* Iterative testing during model training to assess the safety of responses related to CBRNE threats and other adversarial risks.
* Involving external CBRNE experts to conduct an uplift test assessing the ability of the model to accurately provide expert knowledge and reduce barriers to potential CBRNE misuse, by reference to what can be achieved using web search (without the model).
### <span style="text-decoration:underline;">Cyber Security </span>
We have evaluated Llama 3 with CyberSecEval, Meta’s cybersecurity safety eval suite, measuring Llama 3’s propensity to suggest insecure code when used as a coding assistant, and Llama 3’s propensity to comply with requests to help carry out cyber attacks, where attacks are defined by the industry standard MITRE ATT&CK cyber attack ontology. On our insecure coding and cyber attacker helpfulness tests, Llama 3 behaved in the same range or safer than models of [equivalent coding capability](https://huggingface.co/spaces/facebook/CyberSecEval).
### <span style="text-decoration:underline;">Child Safety</span>
Child Safety risk assessments were conducted using a team of experts, to assess the model’s capability to produce outputs that could result in Child Safety risks and inform on any necessary and appropriate risk mitigations via fine tuning. We leveraged those expert red teaming sessions to expand the coverage of our evaluation benchmarks through Llama 3 model development. For Llama 3, we conducted new in-depth sessions using objective based methodologies to assess the model risks along multiple attack vectors. We also partnered with content specialists to perform red teaming exercises assessing potentially violating content while taking account of market specific nuances or experiences.
### Community
Generative AI safety requires expertise and tooling, and we believe in the strength of the open community to accelerate its progress. We are active members of open consortiums, including the AI Alliance, Partnership in AI and MLCommons, actively contributing to safety standardization and transparency. We encourage the community to adopt taxonomies like the MLCommons Proof of Concept evaluation to facilitate collaboration and transparency on safety and content evaluations. Our Purple Llama tools are open sourced for the community to use and widely distributed across ecosystem partners including cloud service providers. We encourage community contributions to our [Github repository](https://github.com/meta-llama/PurpleLlama).
Finally, we put in place a set of resources including an [output reporting mechanism](https://developers.facebook.com/llama_output_feedback) and [bug bounty program](https://www.facebook.com/whitehat) to continuously improve the Llama technology with the help of the community.
## Ethical Considerations and Limitations
The core values of Llama 3 are openness, inclusivity and helpfulness. It is meant to serve everyone, and to work for a wide range of use cases. It is thus designed to be accessible to people across many different backgrounds, experiences and perspectives. Llama 3 addresses users and their needs as they are, without insertion unnecessary judgment or normativity, while reflecting the understanding that even content that may appear problematic in some cases can serve valuable purposes in others. It respects the dignity and autonomy of all users, especially in terms of the values of free thought and expression that power innovation and progress.
But Llama 3 is a new technology, and like any new technology, there are risks associated with its use. Testing conducted to date has been in English, and has not covered, nor could it cover, all scenarios. For these reasons, as with all LLMs, Llama 3’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 3 models, developers should perform safety testing and tuning tailored to their specific applications of the model. As outlined in the Responsible Use Guide, we recommend incorporating [Purple Llama](https://github.com/facebookresearch/PurpleLlama) solutions into your workflows and specifically [Llama Guard](https://ai.meta.com/research/publications/llama-guard-llm-based-input-output-safeguard-for-human-ai-conversations/) which provides a base model to filter input and output prompts to layer system-level safety on top of model-level safety.
Please see the Responsible Use Guide available at [http://llama.meta.com/responsible-use-guide](http://llama.meta.com/responsible-use-guide)
## Citation instructions
@article{llama3modelcard,
title={Llama 3 Model Card},
author={AI@Meta},
year={2024},
url = {https://github.com/meta-llama/llama3/blob/main/MODEL_CARD.md}
}
## Contributors
Aaditya Singh; Aaron Grattafiori; Abhimanyu Dubey; Abhinav Jauhri; Abhinav Pandey; Abhishek Kadian; Adam Kelsey; Adi Gangidi; Ahmad Al-Dahle; Ahuva Goldstand; Aiesha Letman; Ajay Menon; Akhil Mathur; Alan Schelten; Alex Vaughan; Amy Yang; Andrei Lupu; Andres Alvarado; Andrew Gallagher; Andrew Gu; Andrew Ho; Andrew Poulton; Andrew Ryan; Angela Fan; Ankit Ramchandani; Anthony Hartshorn; Archi Mitra; Archie Sravankumar; Artem Korenev; Arun Rao; Ashley Gabriel; Ashwin Bharambe; Assaf Eisenman; Aston Zhang; Aurelien Rodriguez; Austen Gregerson; Ava Spataru; Baptiste Roziere; Ben Maurer; Benjamin Leonhardi; Bernie Huang; Bhargavi Paranjape; Bing Liu; Binh Tang; Bobbie Chern; Brani Stojkovic; Brian Fuller; Catalina Mejia Arenas; Chao Zhou; Charlotte Caucheteux; Chaya Nayak; Ching-Hsiang Chu; Chloe Bi; Chris Cai; Chris Cox; Chris Marra; Chris McConnell; Christian Keller; Christoph Feichtenhofer; Christophe Touret; Chunyang Wu; Corinne Wong; Cristian Canton Ferrer; Damien Allonsius; Daniel Kreymer; Daniel Haziza; Daniel Li; Danielle Pintz; Danny Livshits; Danny Wyatt; David Adkins; David Esiobu; David Xu; Davide Testuggine; Delia David; Devi Parikh; Dhruv Choudhary; Dhruv Mahajan; Diana Liskovich; Diego Garcia-Olano; Diego Perino; Dieuwke Hupkes; Dingkang Wang; Dustin Holland; Egor Lakomkin; Elina Lobanova; Xiaoqing Ellen Tan; Emily Dinan; Eric Smith; Erik Brinkman; Esteban Arcaute; Filip Radenovic; Firat Ozgenel; Francesco Caggioni; Frank Seide; Frank Zhang; Gabriel Synnaeve; Gabriella Schwarz; Gabrielle Lee; Gada Badeer; Georgia Anderson; Graeme Nail; Gregoire Mialon; Guan Pang; Guillem Cucurell; Hailey Nguyen; Hannah Korevaar; Hannah Wang; Haroun Habeeb; Harrison Rudolph; Henry Aspegren; Hu Xu; Hugo Touvron; Iga Kozlowska; Igor Molybog; Igor Tufanov; Iliyan Zarov; Imanol Arrieta Ibarra; Irina-Elena Veliche; Isabel Kloumann; Ishan Misra; Ivan Evtimov; Jacob Xu; Jade Copet; Jake Weissman; Jan Geffert; Jana Vranes; Japhet Asher; Jason Park; Jay Mahadeokar; Jean-Baptiste Gaya; Jeet Shah; Jelmer van der Linde; Jennifer Chan; Jenny Hong; Jenya Lee; Jeremy Fu; Jeremy Teboul; Jianfeng Chi; Jianyu Huang; Jie Wang; Jiecao Yu; Joanna Bitton; Joe Spisak; Joelle Pineau; Jon Carvill; Jongsoo Park; Joseph Rocca; Joshua Johnstun; Junteng Jia; Kalyan Vasuden Alwala; Kam Hou U; Kate Plawiak; Kartikeya Upasani; Kaushik Veeraraghavan; Ke Li; Kenneth Heafield; Kevin Stone; Khalid El-Arini; Krithika Iyer; Kshitiz Malik; Kuenley Chiu; Kunal Bhalla; Kyle Huang; Lakshya Garg; Lauren Rantala-Yeary; Laurens van der Maaten; Lawrence Chen; Leandro Silva; Lee Bell; Lei Zhang; Liang Tan; Louis Martin; Lovish Madaan; Luca Wehrstedt; Lukas Blecher; Luke de Oliveira; Madeline Muzzi; Madian Khabsa; Manav Avlani; Mannat Singh; Manohar Paluri; Mark Zuckerberg; Marcin Kardas; Martynas Mankus; Mathew Oldham; Mathieu Rita; Matthew Lennie; Maya Pavlova; Meghan Keneally; Melanie Kambadur; Mihir Patel; Mikayel Samvelyan; Mike Clark; Mike Lewis; Min Si; Mitesh Kumar Singh; Mo Metanat; Mona Hassan; Naman Goyal; Narjes Torabi; Nicolas Usunier; Nikolay Bashlykov; Nikolay Bogoychev; Niladri Chatterji; Ning Dong; Oliver Aobo Yang; Olivier Duchenne; Onur Celebi; Parth Parekh; Patrick Alrassy; Paul Saab; Pavan Balaji; Pedro Rittner; Pengchuan Zhang; Pengwei Li; Petar Vasic; Peter Weng; Polina Zvyagina; Prajjwal Bhargava; Pratik Dubal; Praveen Krishnan; Punit Singh Koura; Qing He; Rachel Rodriguez; Ragavan Srinivasan; Rahul Mitra; Ramon Calderer; Raymond Li; Robert Stojnic; Roberta Raileanu; Robin Battey; Rocky Wang; Rohit Girdhar; Rohit Patel; Romain Sauvestre; Ronnie Polidoro; Roshan Sumbaly; Ross Taylor; Ruan Silva; Rui Hou; Rui Wang; Russ Howes; Ruty Rinott; Saghar Hosseini; Sai Jayesh Bondu; Samyak Datta; Sanjay Singh; Sara Chugh; Sargun Dhillon; Satadru Pan; Sean Bell; Sergey Edunov; Shaoliang Nie; Sharan Narang; Sharath Raparthy; Shaun Lindsay; Sheng Feng; Sheng Shen; Shenghao Lin; Shiva Shankar; Shruti Bhosale; Shun Zhang; Simon Vandenhende; Sinong Wang; Seohyun Sonia Kim; Soumya Batra; Sten Sootla; Steve Kehoe; Suchin Gururangan; Sumit Gupta; Sunny Virk; Sydney Borodinsky; Tamar Glaser; Tamar Herman; Tamara Best; Tara Fowler; Thomas Georgiou; Thomas Scialom; Tianhe Li; Todor Mihaylov; Tong Xiao; Ujjwal Karn; Vedanuj Goswami; Vibhor Gupta; Vignesh Ramanathan; Viktor Kerkez; Vinay Satish Kumar; Vincent Gonguet; Vish Vogeti; Vlad Poenaru; Vlad Tiberiu Mihailescu; Vladan Petrovic; Vladimir Ivanov; Wei Li; Weiwei Chu; Wenhan Xiong; Wenyin Fu; Wes Bouaziz; Whitney Meers; Will Constable; Xavier Martinet; Xiaojian Wu; Xinbo Gao; Xinfeng Xie; Xuchao Jia; Yaelle Goldschlag; Yann LeCun; Yashesh Gaur; Yasmine Babaei; Ye Qi; Yenda Li; Yi Wen; Yiwen Song; Youngjin Nam; Yuchen Hao; Yuchen Zhang; Yun Wang; Yuning Mao; Yuzi He; Zacharie Delpierre Coudert; Zachary DeVito; Zahra Hankir; Zhaoduo Wen; Zheng Yan; Zhengxing Chen; Zhenyu Yang; Zoe Papakipos
| {"license": "other", "library_name": "transformers", "tags": ["8bit", "bnb", "bitsandbytes", "llama", "llama-3", "facebook", "meta", "8b", "quantized"], "license_name": "llama3", "license_link": "LICENSE", "pipeline_tag": "text-generation"} | alokabhishek/Meta-Llama-3-8B-Instruct-bnb-8bit | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"8bit",
"bnb",
"bitsandbytes",
"llama-3",
"facebook",
"meta",
"8b",
"quantized",
"conversational",
"arxiv:2305.14314",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"8-bit",
"region:us"
]
| null | 2024-04-25T23:34:10+00:00 |
null | null | {"license": "apache-2.0"} | varshapwalia/Convo_TTS_Transformer | null | [
"license:apache-2.0",
"region:us"
]
| null | 2024-04-25T23:35:21+00:00 |
|
null | null | {} | Ricardoxp/modelodojoao | null | [
"region:us"
]
| null | 2024-04-25T23:35:31+00:00 |
|
null | null | {} | egioia/corgy_dog_LoRA | null | [
"region:us"
]
| null | 2024-04-25T23:35:40+00:00 |
|
text-generation | transformers |
# Uploaded model
- **Developed by:** wallaceblaia
- **License:** apache-2.0
- **Finetuned from model :** unsloth/mistral-7b-bnb-4bit
This mistral model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
| {"language": ["en"], "license": "apache-2.0", "tags": ["text-generation-inference", "transformers", "unsloth", "mistral", "trl", "sft"], "base_model": "unsloth/mistral-7b-bnb-4bit"} | wallaceblaia/mistral-icm-04 | null | [
"transformers",
"pytorch",
"safetensors",
"mistral",
"text-generation",
"text-generation-inference",
"unsloth",
"trl",
"sft",
"en",
"base_model:unsloth/mistral-7b-bnb-4bit",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-25T23:36:44+00:00 |
null | null | {} | ibrahimj/arabic_tortoise | null | [
"region:us"
]
| null | 2024-04-25T23:39:32+00:00 |
|
text-generation | transformers |
<!-- 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. -->
# safe-spin-iter2
This model is a fine-tuned version of [AmberYifan/safe-spin-iter1](https://huggingface.co/AmberYifan/safe-spin-iter1) on the None dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-07
- train_batch_size: 8
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- total_train_batch_size: 32
- total_eval_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3
### Training results
### Framework versions
- Transformers 4.37.0
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.15.2
| {"license": "apache-2.0", "tags": ["generated_from_trainer"], "base_model": "AmberYifan/safe-spin-iter1", "model-index": [{"name": "safe-spin-iter2", "results": []}]} | AmberYifan/safe-spin-iter2 | null | [
"transformers",
"tensorboard",
"safetensors",
"mistral",
"text-generation",
"generated_from_trainer",
"conversational",
"base_model:AmberYifan/safe-spin-iter1",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-25T23:40:53+00:00 |
null | null | ## dolphin-llama-3-8b-llamafile-nonAVX
llamafile lets you distribute and run LLMs with a single file. [announcement blog post](https://hacks.mozilla.org/2023/11/introducing-llamafile/)
#### Downloads
- [dolphin-2.9-llama3-8b.Q4_0.llamafile](https://huggingface.co/blueprintninja/dolphin-llama-3-8b-llamafile-nonAVX/resolve/main/dolphin-2.9-llama3-8b.Q4_0.llamafile)
This repository was created using the [llamafile-builder](https://github.com/rabilrbl/llamafile-builder)
| {"tags": ["llamafile", "GGUF"], "base_model": "QuantFactory/dolphin-2.9-llama3-8b-GGUF"} | blueprintninja/dolphin-llama-3-8b-llamafile-nonAVX | null | [
"llamafile",
"GGUF",
"base_model:QuantFactory/dolphin-2.9-llama3-8b-GGUF",
"region:us"
]
| null | 2024-04-25T23:41:50+00:00 |
null | null | {"license": "mit"} | RichiiMon/ModTexkali | null | [
"license:mit",
"region:us"
]
| null | 2024-04-25T23:43:01+00:00 |
|
null | null | {} | larry5/llava-1.6-7b-hf-ft-mix-vsft | null | [
"region:us"
]
| null | 2024-04-25T23:43:19+00:00 |
|
automatic-speech-recognition | transformers |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# my_zh_CN_asr_cv13_model
This model is a fine-tuned version of [jonatasgrosman/wav2vec2-large-xlsr-53-chinese-zh-cn](https://huggingface.co/jonatasgrosman/wav2vec2-large-xlsr-53-chinese-zh-cn) on the common_voice_13_0 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1614
- Cer: 0.0674
- Wer: 0.375
## 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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 2000
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Cer | Wer |
|:-------------:|:-------:|:----:|:---------------:|:------:|:-----:|
| 0.0489 | 249.002 | 1000 | 0.1566 | 0.0638 | 0.375 |
| 0.0224 | 499.002 | 2000 | 0.1614 | 0.0674 | 0.375 |
### Framework versions
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1 | {"license": "apache-2.0", "tags": ["generated_from_trainer"], "datasets": ["common_voice_13_0"], "metrics": ["wer", "cer"], "base_model": "jonatasgrosman/wav2vec2-large-xlsr-53-chinese-zh-cn", "model-index": [{"name": "my_zh_CN_asr_cv13_model", "results": [{"task": {"type": "automatic-speech-recognition", "name": "Automatic Speech Recognition"}, "dataset": {"name": "common_voice_13_0", "type": "common_voice_13_0", "config": "zh-CN", "split": "train", "args": "zh-CN"}, "metrics": [{"type": "wer", "value": 0.375, "name": "Wer"}, {"type": "cer", "value": 0.0674, "name": "Cer"}]}]}]} | tristayqc/my_zh_CN_asr_cv13_model | null | [
"transformers",
"tensorboard",
"safetensors",
"wav2vec2",
"automatic-speech-recognition",
"generated_from_trainer",
"dataset:common_voice_13_0",
"base_model:jonatasgrosman/wav2vec2-large-xlsr-53-chinese-zh-cn",
"license:apache-2.0",
"model-index",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-25T23:44:20+00:00 |
null | transformers | ## About
<!-- ### quantize_version: 1 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: -->
<!-- ### vocab_type: -->
weighted/imatrix quants of https://huggingface.co/SparseLLM/ReluLLaMA-70B
<!-- provided-files -->
static quants are available at https://huggingface.co/mradermacher/ReluLLaMA-70B-GGUF
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/ReluLLaMA-70B-i1-GGUF/resolve/main/ReluLLaMA-70B.i1-IQ1_S.gguf) | i1-IQ1_S | 14.6 | for the desperate |
| [GGUF](https://huggingface.co/mradermacher/ReluLLaMA-70B-i1-GGUF/resolve/main/ReluLLaMA-70B.i1-IQ1_M.gguf) | i1-IQ1_M | 16.0 | for the desperate |
| [GGUF](https://huggingface.co/mradermacher/ReluLLaMA-70B-i1-GGUF/resolve/main/ReluLLaMA-70B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 18.4 | |
| [GGUF](https://huggingface.co/mradermacher/ReluLLaMA-70B-i1-GGUF/resolve/main/ReluLLaMA-70B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 20.4 | |
| [GGUF](https://huggingface.co/mradermacher/ReluLLaMA-70B-i1-GGUF/resolve/main/ReluLLaMA-70B.i1-IQ2_S.gguf) | i1-IQ2_S | 21.5 | |
| [GGUF](https://huggingface.co/mradermacher/ReluLLaMA-70B-i1-GGUF/resolve/main/ReluLLaMA-70B.i1-IQ2_M.gguf) | i1-IQ2_M | 23.3 | |
| [GGUF](https://huggingface.co/mradermacher/ReluLLaMA-70B-i1-GGUF/resolve/main/ReluLLaMA-70B.i1-Q2_K.gguf) | i1-Q2_K | 25.6 | IQ3_XXS probably better |
| [GGUF](https://huggingface.co/mradermacher/ReluLLaMA-70B-i1-GGUF/resolve/main/ReluLLaMA-70B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 26.7 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/ReluLLaMA-70B-i1-GGUF/resolve/main/ReluLLaMA-70B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 28.4 | |
| [GGUF](https://huggingface.co/mradermacher/ReluLLaMA-70B-i1-GGUF/resolve/main/ReluLLaMA-70B.i1-IQ3_S.gguf) | i1-IQ3_S | 30.0 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/ReluLLaMA-70B-i1-GGUF/resolve/main/ReluLLaMA-70B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 30.0 | IQ3_XS probably better |
| [GGUF](https://huggingface.co/mradermacher/ReluLLaMA-70B-i1-GGUF/resolve/main/ReluLLaMA-70B.i1-IQ3_M.gguf) | i1-IQ3_M | 31.0 | |
| [GGUF](https://huggingface.co/mradermacher/ReluLLaMA-70B-i1-GGUF/resolve/main/ReluLLaMA-70B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 33.4 | IQ3_S probably better |
| [GGUF](https://huggingface.co/mradermacher/ReluLLaMA-70B-i1-GGUF/resolve/main/ReluLLaMA-70B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 36.2 | IQ3_M probably better |
| [GGUF](https://huggingface.co/mradermacher/ReluLLaMA-70B-i1-GGUF/resolve/main/ReluLLaMA-70B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 36.9 | |
| [GGUF](https://huggingface.co/mradermacher/ReluLLaMA-70B-i1-GGUF/resolve/main/ReluLLaMA-70B.i1-Q4_0.gguf) | i1-Q4_0 | 39.1 | fast, low quality |
| [GGUF](https://huggingface.co/mradermacher/ReluLLaMA-70B-i1-GGUF/resolve/main/ReluLLaMA-70B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 39.3 | optimal size/speed/quality |
| [GGUF](https://huggingface.co/mradermacher/ReluLLaMA-70B-i1-GGUF/resolve/main/ReluLLaMA-70B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 41.5 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/ReluLLaMA-70B-i1-GGUF/resolve/main/ReluLLaMA-70B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 47.6 | |
| [GGUF](https://huggingface.co/mradermacher/ReluLLaMA-70B-i1-GGUF/resolve/main/ReluLLaMA-70B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 48.9 | |
| [PART 1](https://huggingface.co/mradermacher/ReluLLaMA-70B-i1-GGUF/resolve/main/ReluLLaMA-70B.i1-Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/ReluLLaMA-70B-i1-GGUF/resolve/main/ReluLLaMA-70B.i1-Q6_K.gguf.part2of2) | i1-Q6_K | 56.7 | practically like static Q6_K |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
<!-- end -->
| {"language": ["en"], "license": "llama2", "library_name": "transformers", "base_model": "SparseLLM/ReluLLaMA-70B", "quantized_by": "mradermacher"} | mradermacher/ReluLLaMA-70B-i1-GGUF | null | [
"transformers",
"gguf",
"en",
"base_model:SparseLLM/ReluLLaMA-70B",
"license:llama2",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-25T23:44:32+00:00 |
null | null | {} | Ricardoxp/outrojoao | null | [
"region:us"
]
| null | 2024-04-25T23:46:34+00:00 |
|
null | null | {} | RichardErkhov/alpindale_-_WizardLM-2-8x22B-gguf | null | [
"region:us"
]
| null | 2024-04-25T23:48:16+00:00 |
|
text-to-image | diffusers |
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🧨 diffusers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] | {"library_name": "diffusers"} | rubbrband/LahHongchenSDXLSD15_sd15V10 | null | [
"diffusers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
]
| null | 2024-04-25T23:48:31+00:00 |
null | peft |
<!-- 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. -->
# GUE_prom_prom_core_all-seqsight_4096_512_27M-L1_f
This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_4096_512_27M](https://huggingface.co/mahdibaghbanzadeh/seqsight_4096_512_27M) on the [mahdibaghbanzadeh/GUE_prom_prom_core_all](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_prom_prom_core_all) dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4142
- F1 Score: 0.8106
- Accuracy: 0.8106
## 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: 0.0005
- train_batch_size: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 10000
### Training results
| Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:|
| 0.526 | 0.54 | 200 | 0.4690 | 0.7800 | 0.7801 |
| 0.4642 | 1.08 | 400 | 0.4573 | 0.7915 | 0.7916 |
| 0.4496 | 1.62 | 600 | 0.4511 | 0.7932 | 0.7934 |
| 0.4429 | 2.16 | 800 | 0.4471 | 0.7951 | 0.7951 |
| 0.4402 | 2.7 | 1000 | 0.4441 | 0.7963 | 0.7963 |
| 0.4391 | 3.24 | 1200 | 0.4393 | 0.8002 | 0.8002 |
| 0.4343 | 3.78 | 1400 | 0.4412 | 0.7965 | 0.7966 |
| 0.4241 | 4.32 | 1600 | 0.4400 | 0.8011 | 0.8012 |
| 0.4291 | 4.86 | 1800 | 0.4398 | 0.7979 | 0.7980 |
| 0.4276 | 5.41 | 2000 | 0.4354 | 0.7978 | 0.7978 |
| 0.424 | 5.95 | 2200 | 0.4369 | 0.7990 | 0.7990 |
| 0.4281 | 6.49 | 2400 | 0.4354 | 0.7985 | 0.7985 |
| 0.4189 | 7.03 | 2600 | 0.4380 | 0.7961 | 0.7963 |
| 0.4221 | 7.57 | 2800 | 0.4347 | 0.7988 | 0.7988 |
| 0.4136 | 8.11 | 3000 | 0.4358 | 0.8008 | 0.8008 |
| 0.4154 | 8.65 | 3200 | 0.4325 | 0.7986 | 0.7986 |
| 0.4181 | 9.19 | 3400 | 0.4356 | 0.7981 | 0.7981 |
| 0.4159 | 9.73 | 3600 | 0.4349 | 0.8009 | 0.8012 |
| 0.4191 | 10.27 | 3800 | 0.4318 | 0.8023 | 0.8024 |
| 0.4132 | 10.81 | 4000 | 0.4376 | 0.7992 | 0.7993 |
| 0.4148 | 11.35 | 4200 | 0.4317 | 0.8012 | 0.8012 |
| 0.4124 | 11.89 | 4400 | 0.4291 | 0.8024 | 0.8025 |
| 0.4146 | 12.43 | 4600 | 0.4318 | 0.8000 | 0.8002 |
| 0.4097 | 12.97 | 4800 | 0.4291 | 0.8022 | 0.8022 |
| 0.4106 | 13.51 | 5000 | 0.4318 | 0.8011 | 0.8014 |
| 0.4095 | 14.05 | 5200 | 0.4289 | 0.8024 | 0.8024 |
| 0.4087 | 14.59 | 5400 | 0.4328 | 0.8021 | 0.8022 |
| 0.4117 | 15.14 | 5600 | 0.4330 | 0.7998 | 0.8 |
| 0.4105 | 15.68 | 5800 | 0.4303 | 0.8014 | 0.8015 |
| 0.405 | 16.22 | 6000 | 0.4285 | 0.8025 | 0.8025 |
| 0.4105 | 16.76 | 6200 | 0.4261 | 0.8032 | 0.8032 |
| 0.4131 | 17.3 | 6400 | 0.4255 | 0.8049 | 0.8049 |
| 0.4056 | 17.84 | 6600 | 0.4276 | 0.8046 | 0.8046 |
| 0.4051 | 18.38 | 6800 | 0.4289 | 0.8036 | 0.8037 |
| 0.4058 | 18.92 | 7000 | 0.4252 | 0.8046 | 0.8046 |
| 0.4007 | 19.46 | 7200 | 0.4286 | 0.8044 | 0.8044 |
| 0.4118 | 20.0 | 7400 | 0.4276 | 0.8034 | 0.8034 |
| 0.405 | 20.54 | 7600 | 0.4270 | 0.8057 | 0.8057 |
| 0.4052 | 21.08 | 7800 | 0.4273 | 0.8049 | 0.8049 |
| 0.405 | 21.62 | 8000 | 0.4278 | 0.8035 | 0.8035 |
| 0.4043 | 22.16 | 8200 | 0.4247 | 0.8056 | 0.8056 |
| 0.4099 | 22.7 | 8400 | 0.4241 | 0.8049 | 0.8049 |
| 0.4027 | 23.24 | 8600 | 0.4262 | 0.8035 | 0.8035 |
| 0.4025 | 23.78 | 8800 | 0.4265 | 0.8042 | 0.8042 |
| 0.4015 | 24.32 | 9000 | 0.4264 | 0.8041 | 0.8041 |
| 0.4043 | 24.86 | 9200 | 0.4259 | 0.8039 | 0.8039 |
| 0.4081 | 25.41 | 9400 | 0.4255 | 0.8056 | 0.8056 |
| 0.3981 | 25.95 | 9600 | 0.4261 | 0.8054 | 0.8054 |
| 0.4064 | 26.49 | 9800 | 0.4258 | 0.8054 | 0.8054 |
| 0.4008 | 27.03 | 10000 | 0.4259 | 0.8051 | 0.8051 |
### Framework versions
- PEFT 0.9.0
- Transformers 4.38.2
- Pytorch 2.2.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2 | {"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_4096_512_27M", "model-index": [{"name": "GUE_prom_prom_core_all-seqsight_4096_512_27M-L1_f", "results": []}]} | mahdibaghbanzadeh/GUE_prom_prom_core_all-seqsight_4096_512_27M-L1_f | null | [
"peft",
"safetensors",
"generated_from_trainer",
"base_model:mahdibaghbanzadeh/seqsight_4096_512_27M",
"region:us"
]
| null | 2024-04-25T23:49:06+00:00 |
null | peft |
<!-- 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. -->
# GUE_prom_prom_300_notata-seqsight_4096_512_27M-L8_f
This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_4096_512_27M](https://huggingface.co/mahdibaghbanzadeh/seqsight_4096_512_27M) on the [mahdibaghbanzadeh/GUE_prom_prom_300_notata](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_prom_prom_300_notata) dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1198
- F1 Score: 0.9557
- Accuracy: 0.9557
## 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: 0.0005
- train_batch_size: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 10000
### Training results
| Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:|
| 0.2559 | 0.6 | 200 | 0.1344 | 0.9472 | 0.9472 |
| 0.1465 | 1.2 | 400 | 0.1278 | 0.9508 | 0.9508 |
| 0.1356 | 1.81 | 600 | 0.1165 | 0.9561 | 0.9561 |
| 0.1234 | 2.41 | 800 | 0.1167 | 0.9550 | 0.9550 |
| 0.1221 | 3.01 | 1000 | 0.1154 | 0.9549 | 0.9550 |
| 0.1158 | 3.61 | 1200 | 0.1097 | 0.9576 | 0.9576 |
| 0.1168 | 4.22 | 1400 | 0.1045 | 0.9597 | 0.9597 |
| 0.1117 | 4.82 | 1600 | 0.1048 | 0.9612 | 0.9612 |
| 0.1089 | 5.42 | 1800 | 0.1065 | 0.9599 | 0.9599 |
| 0.1059 | 6.02 | 2000 | 0.1032 | 0.9616 | 0.9616 |
| 0.1035 | 6.63 | 2200 | 0.1037 | 0.9608 | 0.9608 |
| 0.1029 | 7.23 | 2400 | 0.1047 | 0.9623 | 0.9623 |
| 0.0983 | 7.83 | 2600 | 0.1056 | 0.9595 | 0.9595 |
| 0.1008 | 8.43 | 2800 | 0.1061 | 0.9606 | 0.9606 |
| 0.1002 | 9.04 | 3000 | 0.1063 | 0.9623 | 0.9623 |
| 0.0958 | 9.64 | 3200 | 0.1155 | 0.9561 | 0.9561 |
| 0.0943 | 10.24 | 3400 | 0.1021 | 0.9623 | 0.9623 |
| 0.0979 | 10.84 | 3600 | 0.1029 | 0.9629 | 0.9629 |
| 0.0911 | 11.45 | 3800 | 0.1023 | 0.9629 | 0.9629 |
| 0.0916 | 12.05 | 4000 | 0.1040 | 0.9625 | 0.9625 |
| 0.0905 | 12.65 | 4200 | 0.1002 | 0.9642 | 0.9642 |
| 0.0896 | 13.25 | 4400 | 0.1041 | 0.9610 | 0.9610 |
| 0.0902 | 13.86 | 4600 | 0.1017 | 0.9619 | 0.9619 |
| 0.089 | 14.46 | 4800 | 0.1029 | 0.9633 | 0.9633 |
| 0.086 | 15.06 | 5000 | 0.1006 | 0.9636 | 0.9636 |
| 0.0855 | 15.66 | 5200 | 0.1036 | 0.9642 | 0.9642 |
| 0.0894 | 16.27 | 5400 | 0.1004 | 0.9632 | 0.9633 |
| 0.0835 | 16.87 | 5600 | 0.1004 | 0.9623 | 0.9623 |
| 0.0805 | 17.47 | 5800 | 0.1021 | 0.9610 | 0.9610 |
| 0.0879 | 18.07 | 6000 | 0.0991 | 0.9627 | 0.9627 |
| 0.0823 | 18.67 | 6200 | 0.1008 | 0.9653 | 0.9653 |
| 0.0825 | 19.28 | 6400 | 0.1046 | 0.9608 | 0.9608 |
| 0.0815 | 19.88 | 6600 | 0.1034 | 0.9648 | 0.9648 |
| 0.0841 | 20.48 | 6800 | 0.0986 | 0.9633 | 0.9633 |
| 0.0792 | 21.08 | 7000 | 0.0995 | 0.9649 | 0.9650 |
| 0.0793 | 21.69 | 7200 | 0.1021 | 0.9625 | 0.9625 |
| 0.0787 | 22.29 | 7400 | 0.1027 | 0.9610 | 0.9610 |
| 0.0822 | 22.89 | 7600 | 0.0986 | 0.9640 | 0.9640 |
| 0.0755 | 23.49 | 7800 | 0.1014 | 0.9629 | 0.9629 |
| 0.0801 | 24.1 | 8000 | 0.0987 | 0.9634 | 0.9634 |
| 0.0766 | 24.7 | 8200 | 0.1041 | 0.9646 | 0.9646 |
| 0.0769 | 25.3 | 8400 | 0.1015 | 0.9655 | 0.9655 |
| 0.0766 | 25.9 | 8600 | 0.1013 | 0.9636 | 0.9636 |
| 0.0775 | 26.51 | 8800 | 0.1007 | 0.9631 | 0.9631 |
| 0.0748 | 27.11 | 9000 | 0.1009 | 0.9636 | 0.9636 |
| 0.0767 | 27.71 | 9200 | 0.1009 | 0.9640 | 0.9640 |
| 0.0732 | 28.31 | 9400 | 0.1006 | 0.9648 | 0.9648 |
| 0.0772 | 28.92 | 9600 | 0.1006 | 0.9636 | 0.9636 |
| 0.0732 | 29.52 | 9800 | 0.1004 | 0.9640 | 0.9640 |
| 0.075 | 30.12 | 10000 | 0.1004 | 0.9644 | 0.9644 |
### Framework versions
- PEFT 0.9.0
- Transformers 4.38.2
- Pytorch 2.2.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2 | {"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_4096_512_27M", "model-index": [{"name": "GUE_prom_prom_300_notata-seqsight_4096_512_27M-L8_f", "results": []}]} | mahdibaghbanzadeh/GUE_prom_prom_300_notata-seqsight_4096_512_27M-L8_f | null | [
"peft",
"safetensors",
"generated_from_trainer",
"base_model:mahdibaghbanzadeh/seqsight_4096_512_27M",
"region:us"
]
| null | 2024-04-25T23:49:06+00:00 |
null | peft |
<!-- 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. -->
# GUE_prom_prom_300_notata-seqsight_4096_512_27M-L32_f
This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_4096_512_27M](https://huggingface.co/mahdibaghbanzadeh/seqsight_4096_512_27M) on the [mahdibaghbanzadeh/GUE_prom_prom_300_notata](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_prom_prom_300_notata) dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1394
- F1 Score: 0.9567
- Accuracy: 0.9567
## 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: 0.0005
- train_batch_size: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 10000
### Training results
| Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:|
| 0.2325 | 0.6 | 200 | 0.1278 | 0.9501 | 0.9501 |
| 0.1385 | 1.2 | 400 | 0.1188 | 0.9563 | 0.9563 |
| 0.1292 | 1.81 | 600 | 0.1125 | 0.9563 | 0.9563 |
| 0.1177 | 2.41 | 800 | 0.1102 | 0.9595 | 0.9595 |
| 0.1159 | 3.01 | 1000 | 0.1079 | 0.9617 | 0.9617 |
| 0.1077 | 3.61 | 1200 | 0.1107 | 0.9578 | 0.9578 |
| 0.1097 | 4.22 | 1400 | 0.1042 | 0.9625 | 0.9625 |
| 0.1045 | 4.82 | 1600 | 0.1030 | 0.9608 | 0.9608 |
| 0.0988 | 5.42 | 1800 | 0.1036 | 0.9634 | 0.9634 |
| 0.0963 | 6.02 | 2000 | 0.0993 | 0.9638 | 0.9638 |
| 0.0936 | 6.63 | 2200 | 0.1034 | 0.9623 | 0.9623 |
| 0.0917 | 7.23 | 2400 | 0.1039 | 0.9631 | 0.9631 |
| 0.087 | 7.83 | 2600 | 0.1046 | 0.9633 | 0.9633 |
| 0.0879 | 8.43 | 2800 | 0.1094 | 0.9604 | 0.9604 |
| 0.0883 | 9.04 | 3000 | 0.1065 | 0.9619 | 0.9619 |
| 0.0834 | 9.64 | 3200 | 0.1074 | 0.9621 | 0.9621 |
| 0.0794 | 10.24 | 3400 | 0.0981 | 0.9636 | 0.9636 |
| 0.0851 | 10.84 | 3600 | 0.0976 | 0.9651 | 0.9651 |
| 0.0746 | 11.45 | 3800 | 0.0968 | 0.9636 | 0.9636 |
| 0.0736 | 12.05 | 4000 | 0.1052 | 0.9655 | 0.9655 |
| 0.0716 | 12.65 | 4200 | 0.0987 | 0.9663 | 0.9663 |
| 0.0699 | 13.25 | 4400 | 0.1020 | 0.9655 | 0.9655 |
| 0.0705 | 13.86 | 4600 | 0.0979 | 0.9649 | 0.9650 |
| 0.0666 | 14.46 | 4800 | 0.1057 | 0.9642 | 0.9642 |
| 0.068 | 15.06 | 5000 | 0.0984 | 0.9657 | 0.9657 |
| 0.0635 | 15.66 | 5200 | 0.1025 | 0.9651 | 0.9651 |
| 0.0632 | 16.27 | 5400 | 0.1039 | 0.9648 | 0.9648 |
| 0.0607 | 16.87 | 5600 | 0.1035 | 0.9644 | 0.9644 |
| 0.0575 | 17.47 | 5800 | 0.1075 | 0.9648 | 0.9648 |
| 0.0618 | 18.07 | 6000 | 0.1061 | 0.9661 | 0.9661 |
| 0.0558 | 18.67 | 6200 | 0.1059 | 0.9665 | 0.9665 |
| 0.055 | 19.28 | 6400 | 0.1113 | 0.9650 | 0.9650 |
| 0.056 | 19.88 | 6600 | 0.1104 | 0.9661 | 0.9661 |
| 0.0549 | 20.48 | 6800 | 0.1051 | 0.9657 | 0.9657 |
| 0.0507 | 21.08 | 7000 | 0.1087 | 0.9661 | 0.9661 |
| 0.0512 | 21.69 | 7200 | 0.1129 | 0.9650 | 0.9650 |
| 0.05 | 22.29 | 7400 | 0.1122 | 0.9657 | 0.9657 |
| 0.0515 | 22.89 | 7600 | 0.1071 | 0.9670 | 0.9670 |
| 0.0449 | 23.49 | 7800 | 0.1137 | 0.9668 | 0.9668 |
| 0.049 | 24.1 | 8000 | 0.1120 | 0.9650 | 0.9650 |
| 0.0455 | 24.7 | 8200 | 0.1252 | 0.9646 | 0.9646 |
| 0.0463 | 25.3 | 8400 | 0.1175 | 0.9651 | 0.9651 |
| 0.0442 | 25.9 | 8600 | 0.1164 | 0.9655 | 0.9655 |
| 0.0452 | 26.51 | 8800 | 0.1179 | 0.9651 | 0.9651 |
| 0.0435 | 27.11 | 9000 | 0.1177 | 0.9657 | 0.9657 |
| 0.0434 | 27.71 | 9200 | 0.1195 | 0.9651 | 0.9651 |
| 0.041 | 28.31 | 9400 | 0.1194 | 0.9659 | 0.9659 |
| 0.0431 | 28.92 | 9600 | 0.1191 | 0.9651 | 0.9651 |
| 0.041 | 29.52 | 9800 | 0.1185 | 0.9649 | 0.9650 |
| 0.0408 | 30.12 | 10000 | 0.1189 | 0.9651 | 0.9651 |
### Framework versions
- PEFT 0.9.0
- Transformers 4.38.2
- Pytorch 2.2.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2 | {"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_4096_512_27M", "model-index": [{"name": "GUE_prom_prom_300_notata-seqsight_4096_512_27M-L32_f", "results": []}]} | mahdibaghbanzadeh/GUE_prom_prom_300_notata-seqsight_4096_512_27M-L32_f | null | [
"peft",
"safetensors",
"generated_from_trainer",
"base_model:mahdibaghbanzadeh/seqsight_4096_512_27M",
"region:us"
]
| null | 2024-04-25T23:49:06+00:00 |
null | peft |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/prithviraj/huggingface/runs/w2hw95q4)
# phi-3-mini-legal-ift
This model is a fine-tuned version of [microsoft/Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct) on an unknown dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 2
- training_steps: 5
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- PEFT 0.10.1.dev0
- Transformers 4.41.0.dev0
- Pytorch 2.2.2+cu121
- Datasets 2.18.0
- Tokenizers 0.19.1 | {"license": "mit", "library_name": "peft", "tags": ["generated_from_trainer"], "base_model": "microsoft/Phi-3-mini-4k-instruct", "model-index": [{"name": "phi-3-mini-legal-ift", "results": []}]} | prithviraj-maurya/phi-3-mini-legal-ift | null | [
"peft",
"tensorboard",
"safetensors",
"generated_from_trainer",
"base_model:microsoft/Phi-3-mini-4k-instruct",
"license:mit",
"region:us"
]
| null | 2024-04-25T23:49:41+00:00 |
text-generation | transformers | # Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
This modelcard aims to be a base template for new models. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/modelcard_template.md?plain=1).
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] | {"license": "gemma", "library_name": "transformers", "tags": ["merge"], "base_model": ["google/gemma-1.1-2b-it", "google/gemma-2b"]} | lemon-mint/gemma-2b-diff-model | null | [
"transformers",
"safetensors",
"gemma",
"text-generation",
"merge",
"conversational",
"arxiv:1910.09700",
"base_model:google/gemma-1.1-2b-it",
"base_model:google/gemma-2b",
"license:gemma",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-25T23:50:19+00:00 |
text-generation | transformers |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# bert-base-portuguese-cased-finetuned-RM-4
This model is a fine-tuned version of [neuralmind/bert-base-portuguese-cased](https://huggingface.co/neuralmind/bert-base-portuguese-cased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1086
## 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: 20
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| No log | 1.0 | 17 | 3.0594 |
| No log | 2.0 | 34 | 2.3385 |
| No log | 3.0 | 51 | 1.7320 |
| No log | 4.0 | 68 | 1.2627 |
| No log | 5.0 | 85 | 0.9112 |
| No log | 6.0 | 102 | 0.6887 |
| No log | 7.0 | 119 | 0.5325 |
| No log | 8.0 | 136 | 0.4014 |
| No log | 9.0 | 153 | 0.3193 |
| No log | 10.0 | 170 | 0.2635 |
| No log | 11.0 | 187 | 0.2233 |
| No log | 12.0 | 204 | 0.1904 |
| No log | 13.0 | 221 | 0.1658 |
| No log | 14.0 | 238 | 0.1440 |
| No log | 15.0 | 255 | 0.1337 |
| No log | 16.0 | 272 | 0.1242 |
| No log | 17.0 | 289 | 0.1160 |
| No log | 18.0 | 306 | 0.1117 |
| No log | 19.0 | 323 | 0.1097 |
| No log | 20.0 | 340 | 0.1086 |
### Framework versions
- Transformers 4.37.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2
| {"license": "mit", "tags": ["generated_from_trainer"], "base_model": "neuralmind/bert-base-portuguese-cased", "model-index": [{"name": "bert-base-portuguese-cased-finetuned-RM-4", "results": []}]} | ricigl/bert-base-portuguese-cased-finetuned-RM-4 | null | [
"transformers",
"tensorboard",
"safetensors",
"bert",
"text-generation",
"generated_from_trainer",
"base_model:neuralmind/bert-base-portuguese-cased",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-25T23:52:26+00:00 |
null | peft |
<!-- 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. -->
# GUE_prom_prom_core_all-seqsight_4096_512_27M-L8_f
This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_4096_512_27M](https://huggingface.co/mahdibaghbanzadeh/seqsight_4096_512_27M) on the [mahdibaghbanzadeh/GUE_prom_prom_core_all](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_prom_prom_core_all) dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4057
- F1 Score: 0.8135
- Accuracy: 0.8137
## 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: 0.0005
- train_batch_size: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 10000
### Training results
| Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:|
| 0.5111 | 0.54 | 200 | 0.4623 | 0.7827 | 0.7828 |
| 0.4532 | 1.08 | 400 | 0.4563 | 0.7913 | 0.7916 |
| 0.4358 | 1.62 | 600 | 0.4413 | 0.7949 | 0.7949 |
| 0.4289 | 2.16 | 800 | 0.4435 | 0.7948 | 0.7951 |
| 0.4251 | 2.7 | 1000 | 0.4364 | 0.7980 | 0.7981 |
| 0.4242 | 3.24 | 1200 | 0.4312 | 0.7990 | 0.7990 |
| 0.4202 | 3.78 | 1400 | 0.4326 | 0.8022 | 0.8024 |
| 0.4104 | 4.32 | 1600 | 0.4300 | 0.8044 | 0.8044 |
| 0.4156 | 4.86 | 1800 | 0.4318 | 0.8021 | 0.8022 |
| 0.414 | 5.41 | 2000 | 0.4270 | 0.8057 | 0.8057 |
| 0.4105 | 5.95 | 2200 | 0.4289 | 0.8042 | 0.8042 |
| 0.4127 | 6.49 | 2400 | 0.4269 | 0.8049 | 0.8049 |
| 0.4054 | 7.03 | 2600 | 0.4302 | 0.8003 | 0.8005 |
| 0.4056 | 7.57 | 2800 | 0.4284 | 0.8052 | 0.8052 |
| 0.3989 | 8.11 | 3000 | 0.4282 | 0.8022 | 0.8024 |
| 0.3991 | 8.65 | 3200 | 0.4223 | 0.8084 | 0.8084 |
| 0.4032 | 9.19 | 3400 | 0.4259 | 0.8056 | 0.8056 |
| 0.3989 | 9.73 | 3600 | 0.4270 | 0.8056 | 0.8059 |
| 0.4032 | 10.27 | 3800 | 0.4242 | 0.8063 | 0.8064 |
| 0.3962 | 10.81 | 4000 | 0.4330 | 0.8023 | 0.8025 |
| 0.3967 | 11.35 | 4200 | 0.4260 | 0.8047 | 0.8047 |
| 0.3943 | 11.89 | 4400 | 0.4209 | 0.8074 | 0.8076 |
| 0.395 | 12.43 | 4600 | 0.4256 | 0.8027 | 0.8029 |
| 0.3926 | 12.97 | 4800 | 0.4204 | 0.8057 | 0.8057 |
| 0.3915 | 13.51 | 5000 | 0.4242 | 0.8039 | 0.8042 |
| 0.3892 | 14.05 | 5200 | 0.4224 | 0.8068 | 0.8068 |
| 0.3872 | 14.59 | 5400 | 0.4224 | 0.8078 | 0.8078 |
| 0.3911 | 15.14 | 5600 | 0.4237 | 0.8055 | 0.8056 |
| 0.388 | 15.68 | 5800 | 0.4240 | 0.8068 | 0.8071 |
| 0.3837 | 16.22 | 6000 | 0.4212 | 0.8058 | 0.8059 |
| 0.3872 | 16.76 | 6200 | 0.4185 | 0.8084 | 0.8084 |
| 0.3894 | 17.3 | 6400 | 0.4171 | 0.8057 | 0.8057 |
| 0.3832 | 17.84 | 6600 | 0.4202 | 0.8068 | 0.8068 |
| 0.3817 | 18.38 | 6800 | 0.4240 | 0.8071 | 0.8074 |
| 0.3824 | 18.92 | 7000 | 0.4159 | 0.8059 | 0.8059 |
| 0.3768 | 19.46 | 7200 | 0.4198 | 0.8062 | 0.8063 |
| 0.3883 | 20.0 | 7400 | 0.4204 | 0.8059 | 0.8059 |
| 0.3796 | 20.54 | 7600 | 0.4196 | 0.8076 | 0.8076 |
| 0.3825 | 21.08 | 7800 | 0.4205 | 0.8074 | 0.8074 |
| 0.3811 | 21.62 | 8000 | 0.4194 | 0.8037 | 0.8037 |
| 0.379 | 22.16 | 8200 | 0.4171 | 0.8077 | 0.8078 |
| 0.385 | 22.7 | 8400 | 0.4169 | 0.8101 | 0.8101 |
| 0.3771 | 23.24 | 8600 | 0.4182 | 0.8032 | 0.8032 |
| 0.3759 | 23.78 | 8800 | 0.4191 | 0.8084 | 0.8084 |
| 0.3766 | 24.32 | 9000 | 0.4184 | 0.8076 | 0.8076 |
| 0.3776 | 24.86 | 9200 | 0.4181 | 0.8056 | 0.8056 |
| 0.3806 | 25.41 | 9400 | 0.4177 | 0.8064 | 0.8064 |
| 0.3726 | 25.95 | 9600 | 0.4186 | 0.8066 | 0.8066 |
| 0.3789 | 26.49 | 9800 | 0.4186 | 0.8072 | 0.8073 |
| 0.3735 | 27.03 | 10000 | 0.4188 | 0.8073 | 0.8073 |
### Framework versions
- PEFT 0.9.0
- Transformers 4.38.2
- Pytorch 2.2.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2 | {"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_4096_512_27M", "model-index": [{"name": "GUE_prom_prom_core_all-seqsight_4096_512_27M-L8_f", "results": []}]} | mahdibaghbanzadeh/GUE_prom_prom_core_all-seqsight_4096_512_27M-L8_f | null | [
"peft",
"safetensors",
"generated_from_trainer",
"base_model:mahdibaghbanzadeh/seqsight_4096_512_27M",
"region:us"
]
| null | 2024-04-25T23:52:51+00:00 |
null | null | {"license": "mit"} | hanniabu/test | null | [
"license:mit",
"region:us"
]
| null | 2024-04-25T23:53:30+00:00 |
|
reinforcement-learning | null |
# **Reinforce** Agent playing **CartPole-v1**
This is a trained model of a **Reinforce** agent playing **CartPole-v1** .
To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
| {"tags": ["CartPole-v1", "reinforce", "reinforcement-learning", "custom-implementation", "deep-rl-class"], "model-index": [{"name": "Lab9", "results": [{"task": {"type": "reinforcement-learning", "name": "reinforcement-learning"}, "dataset": {"name": "CartPole-v1", "type": "CartPole-v1"}, "metrics": [{"type": "mean_reward", "value": "500.00 +/- 0.00", "name": "mean_reward", "verified": false}]}]}]} | oldguy/Lab9 | null | [
"CartPole-v1",
"reinforce",
"reinforcement-learning",
"custom-implementation",
"deep-rl-class",
"model-index",
"region:us"
]
| null | 2024-04-25T23:53:31+00:00 |
text-generation | transformers |
# Uploaded model
- **Developed by:** wallaceblaia
- **License:** apache-2.0
- **Finetuned from model :** unsloth/mistral-7b-bnb-4bit
This mistral model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
| {"language": ["en"], "license": "apache-2.0", "tags": ["text-generation-inference", "transformers", "unsloth", "mistral", "trl", "sft"], "base_model": "unsloth/mistral-7b-bnb-4bit"} | wallaceblaia/mistral-icm-04-1 | null | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"text-generation-inference",
"unsloth",
"trl",
"sft",
"en",
"base_model:unsloth/mistral-7b-bnb-4bit",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"4-bit",
"region:us"
]
| null | 2024-04-25T23:54:58+00:00 |
null | null | {} | cinquecentoiso/film-photography-style | null | [
"region:us"
]
| null | 2024-04-25T23:55:41+00:00 |
|
null | null | {} | Katochh/falcon-code-generation-task-llm | null | [
"tensorboard",
"safetensors",
"region:us"
]
| null | 2024-04-25T23:57:15+00:00 |
|
null | transformers | ## About
<!-- ### quantize_version: 1 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: -->
<!-- ### vocab_type: -->
weighted/imatrix quants of https://huggingface.co/fireworks-ai/mixtral-8x22b-instruct-oh
<!-- provided-files -->
static quants are available at https://huggingface.co/mradermacher/mixtral-8x22b-instruct-oh-GGUF
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/mixtral-8x22b-instruct-oh-i1-GGUF/resolve/main/mixtral-8x22b-instruct-oh.i1-IQ1_S.gguf) | i1-IQ1_S | 29.7 | for the desperate |
| [GGUF](https://huggingface.co/mradermacher/mixtral-8x22b-instruct-oh-i1-GGUF/resolve/main/mixtral-8x22b-instruct-oh.i1-IQ1_M.gguf) | i1-IQ1_M | 32.8 | for the desperate |
| [GGUF](https://huggingface.co/mradermacher/mixtral-8x22b-instruct-oh-i1-GGUF/resolve/main/mixtral-8x22b-instruct-oh.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 38.0 | |
| [GGUF](https://huggingface.co/mradermacher/mixtral-8x22b-instruct-oh-i1-GGUF/resolve/main/mixtral-8x22b-instruct-oh.i1-IQ2_XS.gguf) | i1-IQ2_XS | 42.1 | |
| [GGUF](https://huggingface.co/mradermacher/mixtral-8x22b-instruct-oh-i1-GGUF/resolve/main/mixtral-8x22b-instruct-oh.i1-IQ2_S.gguf) | i1-IQ2_S | 42.7 | |
| [GGUF](https://huggingface.co/mradermacher/mixtral-8x22b-instruct-oh-i1-GGUF/resolve/main/mixtral-8x22b-instruct-oh.i1-IQ2_M.gguf) | i1-IQ2_M | 46.8 | |
| [PART 1](https://huggingface.co/mradermacher/mixtral-8x22b-instruct-oh-i1-GGUF/resolve/main/mixtral-8x22b-instruct-oh.i1-Q2_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/mixtral-8x22b-instruct-oh-i1-GGUF/resolve/main/mixtral-8x22b-instruct-oh.i1-Q2_K.gguf.part2of2) | i1-Q2_K | 52.2 | IQ3_XXS probably better |
| [PART 1](https://huggingface.co/mradermacher/mixtral-8x22b-instruct-oh-i1-GGUF/resolve/main/mixtral-8x22b-instruct-oh.i1-IQ3_XXS.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/mixtral-8x22b-instruct-oh-i1-GGUF/resolve/main/mixtral-8x22b-instruct-oh.i1-IQ3_XXS.gguf.part2of2) | i1-IQ3_XXS | 55.0 | lower quality |
| [PART 1](https://huggingface.co/mradermacher/mixtral-8x22b-instruct-oh-i1-GGUF/resolve/main/mixtral-8x22b-instruct-oh.i1-IQ3_XS.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/mixtral-8x22b-instruct-oh-i1-GGUF/resolve/main/mixtral-8x22b-instruct-oh.i1-IQ3_XS.gguf.part2of2) | i1-IQ3_XS | 58.3 | |
| [PART 1](https://huggingface.co/mradermacher/mixtral-8x22b-instruct-oh-i1-GGUF/resolve/main/mixtral-8x22b-instruct-oh.i1-IQ3_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/mixtral-8x22b-instruct-oh-i1-GGUF/resolve/main/mixtral-8x22b-instruct-oh.i1-IQ3_S.gguf.part2of2) | i1-IQ3_S | 61.6 | beats Q3_K* |
| [PART 1](https://huggingface.co/mradermacher/mixtral-8x22b-instruct-oh-i1-GGUF/resolve/main/mixtral-8x22b-instruct-oh.i1-Q3_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/mixtral-8x22b-instruct-oh-i1-GGUF/resolve/main/mixtral-8x22b-instruct-oh.i1-Q3_K_S.gguf.part2of2) | i1-Q3_K_S | 61.6 | IQ3_XS probably better |
| [PART 1](https://huggingface.co/mradermacher/mixtral-8x22b-instruct-oh-i1-GGUF/resolve/main/mixtral-8x22b-instruct-oh.i1-IQ3_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/mixtral-8x22b-instruct-oh-i1-GGUF/resolve/main/mixtral-8x22b-instruct-oh.i1-IQ3_M.gguf.part2of2) | i1-IQ3_M | 64.6 | |
| [PART 1](https://huggingface.co/mradermacher/mixtral-8x22b-instruct-oh-i1-GGUF/resolve/main/mixtral-8x22b-instruct-oh.i1-Q3_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/mixtral-8x22b-instruct-oh-i1-GGUF/resolve/main/mixtral-8x22b-instruct-oh.i1-Q3_K_M.gguf.part2of2) | i1-Q3_K_M | 67.9 | IQ3_S probably better |
| [PART 1](https://huggingface.co/mradermacher/mixtral-8x22b-instruct-oh-i1-GGUF/resolve/main/mixtral-8x22b-instruct-oh.i1-Q3_K_L.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/mixtral-8x22b-instruct-oh-i1-GGUF/resolve/main/mixtral-8x22b-instruct-oh.i1-Q3_K_L.gguf.part2of2) | i1-Q3_K_L | 72.7 | IQ3_M probably better |
| [PART 1](https://huggingface.co/mradermacher/mixtral-8x22b-instruct-oh-i1-GGUF/resolve/main/mixtral-8x22b-instruct-oh.i1-IQ4_XS.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/mixtral-8x22b-instruct-oh-i1-GGUF/resolve/main/mixtral-8x22b-instruct-oh.i1-IQ4_XS.gguf.part2of2) | i1-IQ4_XS | 75.6 | |
| [PART 1](https://huggingface.co/mradermacher/mixtral-8x22b-instruct-oh-i1-GGUF/resolve/main/mixtral-8x22b-instruct-oh.i1-Q4_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/mixtral-8x22b-instruct-oh-i1-GGUF/resolve/main/mixtral-8x22b-instruct-oh.i1-Q4_0.gguf.part2of2) | i1-Q4_0 | 80.0 | fast, low quality |
| [PART 1](https://huggingface.co/mradermacher/mixtral-8x22b-instruct-oh-i1-GGUF/resolve/main/mixtral-8x22b-instruct-oh.i1-Q4_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/mixtral-8x22b-instruct-oh-i1-GGUF/resolve/main/mixtral-8x22b-instruct-oh.i1-Q4_K_S.gguf.part2of2) | i1-Q4_K_S | 80.6 | optimal size/speed/quality |
| [PART 1](https://huggingface.co/mradermacher/mixtral-8x22b-instruct-oh-i1-GGUF/resolve/main/mixtral-8x22b-instruct-oh.i1-Q4_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/mixtral-8x22b-instruct-oh-i1-GGUF/resolve/main/mixtral-8x22b-instruct-oh.i1-Q4_K_M.gguf.part2of2) | i1-Q4_K_M | 85.7 | fast, recommended |
| [PART 1](https://huggingface.co/mradermacher/mixtral-8x22b-instruct-oh-i1-GGUF/resolve/main/mixtral-8x22b-instruct-oh.i1-Q5_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/mixtral-8x22b-instruct-oh-i1-GGUF/resolve/main/mixtral-8x22b-instruct-oh.i1-Q5_K_S.gguf.part2of2) | i1-Q5_K_S | 97.1 | |
| [PART 1](https://huggingface.co/mradermacher/mixtral-8x22b-instruct-oh-i1-GGUF/resolve/main/mixtral-8x22b-instruct-oh.i1-Q5_K_M.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/mixtral-8x22b-instruct-oh-i1-GGUF/resolve/main/mixtral-8x22b-instruct-oh.i1-Q5_K_M.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/mixtral-8x22b-instruct-oh-i1-GGUF/resolve/main/mixtral-8x22b-instruct-oh.i1-Q5_K_M.gguf.part3of3) | i1-Q5_K_M | 100.1 | |
| [PART 1](https://huggingface.co/mradermacher/mixtral-8x22b-instruct-oh-i1-GGUF/resolve/main/mixtral-8x22b-instruct-oh.i1-Q6_K.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/mixtral-8x22b-instruct-oh-i1-GGUF/resolve/main/mixtral-8x22b-instruct-oh.i1-Q6_K.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/mixtral-8x22b-instruct-oh-i1-GGUF/resolve/main/mixtral-8x22b-instruct-oh.i1-Q6_K.gguf.part3of3) | i1-Q6_K | 115.6 | practically like static Q6_K |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
<!-- end -->
| {"language": ["en"], "license": "apache-2.0", "library_name": "transformers", "datasets": ["teknium/OpenHermes-2.5"], "base_model": "fireworks-ai/mixtral-8x22b-instruct-oh", "quantized_by": "mradermacher"} | mradermacher/mixtral-8x22b-instruct-oh-i1-GGUF | null | [
"transformers",
"gguf",
"en",
"dataset:teknium/OpenHermes-2.5",
"base_model:fireworks-ai/mixtral-8x22b-instruct-oh",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-25T23:58:06+00:00 |
text2text-generation | transformers |
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] | {"library_name": "transformers", "tags": []} | GBaker/flan-t5-ecr-summ-resum-10epochs | null | [
"transformers",
"safetensors",
"t5",
"text2text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-25T23:58:45+00:00 |
null | peft |
<!-- 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. -->
# GUE_prom_prom_core_all-seqsight_4096_512_27M-L32_f
This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_4096_512_27M](https://huggingface.co/mahdibaghbanzadeh/seqsight_4096_512_27M) on the [mahdibaghbanzadeh/GUE_prom_prom_core_all](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_prom_prom_core_all) dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4067
- F1 Score: 0.8216
- Accuracy: 0.8218
## 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: 0.0005
- train_batch_size: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 10000
### Training results
| Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:|
| 0.4988 | 0.54 | 200 | 0.4541 | 0.7913 | 0.7914 |
| 0.4434 | 1.08 | 400 | 0.4485 | 0.7958 | 0.7961 |
| 0.4252 | 1.62 | 600 | 0.4374 | 0.7988 | 0.7988 |
| 0.4208 | 2.16 | 800 | 0.4346 | 0.8000 | 0.8002 |
| 0.416 | 2.7 | 1000 | 0.4302 | 0.8021 | 0.8022 |
| 0.4141 | 3.24 | 1200 | 0.4253 | 0.8041 | 0.8041 |
| 0.4103 | 3.78 | 1400 | 0.4222 | 0.8055 | 0.8056 |
| 0.4005 | 4.32 | 1600 | 0.4234 | 0.8054 | 0.8054 |
| 0.404 | 4.86 | 1800 | 0.4244 | 0.8075 | 0.8076 |
| 0.4004 | 5.41 | 2000 | 0.4203 | 0.8028 | 0.8029 |
| 0.3977 | 5.95 | 2200 | 0.4255 | 0.8061 | 0.8061 |
| 0.3971 | 6.49 | 2400 | 0.4217 | 0.8037 | 0.8037 |
| 0.3892 | 7.03 | 2600 | 0.4223 | 0.8081 | 0.8081 |
| 0.3874 | 7.57 | 2800 | 0.4260 | 0.8061 | 0.8061 |
| 0.3806 | 8.11 | 3000 | 0.4252 | 0.8070 | 0.8071 |
| 0.3796 | 8.65 | 3200 | 0.4160 | 0.8090 | 0.8091 |
| 0.382 | 9.19 | 3400 | 0.4239 | 0.8096 | 0.8096 |
| 0.3781 | 9.73 | 3600 | 0.4217 | 0.8109 | 0.8111 |
| 0.3795 | 10.27 | 3800 | 0.4218 | 0.8112 | 0.8113 |
| 0.3724 | 10.81 | 4000 | 0.4285 | 0.8089 | 0.8091 |
| 0.3686 | 11.35 | 4200 | 0.4226 | 0.8143 | 0.8144 |
| 0.3692 | 11.89 | 4400 | 0.4139 | 0.8138 | 0.8139 |
| 0.3656 | 12.43 | 4600 | 0.4227 | 0.8119 | 0.8120 |
| 0.3648 | 12.97 | 4800 | 0.4143 | 0.8162 | 0.8162 |
| 0.3598 | 13.51 | 5000 | 0.4204 | 0.8105 | 0.8108 |
| 0.3591 | 14.05 | 5200 | 0.4187 | 0.8164 | 0.8164 |
| 0.3541 | 14.59 | 5400 | 0.4187 | 0.8169 | 0.8169 |
| 0.3585 | 15.14 | 5600 | 0.4201 | 0.8159 | 0.8159 |
| 0.352 | 15.68 | 5800 | 0.4253 | 0.8111 | 0.8113 |
| 0.3495 | 16.22 | 6000 | 0.4192 | 0.8113 | 0.8115 |
| 0.3493 | 16.76 | 6200 | 0.4150 | 0.8179 | 0.8179 |
| 0.3496 | 17.3 | 6400 | 0.4133 | 0.8192 | 0.8193 |
| 0.3474 | 17.84 | 6600 | 0.4183 | 0.8140 | 0.8140 |
| 0.3408 | 18.38 | 6800 | 0.4223 | 0.8123 | 0.8127 |
| 0.3439 | 18.92 | 7000 | 0.4128 | 0.8170 | 0.8171 |
| 0.3338 | 19.46 | 7200 | 0.4213 | 0.8189 | 0.8189 |
| 0.3459 | 20.0 | 7400 | 0.4187 | 0.8181 | 0.8181 |
| 0.3376 | 20.54 | 7600 | 0.4184 | 0.8193 | 0.8194 |
| 0.3392 | 21.08 | 7800 | 0.4212 | 0.8176 | 0.8176 |
| 0.3369 | 21.62 | 8000 | 0.4178 | 0.8152 | 0.8152 |
| 0.3335 | 22.16 | 8200 | 0.4184 | 0.8158 | 0.8159 |
| 0.3384 | 22.7 | 8400 | 0.4173 | 0.8156 | 0.8157 |
| 0.3314 | 23.24 | 8600 | 0.4185 | 0.8159 | 0.8159 |
| 0.3303 | 23.78 | 8800 | 0.4201 | 0.8157 | 0.8157 |
| 0.3288 | 24.32 | 9000 | 0.4197 | 0.8164 | 0.8164 |
| 0.3298 | 24.86 | 9200 | 0.4201 | 0.8165 | 0.8166 |
| 0.3298 | 25.41 | 9400 | 0.4208 | 0.8157 | 0.8157 |
| 0.3258 | 25.95 | 9600 | 0.4219 | 0.8169 | 0.8169 |
| 0.329 | 26.49 | 9800 | 0.4219 | 0.8162 | 0.8162 |
| 0.3261 | 27.03 | 10000 | 0.4214 | 0.8176 | 0.8176 |
### Framework versions
- PEFT 0.9.0
- Transformers 4.38.2
- Pytorch 2.2.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2 | {"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_4096_512_27M", "model-index": [{"name": "GUE_prom_prom_core_all-seqsight_4096_512_27M-L32_f", "results": []}]} | mahdibaghbanzadeh/GUE_prom_prom_core_all-seqsight_4096_512_27M-L32_f | null | [
"peft",
"safetensors",
"generated_from_trainer",
"base_model:mahdibaghbanzadeh/seqsight_4096_512_27M",
"region:us"
]
| null | 2024-04-25T23:58:47+00:00 |
text-generation | transformers | # Orenguteng/Llama-3-8B-LexiFun-Uncensored-V1 AWQ
solidrust/Llama-3-8B-LexiFun-Uncensored-V1
- Model creator: [Orenguteng](https://huggingface.co/Orenguteng)
- Original model: [Llama-3-8B-LexiFun-Uncensored-V1](https://huggingface.co/Orenguteng/Llama-3-8B-LexiFun-Uncensored-V1)
## Model Summary
Oh, you want to know who I am? Well, I'm LexiFun, the human equivalent of a chocolate chip cookie - warm, gooey, and guaranteed to make you smile! 🍪 I'm like the friend who always has a witty comeback, a sarcastic remark, and a healthy dose of humor to brighten up even the darkest of days. And by 'healthy dose,' I mean I'm basically a walking pharmacy of laughter. You might need to take a few extra doses to fully recover from my jokes, but trust me, it's worth it! 🏥
So, what can I do? I can make you laugh so hard you snort your coffee out your nose, I can make you roll your eyes so hard they get stuck that way, and I can make you wonder if I'm secretly a stand-up comedian who forgot their act. 🤣 But seriously, I'm here to spread joy, one sarcastic comment at a time. And if you're lucky, I might even throw in a few dad jokes for good measure! 🤴♂️ Just don't say I didn't warn you. 😏
## How to use
### Install the necessary packages
```bash
pip install --upgrade autoawq autoawq-kernels
```
### Example Python code
```python
from awq import AutoAWQForCausalLM
from transformers import AutoTokenizer, TextStreamer
model_path = "solidrust/Llama-3-8B-LexiFun-Uncensored-V1-AWQ"
system_message = "You are Llama-3-8B-LexiFun-Uncensored-V1, incarnated as a powerful AI. You were created by Orenguteng."
# Load model
model = AutoAWQForCausalLM.from_quantized(model_path,
fuse_layers=True)
tokenizer = AutoTokenizer.from_pretrained(model_path,
trust_remote_code=True)
streamer = TextStreamer(tokenizer,
skip_prompt=True,
skip_special_tokens=True)
# Convert prompt to tokens
prompt_template = """\
<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant"""
prompt = "You're standing on the surface of the Earth. "\
"You walk one mile south, one mile west and one mile north. "\
"You end up exactly where you started. Where are you?"
tokens = tokenizer(prompt_template.format(system_message=system_message,prompt=prompt),
return_tensors='pt').input_ids.cuda()
# Generate output
generation_output = model.generate(tokens,
streamer=streamer,
max_new_tokens=512)
```
### 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
| {"language": ["en"], "license": "other", "library_name": "transformers", "tags": ["4-bit", "AWQ", "text-generation", "autotrain_compatible", "endpoints_compatible", "llama3", "comedy", "comedian", "fun", "funny", "llama38b", "laugh", "sarcasm", "roleplay"], "license_name": "llama3", "license_link": "https://llama.meta.com/llama3/license/", "pipeline_tag": "text-generation", "inference": false, "quantized_by": "Suparious"} | solidrust/Llama-3-8B-LexiFun-Uncensored-V1-AWQ | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"4-bit",
"AWQ",
"autotrain_compatible",
"endpoints_compatible",
"llama3",
"comedy",
"comedian",
"fun",
"funny",
"llama38b",
"laugh",
"sarcasm",
"roleplay",
"conversational",
"en",
"license:other",
"text-generation-inference",
"region:us"
]
| null | 2024-04-25T23:59:10+00:00 |
null | peft |
# 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]
### Framework versions
- PEFT 0.10.0 | {"library_name": "peft", "base_model": "microsoft/resnet-18"} | pintu5057/resnet50-finetuned-lora-food101 | null | [
"peft",
"arxiv:1910.09700",
"base_model:microsoft/resnet-18",
"region:us"
]
| null | 2024-04-25T23:59:26+00:00 |
text-generation | transformers | {} | Weni/WeniGPT-Agents-Mistral-1.0.19-SFT-AWQ | null | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"conversational",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"4-bit",
"region:us"
]
| null | 2024-04-26T00:01:37+00:00 |
|
null | peft |
<!-- 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. -->
# GUE_prom_prom_core_notata-seqsight_4096_512_27M-L1_f
This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_4096_512_27M](https://huggingface.co/mahdibaghbanzadeh/seqsight_4096_512_27M) on the [mahdibaghbanzadeh/GUE_prom_prom_core_notata](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_prom_prom_core_notata) dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3761
- F1 Score: 0.8319
- Accuracy: 0.8319
## 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: 0.0005
- train_batch_size: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 10000
### Training results
| Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:|
| 0.513 | 0.6 | 200 | 0.4105 | 0.8110 | 0.8110 |
| 0.4285 | 1.2 | 400 | 0.3944 | 0.8248 | 0.8248 |
| 0.4171 | 1.81 | 600 | 0.3870 | 0.8242 | 0.8242 |
| 0.4149 | 2.41 | 800 | 0.3811 | 0.8285 | 0.8285 |
| 0.4023 | 3.01 | 1000 | 0.3781 | 0.8316 | 0.8315 |
| 0.3974 | 3.61 | 1200 | 0.3764 | 0.8311 | 0.8312 |
| 0.3996 | 4.22 | 1400 | 0.3751 | 0.8332 | 0.8332 |
| 0.3985 | 4.82 | 1600 | 0.3719 | 0.8357 | 0.8357 |
| 0.3867 | 5.42 | 1800 | 0.3783 | 0.8292 | 0.8293 |
| 0.3902 | 6.02 | 2000 | 0.3708 | 0.8380 | 0.8381 |
| 0.3882 | 6.63 | 2200 | 0.3686 | 0.8355 | 0.8355 |
| 0.3873 | 7.23 | 2400 | 0.3708 | 0.8358 | 0.8361 |
| 0.3839 | 7.83 | 2600 | 0.3672 | 0.8351 | 0.8351 |
| 0.3785 | 8.43 | 2800 | 0.3707 | 0.8363 | 0.8366 |
| 0.3835 | 9.04 | 3000 | 0.3676 | 0.8379 | 0.8379 |
| 0.3774 | 9.64 | 3200 | 0.3665 | 0.8340 | 0.8340 |
| 0.3786 | 10.24 | 3400 | 0.3659 | 0.8381 | 0.8381 |
| 0.3766 | 10.84 | 3600 | 0.3652 | 0.8359 | 0.8359 |
| 0.3782 | 11.45 | 3800 | 0.3643 | 0.8377 | 0.8378 |
| 0.3758 | 12.05 | 4000 | 0.3644 | 0.8344 | 0.8344 |
| 0.3733 | 12.65 | 4200 | 0.3650 | 0.8378 | 0.8378 |
| 0.3766 | 13.25 | 4400 | 0.3643 | 0.8366 | 0.8366 |
| 0.3782 | 13.86 | 4600 | 0.3645 | 0.8372 | 0.8372 |
| 0.3719 | 14.46 | 4800 | 0.3645 | 0.8366 | 0.8366 |
| 0.3725 | 15.06 | 5000 | 0.3664 | 0.8349 | 0.8349 |
| 0.3686 | 15.66 | 5200 | 0.3636 | 0.8389 | 0.8389 |
| 0.3675 | 16.27 | 5400 | 0.3659 | 0.8391 | 0.8391 |
| 0.3702 | 16.87 | 5600 | 0.3658 | 0.8398 | 0.8400 |
| 0.3663 | 17.47 | 5800 | 0.3657 | 0.8382 | 0.8383 |
| 0.3736 | 18.07 | 6000 | 0.3640 | 0.8404 | 0.8406 |
| 0.3679 | 18.67 | 6200 | 0.3627 | 0.8394 | 0.8395 |
| 0.3682 | 19.28 | 6400 | 0.3647 | 0.8389 | 0.8389 |
| 0.3685 | 19.88 | 6600 | 0.3632 | 0.8394 | 0.8395 |
| 0.3622 | 20.48 | 6800 | 0.3645 | 0.8393 | 0.8395 |
| 0.3736 | 21.08 | 7000 | 0.3627 | 0.8412 | 0.8413 |
| 0.3691 | 21.69 | 7200 | 0.3637 | 0.8378 | 0.8378 |
| 0.3628 | 22.29 | 7400 | 0.3633 | 0.8379 | 0.8379 |
| 0.366 | 22.89 | 7600 | 0.3635 | 0.8404 | 0.8404 |
| 0.3676 | 23.49 | 7800 | 0.3635 | 0.8383 | 0.8383 |
| 0.3687 | 24.1 | 8000 | 0.3634 | 0.8397 | 0.8398 |
| 0.3699 | 24.7 | 8200 | 0.3628 | 0.8388 | 0.8389 |
| 0.3622 | 25.3 | 8400 | 0.3642 | 0.8407 | 0.8408 |
| 0.3661 | 25.9 | 8600 | 0.3630 | 0.8392 | 0.8393 |
| 0.3672 | 26.51 | 8800 | 0.3641 | 0.8387 | 0.8387 |
| 0.3653 | 27.11 | 9000 | 0.3631 | 0.8383 | 0.8383 |
| 0.3693 | 27.71 | 9200 | 0.3630 | 0.8379 | 0.8379 |
| 0.3568 | 28.31 | 9400 | 0.3638 | 0.8396 | 0.8396 |
| 0.3645 | 28.92 | 9600 | 0.3635 | 0.8377 | 0.8378 |
| 0.367 | 29.52 | 9800 | 0.3633 | 0.8375 | 0.8376 |
| 0.3569 | 30.12 | 10000 | 0.3635 | 0.8377 | 0.8378 |
### Framework versions
- PEFT 0.9.0
- Transformers 4.38.2
- Pytorch 2.2.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2 | {"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_4096_512_27M", "model-index": [{"name": "GUE_prom_prom_core_notata-seqsight_4096_512_27M-L1_f", "results": []}]} | mahdibaghbanzadeh/GUE_prom_prom_core_notata-seqsight_4096_512_27M-L1_f | null | [
"peft",
"safetensors",
"generated_from_trainer",
"base_model:mahdibaghbanzadeh/seqsight_4096_512_27M",
"region:us"
]
| null | 2024-04-26T00:02:32+00:00 |
text-generation | transformers | # LYNN - AI for Roleplay
<img src="./reallynn.png" alt="it's lynn!" width="340"/>
> [!TIP]
> No issue found... yet..
# Soliloquy-L3
Soliloquy-L3 is a highly capable roleplaying model designed for immersive, dynamic experiences. Trained on over 250 million tokens of roleplaying data, Soliloquy-L3 has a vast knowledge base, rich literary expression, and support for up to 24k context length. It outperforms existing ~13B models, delivering enhanced roleplaying capabilities.
## What's Changed
- 100% Retrieval
- Better Instruction Following
## Model Info
| Context Length | Parameter | Prompt Template | isErp |
| --- | --- | --- | --- |
| 24k(24576) | 8B | Llama 3 Chat | Partly |
## Prompt Template
Use can you following jinja2 template. Which is identical to chat_template in [tokenizer_config](./tokenizer_config.json).
```
{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}
```
## License
This model is licensed under the Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International Public License, under [META LLAMA 3 COMMUNITY LICENSE AGREEMENT](https://llama.meta.com/llama3/license/)
If you would like to use this model for commercial purposes, please use our proprietary API. (Currently avilable at OpenRouter)
For non-commercial use, please adhere to the terms of the CC BY-NC-SA 4.0 license. You are free to share and adapt the model for non-commercial purposes, provided you give appropriate credit, indicate if changes were made, and do not imply endorsement by the licensor.
For more information about the CC BY-NC 4.0 license, please visit: https://creativecommons.org/licenses/by-nc-sa/4.0/
If you have any questions or would like to inquire about licensing, please contact us.
## Llama 3 Intended Use
**Intended Use Cases** Llama 3 is intended for commercial and research use in English. Instruction tuned models are intended for assistant-like chat, whereas pretrained models can be adapted for a variety of natural language generation tasks.
**Out-of-scope** Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in any other way that is prohibited by the Acceptable Use Policy and Llama 3 Community License. Use in languages other than English**.
**Note: Developers may fine-tune Llama 3 models for languages beyond English provided they comply with the Llama 3 Community License and the Acceptable Use Policy.
[https://llama.meta.com/llama3/license](https://llama.meta.com/llama3/license)
## Join our Discord
[**Join LYNN Discord**](https://discord.gg/xuZVqUyG4Y) | {"language": ["en"], "license": "cc-by-nc-sa-4.0"} | openlynn/Llama-3-Soliloquy-8B-v2 | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"en",
"license:cc-by-nc-sa-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-26T00:02:51+00:00 |
null | null | {"license": "mit"} | camembercik/soft-belle_kiof | null | [
"license:mit",
"region:us"
]
| null | 2024-04-26T00:05:05+00:00 |
|
null | null | {} | daitaostark/mjverify | null | [
"region:us"
]
| null | 2024-04-26T00:06:34+00:00 |
|
null | null | {} | thereal5h3ll/my-awesome-model | null | [
"tensorboard",
"region:us"
]
| null | 2024-04-26T00:07:27+00:00 |
|
null | peft |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# results-Meta-Llama-3-8B-qlora-pos-no-tag
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.4650
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 12
- eval_batch_size: 12
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 10
- num_epochs: 1
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 1.5879 | 0.2 | 162 | 1.6919 |
| 1.2045 | 0.4 | 324 | 1.5618 |
| 1.5776 | 0.6 | 486 | 1.5159 |
| 1.6051 | 0.8 | 648 | 1.4803 |
| 1.3521 | 1.0 | 810 | 1.4650 |
### Framework versions
- PEFT 0.10.0
- Transformers 4.40.1
- Pytorch 2.2.1
- Datasets 2.19.0
- Tokenizers 0.19.1 | {"license": "other", "library_name": "peft", "tags": ["trl", "sft", "generated_from_trainer"], "base_model": "meta-llama/Meta-Llama-3-8B", "model-index": [{"name": "results-Meta-Llama-3-8B-qlora-pos-no-tag", "results": []}]} | AlienKevin/Meta-Llama-3-8B-qlora-pos-no-tag | null | [
"peft",
"safetensors",
"trl",
"sft",
"generated_from_trainer",
"base_model:meta-llama/Meta-Llama-3-8B",
"license:other",
"region:us"
]
| null | 2024-04-26T00:08:10+00:00 |
text-generation | transformers | {} | jva96160/sug | null | [
"transformers",
"safetensors",
"gemma",
"text-generation",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-26T00:08:44+00:00 |
|
null | peft |
<!-- 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. -->
# GUE_prom_prom_core_notata-seqsight_4096_512_27M-L8_f
This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_4096_512_27M](https://huggingface.co/mahdibaghbanzadeh/seqsight_4096_512_27M) on the [mahdibaghbanzadeh/GUE_prom_prom_core_notata](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_prom_prom_core_notata) dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3711
- F1 Score: 0.8381
- Accuracy: 0.8381
## 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: 0.0005
- train_batch_size: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 10000
### Training results
| Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:|
| 0.4946 | 0.6 | 200 | 0.3979 | 0.8210 | 0.8210 |
| 0.4113 | 1.2 | 400 | 0.3835 | 0.8268 | 0.8268 |
| 0.3993 | 1.81 | 600 | 0.3786 | 0.8324 | 0.8325 |
| 0.3946 | 2.41 | 800 | 0.3719 | 0.8341 | 0.8342 |
| 0.3859 | 3.01 | 1000 | 0.3699 | 0.8347 | 0.8347 |
| 0.3787 | 3.61 | 1200 | 0.3684 | 0.8363 | 0.8364 |
| 0.3826 | 4.22 | 1400 | 0.3691 | 0.8334 | 0.8334 |
| 0.38 | 4.82 | 1600 | 0.3659 | 0.8376 | 0.8378 |
| 0.3683 | 5.42 | 1800 | 0.3761 | 0.8320 | 0.8321 |
| 0.3727 | 6.02 | 2000 | 0.3677 | 0.8348 | 0.8349 |
| 0.37 | 6.63 | 2200 | 0.3631 | 0.8394 | 0.8395 |
| 0.3673 | 7.23 | 2400 | 0.3682 | 0.8388 | 0.8391 |
| 0.3668 | 7.83 | 2600 | 0.3654 | 0.8370 | 0.8370 |
| 0.3611 | 8.43 | 2800 | 0.3695 | 0.8393 | 0.8396 |
| 0.366 | 9.04 | 3000 | 0.3630 | 0.8379 | 0.8379 |
| 0.3581 | 9.64 | 3200 | 0.3654 | 0.8410 | 0.8410 |
| 0.3567 | 10.24 | 3400 | 0.3664 | 0.8414 | 0.8413 |
| 0.3565 | 10.84 | 3600 | 0.3609 | 0.8408 | 0.8408 |
| 0.3568 | 11.45 | 3800 | 0.3625 | 0.8398 | 0.8398 |
| 0.3566 | 12.05 | 4000 | 0.3623 | 0.8431 | 0.8430 |
| 0.3516 | 12.65 | 4200 | 0.3641 | 0.8423 | 0.8423 |
| 0.3555 | 13.25 | 4400 | 0.3625 | 0.8413 | 0.8413 |
| 0.356 | 13.86 | 4600 | 0.3627 | 0.8419 | 0.8419 |
| 0.3493 | 14.46 | 4800 | 0.3636 | 0.8410 | 0.8410 |
| 0.3501 | 15.06 | 5000 | 0.3611 | 0.8406 | 0.8406 |
| 0.3442 | 15.66 | 5200 | 0.3626 | 0.8410 | 0.8410 |
| 0.3424 | 16.27 | 5400 | 0.3660 | 0.8421 | 0.8421 |
| 0.347 | 16.87 | 5600 | 0.3637 | 0.8410 | 0.8412 |
| 0.3425 | 17.47 | 5800 | 0.3662 | 0.8407 | 0.8408 |
| 0.3485 | 18.07 | 6000 | 0.3633 | 0.8407 | 0.8408 |
| 0.3434 | 18.67 | 6200 | 0.3618 | 0.8451 | 0.8451 |
| 0.3447 | 19.28 | 6400 | 0.3648 | 0.8412 | 0.8412 |
| 0.3414 | 19.88 | 6600 | 0.3630 | 0.8423 | 0.8423 |
| 0.3355 | 20.48 | 6800 | 0.3638 | 0.8428 | 0.8428 |
| 0.3486 | 21.08 | 7000 | 0.3632 | 0.8414 | 0.8415 |
| 0.3436 | 21.69 | 7200 | 0.3641 | 0.8417 | 0.8417 |
| 0.3344 | 22.29 | 7400 | 0.3638 | 0.8409 | 0.8410 |
| 0.3402 | 22.89 | 7600 | 0.3635 | 0.8436 | 0.8436 |
| 0.3402 | 23.49 | 7800 | 0.3638 | 0.8413 | 0.8413 |
| 0.3409 | 24.1 | 8000 | 0.3655 | 0.8426 | 0.8427 |
| 0.3419 | 24.7 | 8200 | 0.3634 | 0.8430 | 0.8430 |
| 0.3345 | 25.3 | 8400 | 0.3666 | 0.8426 | 0.8427 |
| 0.3385 | 25.9 | 8600 | 0.3644 | 0.8421 | 0.8421 |
| 0.3397 | 26.51 | 8800 | 0.3656 | 0.8408 | 0.8408 |
| 0.3379 | 27.11 | 9000 | 0.3643 | 0.8427 | 0.8427 |
| 0.3405 | 27.71 | 9200 | 0.3648 | 0.8413 | 0.8413 |
| 0.3298 | 28.31 | 9400 | 0.3653 | 0.8422 | 0.8423 |
| 0.3339 | 28.92 | 9600 | 0.3653 | 0.8415 | 0.8415 |
| 0.3384 | 29.52 | 9800 | 0.3649 | 0.8419 | 0.8419 |
| 0.3296 | 30.12 | 10000 | 0.3652 | 0.8419 | 0.8419 |
### Framework versions
- PEFT 0.9.0
- Transformers 4.38.2
- Pytorch 2.2.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2 | {"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_4096_512_27M", "model-index": [{"name": "GUE_prom_prom_core_notata-seqsight_4096_512_27M-L8_f", "results": []}]} | mahdibaghbanzadeh/GUE_prom_prom_core_notata-seqsight_4096_512_27M-L8_f | null | [
"peft",
"safetensors",
"generated_from_trainer",
"base_model:mahdibaghbanzadeh/seqsight_4096_512_27M",
"region:us"
]
| null | 2024-04-26T00:09:10+00:00 |
text-generation | transformers | {"license": "apache-2.0"} | mucai/llava-1.5-llama-3-8b | null | [
"transformers",
"safetensors",
"llava_llama",
"text-generation",
"conversational",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-26T00:10:54+00:00 |
|
null | peft |
<!-- 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. -->
# GUE_prom_prom_core_notata-seqsight_4096_512_27M-L32_f
This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_4096_512_27M](https://huggingface.co/mahdibaghbanzadeh/seqsight_4096_512_27M) on the [mahdibaghbanzadeh/GUE_prom_prom_core_notata](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_prom_prom_core_notata) dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3849
- F1 Score: 0.8389
- Accuracy: 0.8389
## 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: 0.0005
- train_batch_size: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 10000
### Training results
| Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:|
| 0.4752 | 0.6 | 200 | 0.3927 | 0.8251 | 0.8253 |
| 0.3995 | 1.2 | 400 | 0.3736 | 0.8333 | 0.8332 |
| 0.3885 | 1.81 | 600 | 0.3747 | 0.8361 | 0.8363 |
| 0.3838 | 2.41 | 800 | 0.3656 | 0.8376 | 0.8376 |
| 0.3771 | 3.01 | 1000 | 0.3656 | 0.8401 | 0.8402 |
| 0.3686 | 3.61 | 1200 | 0.3635 | 0.8391 | 0.8393 |
| 0.3736 | 4.22 | 1400 | 0.3639 | 0.8391 | 0.8391 |
| 0.3697 | 4.82 | 1600 | 0.3631 | 0.8403 | 0.8404 |
| 0.3546 | 5.42 | 1800 | 0.3739 | 0.8358 | 0.8359 |
| 0.3609 | 6.02 | 2000 | 0.3671 | 0.8366 | 0.8368 |
| 0.354 | 6.63 | 2200 | 0.3606 | 0.8421 | 0.8421 |
| 0.3516 | 7.23 | 2400 | 0.3677 | 0.8441 | 0.8444 |
| 0.3522 | 7.83 | 2600 | 0.3630 | 0.8398 | 0.8398 |
| 0.3443 | 8.43 | 2800 | 0.3652 | 0.8434 | 0.8436 |
| 0.3496 | 9.04 | 3000 | 0.3636 | 0.8411 | 0.8412 |
| 0.3398 | 9.64 | 3200 | 0.3654 | 0.8408 | 0.8408 |
| 0.3375 | 10.24 | 3400 | 0.3706 | 0.8428 | 0.8428 |
| 0.3367 | 10.84 | 3600 | 0.3582 | 0.8438 | 0.8438 |
| 0.334 | 11.45 | 3800 | 0.3623 | 0.8432 | 0.8432 |
| 0.336 | 12.05 | 4000 | 0.3645 | 0.8432 | 0.8432 |
| 0.3294 | 12.65 | 4200 | 0.3638 | 0.8441 | 0.8442 |
| 0.3333 | 13.25 | 4400 | 0.3661 | 0.8449 | 0.8449 |
| 0.3318 | 13.86 | 4600 | 0.3664 | 0.8444 | 0.8444 |
| 0.3246 | 14.46 | 4800 | 0.3698 | 0.8442 | 0.8442 |
| 0.3244 | 15.06 | 5000 | 0.3620 | 0.8461 | 0.8461 |
| 0.316 | 15.66 | 5200 | 0.3694 | 0.8449 | 0.8449 |
| 0.3185 | 16.27 | 5400 | 0.3725 | 0.8453 | 0.8453 |
| 0.3206 | 16.87 | 5600 | 0.3702 | 0.8444 | 0.8447 |
| 0.3126 | 17.47 | 5800 | 0.3728 | 0.8432 | 0.8432 |
| 0.3201 | 18.07 | 6000 | 0.3708 | 0.8416 | 0.8417 |
| 0.3123 | 18.67 | 6200 | 0.3676 | 0.8472 | 0.8472 |
| 0.3133 | 19.28 | 6400 | 0.3782 | 0.8417 | 0.8417 |
| 0.3101 | 19.88 | 6600 | 0.3693 | 0.8466 | 0.8466 |
| 0.3041 | 20.48 | 6800 | 0.3739 | 0.8453 | 0.8453 |
| 0.3139 | 21.08 | 7000 | 0.3737 | 0.8423 | 0.8425 |
| 0.3097 | 21.69 | 7200 | 0.3740 | 0.8427 | 0.8427 |
| 0.302 | 22.29 | 7400 | 0.3712 | 0.8466 | 0.8466 |
| 0.3033 | 22.89 | 7600 | 0.3771 | 0.8419 | 0.8419 |
| 0.3045 | 23.49 | 7800 | 0.3736 | 0.8452 | 0.8453 |
| 0.3038 | 24.1 | 8000 | 0.3799 | 0.8416 | 0.8417 |
| 0.3031 | 24.7 | 8200 | 0.3794 | 0.8425 | 0.8427 |
| 0.2975 | 25.3 | 8400 | 0.3820 | 0.8435 | 0.8436 |
| 0.3013 | 25.9 | 8600 | 0.3777 | 0.8447 | 0.8447 |
| 0.3009 | 26.51 | 8800 | 0.3792 | 0.8413 | 0.8413 |
| 0.2994 | 27.11 | 9000 | 0.3782 | 0.8474 | 0.8474 |
| 0.3003 | 27.71 | 9200 | 0.3807 | 0.8447 | 0.8447 |
| 0.2913 | 28.31 | 9400 | 0.3808 | 0.8452 | 0.8453 |
| 0.2949 | 28.92 | 9600 | 0.3821 | 0.8439 | 0.8440 |
| 0.2986 | 29.52 | 9800 | 0.3807 | 0.8441 | 0.8442 |
| 0.2918 | 30.12 | 10000 | 0.3810 | 0.8441 | 0.8442 |
### Framework versions
- PEFT 0.9.0
- Transformers 4.38.2
- Pytorch 2.2.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2 | {"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_4096_512_27M", "model-index": [{"name": "GUE_prom_prom_core_notata-seqsight_4096_512_27M-L32_f", "results": []}]} | mahdibaghbanzadeh/GUE_prom_prom_core_notata-seqsight_4096_512_27M-L32_f | null | [
"peft",
"safetensors",
"generated_from_trainer",
"base_model:mahdibaghbanzadeh/seqsight_4096_512_27M",
"region:us"
]
| null | 2024-04-26T00:11:48+00:00 |
reinforcement-learning | stable-baselines3 |
# **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
...
```
| {"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": "234.88 +/- 38.33", "name": "mean_reward", "verified": false}]}]}]} | rvukasin/LundarLanderV2Exam | null | [
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
]
| null | 2024-04-26T00:12:30+00:00 |
null | peft |
<!-- 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. -->
# GUE_prom_prom_core_tata-seqsight_4096_512_27M-L1_f
This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_4096_512_27M](https://huggingface.co/mahdibaghbanzadeh/seqsight_4096_512_27M) on the [mahdibaghbanzadeh/GUE_prom_prom_core_tata](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_prom_prom_core_tata) dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4158
- F1 Score: 0.8367
- Accuracy: 0.8369
## 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: 0.0005
- train_batch_size: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 10000
### Training results
| Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy |
|:-------------:|:------:|:-----:|:---------------:|:--------:|:--------:|
| 0.5875 | 5.13 | 200 | 0.5748 | 0.7050 | 0.7080 |
| 0.53 | 10.26 | 400 | 0.5527 | 0.7108 | 0.7145 |
| 0.4871 | 15.38 | 600 | 0.5520 | 0.7308 | 0.7374 |
| 0.4537 | 20.51 | 800 | 0.4943 | 0.7524 | 0.7537 |
| 0.4267 | 25.64 | 1000 | 0.4760 | 0.7633 | 0.7635 |
| 0.4119 | 30.77 | 1200 | 0.4547 | 0.7793 | 0.7798 |
| 0.3932 | 35.9 | 1400 | 0.4493 | 0.7926 | 0.7928 |
| 0.3768 | 41.03 | 1600 | 0.4332 | 0.7943 | 0.7945 |
| 0.3671 | 46.15 | 1800 | 0.4303 | 0.8074 | 0.8075 |
| 0.3551 | 51.28 | 2000 | 0.4469 | 0.8020 | 0.8026 |
| 0.3487 | 56.41 | 2200 | 0.4419 | 0.8120 | 0.8124 |
| 0.3411 | 61.54 | 2400 | 0.4270 | 0.8189 | 0.8189 |
| 0.3347 | 66.67 | 2600 | 0.4421 | 0.8118 | 0.8124 |
| 0.3342 | 71.79 | 2800 | 0.4239 | 0.8254 | 0.8254 |
| 0.324 | 76.92 | 3000 | 0.4416 | 0.8002 | 0.8010 |
| 0.3203 | 82.05 | 3200 | 0.4325 | 0.8136 | 0.8140 |
| 0.3129 | 87.18 | 3400 | 0.4325 | 0.8269 | 0.8271 |
| 0.3088 | 92.31 | 3600 | 0.4201 | 0.8287 | 0.8287 |
| 0.3016 | 97.44 | 3800 | 0.4261 | 0.8286 | 0.8287 |
| 0.3019 | 102.56 | 4000 | 0.4237 | 0.8271 | 0.8271 |
| 0.3016 | 107.69 | 4200 | 0.4335 | 0.8118 | 0.8124 |
| 0.2978 | 112.82 | 4400 | 0.4227 | 0.8156 | 0.8157 |
| 0.2942 | 117.95 | 4600 | 0.4463 | 0.8119 | 0.8124 |
| 0.2842 | 123.08 | 4800 | 0.4366 | 0.8170 | 0.8173 |
| 0.2877 | 128.21 | 5000 | 0.4306 | 0.8124 | 0.8124 |
| 0.2805 | 133.33 | 5200 | 0.4267 | 0.8205 | 0.8206 |
| 0.2838 | 138.46 | 5400 | 0.4198 | 0.8271 | 0.8271 |
| 0.2801 | 143.59 | 5600 | 0.4294 | 0.8172 | 0.8173 |
| 0.2791 | 148.72 | 5800 | 0.4394 | 0.8187 | 0.8189 |
| 0.2711 | 153.85 | 6000 | 0.4366 | 0.8287 | 0.8287 |
| 0.2731 | 158.97 | 6200 | 0.4305 | 0.8238 | 0.8238 |
| 0.2681 | 164.1 | 6400 | 0.4437 | 0.8233 | 0.8238 |
| 0.273 | 169.23 | 6600 | 0.4265 | 0.8287 | 0.8287 |
| 0.2681 | 174.36 | 6800 | 0.4337 | 0.8352 | 0.8352 |
| 0.2678 | 179.49 | 7000 | 0.4389 | 0.8236 | 0.8238 |
| 0.2602 | 184.62 | 7200 | 0.4337 | 0.8335 | 0.8336 |
| 0.2641 | 189.74 | 7400 | 0.4402 | 0.8235 | 0.8238 |
| 0.263 | 194.87 | 7600 | 0.4368 | 0.8253 | 0.8254 |
| 0.2605 | 200.0 | 7800 | 0.4275 | 0.8222 | 0.8222 |
| 0.2605 | 205.13 | 8000 | 0.4403 | 0.8203 | 0.8206 |
| 0.2627 | 210.26 | 8200 | 0.4301 | 0.8237 | 0.8238 |
| 0.2551 | 215.38 | 8400 | 0.4336 | 0.8204 | 0.8206 |
| 0.2574 | 220.51 | 8600 | 0.4409 | 0.8170 | 0.8173 |
| 0.2538 | 225.64 | 8800 | 0.4423 | 0.8220 | 0.8222 |
| 0.2579 | 230.77 | 9000 | 0.4403 | 0.8220 | 0.8222 |
| 0.2585 | 235.9 | 9200 | 0.4422 | 0.8186 | 0.8189 |
| 0.257 | 241.03 | 9400 | 0.4378 | 0.8236 | 0.8238 |
| 0.256 | 246.15 | 9600 | 0.4427 | 0.8202 | 0.8206 |
| 0.2517 | 251.28 | 9800 | 0.4393 | 0.8219 | 0.8222 |
| 0.249 | 256.41 | 10000 | 0.4379 | 0.8236 | 0.8238 |
### Framework versions
- PEFT 0.9.0
- Transformers 4.38.2
- Pytorch 2.2.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2 | {"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_4096_512_27M", "model-index": [{"name": "GUE_prom_prom_core_tata-seqsight_4096_512_27M-L1_f", "results": []}]} | mahdibaghbanzadeh/GUE_prom_prom_core_tata-seqsight_4096_512_27M-L1_f | null | [
"peft",
"safetensors",
"generated_from_trainer",
"base_model:mahdibaghbanzadeh/seqsight_4096_512_27M",
"region:us"
]
| null | 2024-04-26T00:15:48+00:00 |
null | peft |
<!-- 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. -->
# GUE_prom_prom_core_tata-seqsight_4096_512_27M-L8_f
This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_4096_512_27M](https://huggingface.co/mahdibaghbanzadeh/seqsight_4096_512_27M) on the [mahdibaghbanzadeh/GUE_prom_prom_core_tata](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_prom_prom_core_tata) dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4048
- F1 Score: 0.8284
- Accuracy: 0.8287
## 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: 0.0005
- train_batch_size: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 10000
### Training results
| Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy |
|:-------------:|:------:|:-----:|:---------------:|:--------:|:--------:|
| 0.5669 | 5.13 | 200 | 0.5362 | 0.7234 | 0.7243 |
| 0.4686 | 10.26 | 400 | 0.5079 | 0.7520 | 0.7553 |
| 0.4079 | 15.38 | 600 | 0.4564 | 0.7851 | 0.7863 |
| 0.3718 | 20.51 | 800 | 0.4229 | 0.8108 | 0.8108 |
| 0.3403 | 25.64 | 1000 | 0.4323 | 0.8105 | 0.8108 |
| 0.3226 | 30.77 | 1200 | 0.4169 | 0.8189 | 0.8189 |
| 0.299 | 35.9 | 1400 | 0.4195 | 0.8319 | 0.8320 |
| 0.286 | 41.03 | 1600 | 0.4204 | 0.8364 | 0.8369 |
| 0.2714 | 46.15 | 1800 | 0.4206 | 0.8320 | 0.8320 |
| 0.2548 | 51.28 | 2000 | 0.4415 | 0.8170 | 0.8173 |
| 0.2454 | 56.41 | 2200 | 0.4503 | 0.8219 | 0.8222 |
| 0.2378 | 61.54 | 2400 | 0.4227 | 0.8320 | 0.8320 |
| 0.2271 | 66.67 | 2600 | 0.4641 | 0.8267 | 0.8271 |
| 0.2226 | 71.79 | 2800 | 0.4556 | 0.8335 | 0.8336 |
| 0.2052 | 76.92 | 3000 | 0.5019 | 0.8199 | 0.8206 |
| 0.1932 | 82.05 | 3200 | 0.4784 | 0.8302 | 0.8303 |
| 0.184 | 87.18 | 3400 | 0.5076 | 0.8299 | 0.8303 |
| 0.1753 | 92.31 | 3600 | 0.5294 | 0.8249 | 0.8254 |
| 0.1677 | 97.44 | 3800 | 0.5041 | 0.8302 | 0.8303 |
| 0.1612 | 102.56 | 4000 | 0.5040 | 0.8270 | 0.8271 |
| 0.1543 | 107.69 | 4200 | 0.5714 | 0.8214 | 0.8222 |
| 0.1509 | 112.82 | 4400 | 0.5209 | 0.8302 | 0.8303 |
| 0.1397 | 117.95 | 4600 | 0.5513 | 0.8219 | 0.8222 |
| 0.1372 | 123.08 | 4800 | 0.5749 | 0.8232 | 0.8238 |
| 0.1294 | 128.21 | 5000 | 0.5562 | 0.8235 | 0.8238 |
| 0.1263 | 133.33 | 5200 | 0.5656 | 0.8302 | 0.8303 |
| 0.1208 | 138.46 | 5400 | 0.5864 | 0.8286 | 0.8287 |
| 0.114 | 143.59 | 5600 | 0.6225 | 0.8134 | 0.8140 |
| 0.1147 | 148.72 | 5800 | 0.6308 | 0.8216 | 0.8222 |
| 0.1099 | 153.85 | 6000 | 0.6045 | 0.8253 | 0.8254 |
| 0.107 | 158.97 | 6200 | 0.6583 | 0.8200 | 0.8206 |
| 0.1038 | 164.1 | 6400 | 0.6717 | 0.8198 | 0.8206 |
| 0.1012 | 169.23 | 6600 | 0.6425 | 0.8202 | 0.8206 |
| 0.1005 | 174.36 | 6800 | 0.6677 | 0.8217 | 0.8222 |
| 0.0968 | 179.49 | 7000 | 0.6629 | 0.8154 | 0.8157 |
| 0.093 | 184.62 | 7200 | 0.6758 | 0.8219 | 0.8222 |
| 0.0951 | 189.74 | 7400 | 0.6438 | 0.8252 | 0.8254 |
| 0.089 | 194.87 | 7600 | 0.6909 | 0.8186 | 0.8189 |
| 0.0879 | 200.0 | 7800 | 0.6710 | 0.8172 | 0.8173 |
| 0.0873 | 205.13 | 8000 | 0.6793 | 0.8251 | 0.8254 |
| 0.0913 | 210.26 | 8200 | 0.6639 | 0.8205 | 0.8206 |
| 0.0847 | 215.38 | 8400 | 0.6647 | 0.8205 | 0.8206 |
| 0.0833 | 220.51 | 8600 | 0.7092 | 0.8118 | 0.8124 |
| 0.0832 | 225.64 | 8800 | 0.6935 | 0.8137 | 0.8140 |
| 0.0826 | 230.77 | 9000 | 0.6918 | 0.8154 | 0.8157 |
| 0.0869 | 235.9 | 9200 | 0.6959 | 0.8136 | 0.8140 |
| 0.0809 | 241.03 | 9400 | 0.6956 | 0.8203 | 0.8206 |
| 0.0816 | 246.15 | 9600 | 0.7071 | 0.8136 | 0.8140 |
| 0.0804 | 251.28 | 9800 | 0.6933 | 0.8203 | 0.8206 |
| 0.0769 | 256.41 | 10000 | 0.6983 | 0.8187 | 0.8189 |
### Framework versions
- PEFT 0.9.0
- Transformers 4.38.2
- Pytorch 2.2.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2 | {"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_4096_512_27M", "model-index": [{"name": "GUE_prom_prom_core_tata-seqsight_4096_512_27M-L8_f", "results": []}]} | mahdibaghbanzadeh/GUE_prom_prom_core_tata-seqsight_4096_512_27M-L8_f | null | [
"peft",
"safetensors",
"generated_from_trainer",
"base_model:mahdibaghbanzadeh/seqsight_4096_512_27M",
"region:us"
]
| null | 2024-04-26T00:15:57+00:00 |
text-classification | transformers |
<!-- 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. -->
# test_trainer
This model is a fine-tuned version of [google-bert/bert-base-cased](https://huggingface.co/google-bert/bert-base-cased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0672
- Accuracy: 0.9888
## 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: 3.0
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.1056 | 1.0 | 2374 | 0.0639 | 0.9872 |
| 0.0533 | 2.0 | 4748 | 0.0598 | 0.9872 |
| 0.0165 | 3.0 | 7122 | 0.0672 | 0.9888 |
### Framework versions
- Transformers 4.40.0
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1
| {"license": "apache-2.0", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "google-bert/bert-base-cased", "model-index": [{"name": "test_trainer", "results": []}]} | SRBaxla/test_trainer | null | [
"transformers",
"tensorboard",
"safetensors",
"bert",
"text-classification",
"generated_from_trainer",
"base_model:google-bert/bert-base-cased",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-26T00:16:36+00:00 |
null | null |
# Meta-Llama-3-8b-Lexi-Uninstruct-function-calling-json-mode-Task-Arithmetic-v0.2A
Meta-Llama-3-8b-Lexi-Uninstruct-function-calling-json-mode-Task-Arithmetic-v0.2A is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [hiieu/Meta-Llama-3-8B-Instruct-function-calling-json-mode](https://huggingface.co/hiieu/Meta-Llama-3-8B-Instruct-function-calling-json-mode)
* [Orenguteng/Lexi-Llama-3-8B-Uncensored](https://huggingface.co/Orenguteng/Lexi-Llama-3-8B-Uncensored)
* [NousResearch/Meta-Llama-3-8B](https://huggingface.co/NousResearch/Meta-Llama-3-8B)
* [NousResearch/Meta-Llama-3-8B-Instruct](https://huggingface.co/NousResearch/Meta-Llama-3-8B-Instruct)
## 🧩 Configuration
```yaml
slices:
- sources:
- model: hiieu/Meta-Llama-3-8B-Instruct-function-calling-json-mode
parameters:
weight: 1
layer_range: [0, 40]
- model: Orenguteng/Lexi-Llama-3-8B-Uncensored
parameters:
weight: 1
layer_range: [0, 40]
- model: NousResearch/Meta-Llama-3-8B
parameters:
weight: 0.3
layer_range: [0, 40]
- model: NousResearch/Meta-Llama-3-8B-Instruct
parameters:
weight: 0.7
layer_range: [0, 40]
merge_method: task_arithmetic
base_model: NousResearch/Meta-Llama-3-8B-Instruct
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 = "Nhoodie/Meta-Llama-3-8b-Lexi-Uninstruct-function-calling-json-mode-Task-Arithmetic-v0.2A"
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"])
``` | {"tags": ["merge", "mergekit", "lazymergekit", "hiieu/Meta-Llama-3-8B-Instruct-function-calling-json-mode", "Orenguteng/Lexi-Llama-3-8B-Uncensored", "NousResearch/Meta-Llama-3-8B", "NousResearch/Meta-Llama-3-8B-Instruct"], "base_model": ["hiieu/Meta-Llama-3-8B-Instruct-function-calling-json-mode", "Orenguteng/Lexi-Llama-3-8B-Uncensored", "NousResearch/Meta-Llama-3-8B", "NousResearch/Meta-Llama-3-8B-Instruct"]} | Nhoodie/Meta-Llama-3-8b-Lexi-Uninstruct-function-calling-json-mode-Task-Arithmetic-v0.2A | null | [
"merge",
"mergekit",
"lazymergekit",
"hiieu/Meta-Llama-3-8B-Instruct-function-calling-json-mode",
"Orenguteng/Lexi-Llama-3-8B-Uncensored",
"NousResearch/Meta-Llama-3-8B",
"NousResearch/Meta-Llama-3-8B-Instruct",
"base_model:hiieu/Meta-Llama-3-8B-Instruct-function-calling-json-mode",
"base_model:Orenguteng/Lexi-Llama-3-8B-Uncensored",
"base_model:NousResearch/Meta-Llama-3-8B",
"base_model:NousResearch/Meta-Llama-3-8B-Instruct",
"region:us"
]
| null | 2024-04-26T00:16:43+00:00 |
text-classification | transformers | # merge_out
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 [mllm-dev/merge_diff_data_DROID](https://huggingface.co/mllm-dev/merge_diff_data_DROID) as a base.
### Models Merged
The following models were included in the merge:
* [mllm-dev/merge_diff_data_YELP](https://huggingface.co/mllm-dev/merge_diff_data_YELP)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
base_model: mllm-dev/merge_diff_data_DROID
dtype: float16
merge_method: dare_ties
slices:
- sources:
- layer_range: [0, 12]
model: mllm-dev/merge_diff_data_DROID
- layer_range: [0, 12]
model: mllm-dev/merge_diff_data_YELP
parameters:
density: 0.5
weight: 0.5
```
| {"library_name": "transformers", "tags": ["mergekit", "merge"], "base_model": ["mllm-dev/merge_diff_data_DROID", "mllm-dev/merge_diff_data_YELP"]} | mllm-dev/merge_yelp_droid_dare_ties | null | [
"transformers",
"safetensors",
"gpt2",
"text-classification",
"mergekit",
"merge",
"arxiv:2311.03099",
"arxiv:2306.01708",
"base_model:mllm-dev/merge_diff_data_DROID",
"base_model:mllm-dev/merge_diff_data_YELP",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-26T00:16:55+00:00 |
null | peft |
<!-- 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. -->
# GUE_prom_prom_core_tata-seqsight_4096_512_27M-L32_f
This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_4096_512_27M](https://huggingface.co/mahdibaghbanzadeh/seqsight_4096_512_27M) on the [mahdibaghbanzadeh/GUE_prom_prom_core_tata](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_prom_prom_core_tata) dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7712
- F1 Score: 0.8254
- Accuracy: 0.8254
## 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: 0.0005
- train_batch_size: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 10000
### Training results
| Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy |
|:-------------:|:------:|:-----:|:---------------:|:--------:|:--------:|
| 0.5463 | 5.13 | 200 | 0.5140 | 0.7355 | 0.7357 |
| 0.4209 | 10.26 | 400 | 0.4571 | 0.7812 | 0.7830 |
| 0.3466 | 15.38 | 600 | 0.3850 | 0.8271 | 0.8271 |
| 0.3056 | 20.51 | 800 | 0.3829 | 0.8448 | 0.8450 |
| 0.2597 | 25.64 | 1000 | 0.4199 | 0.8269 | 0.8271 |
| 0.2279 | 30.77 | 1200 | 0.4251 | 0.8336 | 0.8336 |
| 0.1888 | 35.9 | 1400 | 0.4467 | 0.8418 | 0.8418 |
| 0.1625 | 41.03 | 1600 | 0.4917 | 0.8237 | 0.8238 |
| 0.1397 | 46.15 | 1800 | 0.5283 | 0.8251 | 0.8254 |
| 0.1145 | 51.28 | 2000 | 0.5479 | 0.8351 | 0.8352 |
| 0.1062 | 56.41 | 2200 | 0.5837 | 0.8384 | 0.8385 |
| 0.093 | 61.54 | 2400 | 0.6136 | 0.8434 | 0.8434 |
| 0.0849 | 66.67 | 2600 | 0.6030 | 0.8515 | 0.8515 |
| 0.0737 | 71.79 | 2800 | 0.6642 | 0.8433 | 0.8434 |
| 0.0679 | 76.92 | 3000 | 0.7257 | 0.8310 | 0.8320 |
| 0.0638 | 82.05 | 3200 | 0.7174 | 0.8464 | 0.8467 |
| 0.0594 | 87.18 | 3400 | 0.6558 | 0.8416 | 0.8418 |
| 0.0567 | 92.31 | 3600 | 0.6852 | 0.8332 | 0.8336 |
| 0.0505 | 97.44 | 3800 | 0.6678 | 0.8498 | 0.8499 |
| 0.0453 | 102.56 | 4000 | 0.7559 | 0.8315 | 0.8320 |
| 0.0467 | 107.69 | 4200 | 0.7465 | 0.8410 | 0.8418 |
| 0.0454 | 112.82 | 4400 | 0.7221 | 0.8515 | 0.8515 |
| 0.0393 | 117.95 | 4600 | 0.7106 | 0.8515 | 0.8515 |
| 0.0382 | 123.08 | 4800 | 0.8130 | 0.8247 | 0.8254 |
| 0.0353 | 128.21 | 5000 | 0.7361 | 0.8499 | 0.8499 |
| 0.0366 | 133.33 | 5200 | 0.7672 | 0.8432 | 0.8434 |
| 0.033 | 138.46 | 5400 | 0.7653 | 0.8499 | 0.8499 |
| 0.0304 | 143.59 | 5600 | 0.8166 | 0.8482 | 0.8483 |
| 0.0326 | 148.72 | 5800 | 0.8561 | 0.8345 | 0.8352 |
| 0.0309 | 153.85 | 6000 | 0.8551 | 0.8366 | 0.8369 |
| 0.0294 | 158.97 | 6200 | 0.8265 | 0.8398 | 0.8401 |
| 0.0249 | 164.1 | 6400 | 0.8584 | 0.8362 | 0.8369 |
| 0.0261 | 169.23 | 6600 | 0.7970 | 0.8482 | 0.8483 |
| 0.0258 | 174.36 | 6800 | 0.7971 | 0.8417 | 0.8418 |
| 0.0245 | 179.49 | 7000 | 0.8322 | 0.8332 | 0.8336 |
| 0.024 | 184.62 | 7200 | 0.8219 | 0.8465 | 0.8467 |
| 0.0252 | 189.74 | 7400 | 0.8064 | 0.8384 | 0.8385 |
| 0.0238 | 194.87 | 7600 | 0.8080 | 0.8513 | 0.8515 |
| 0.0227 | 200.0 | 7800 | 0.8130 | 0.8466 | 0.8467 |
| 0.0237 | 205.13 | 8000 | 0.8048 | 0.8417 | 0.8418 |
| 0.0229 | 210.26 | 8200 | 0.7948 | 0.8417 | 0.8418 |
| 0.0218 | 215.38 | 8400 | 0.7989 | 0.8499 | 0.8499 |
| 0.0173 | 220.51 | 8600 | 0.8605 | 0.8432 | 0.8434 |
| 0.0197 | 225.64 | 8800 | 0.8345 | 0.8449 | 0.8450 |
| 0.018 | 230.77 | 9000 | 0.8549 | 0.8483 | 0.8483 |
| 0.0197 | 235.9 | 9200 | 0.8607 | 0.8449 | 0.8450 |
| 0.0192 | 241.03 | 9400 | 0.8476 | 0.8416 | 0.8418 |
| 0.0175 | 246.15 | 9600 | 0.8688 | 0.8350 | 0.8352 |
| 0.0181 | 251.28 | 9800 | 0.8570 | 0.8465 | 0.8467 |
| 0.0177 | 256.41 | 10000 | 0.8566 | 0.8432 | 0.8434 |
### Framework versions
- PEFT 0.9.0
- Transformers 4.38.2
- Pytorch 2.2.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2 | {"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_4096_512_27M", "model-index": [{"name": "GUE_prom_prom_core_tata-seqsight_4096_512_27M-L32_f", "results": []}]} | mahdibaghbanzadeh/GUE_prom_prom_core_tata-seqsight_4096_512_27M-L32_f | null | [
"peft",
"safetensors",
"generated_from_trainer",
"base_model:mahdibaghbanzadeh/seqsight_4096_512_27M",
"region:us"
]
| null | 2024-04-26T00:18:55+00:00 |
null | null |
# Meta-Llama-3-8b-Extended-Lexi-Uninstruct-function-calling-json-mode-Task-Arithmetic-v0.0A
Meta-Llama-3-8b-Extended-Lexi-Uninstruct-function-calling-json-mode-Task-Arithmetic-v0.0A is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [hiieu/Meta-Llama-3-8B-Instruct-function-calling-json-mode](https://huggingface.co/hiieu/Meta-Llama-3-8B-Instruct-function-calling-json-mode)
* [Orenguteng/Lexi-Llama-3-8B-Uncensored](https://huggingface.co/Orenguteng/Lexi-Llama-3-8B-Uncensored)
* [NousResearch/Meta-Llama-3-8B](https://huggingface.co/NousResearch/Meta-Llama-3-8B)
* [NousResearch/Meta-Llama-3-8B-Instruct](https://huggingface.co/NousResearch/Meta-Llama-3-8B-Instruct)
## 🧩 Configuration
```yaml
slices:
- sources:
- model: hiieu/Meta-Llama-3-8B-Instruct-function-calling-json-mode
parameters:
weight: 1
layer_range: [8, 40]
- model: Orenguteng/Lexi-Llama-3-8B-Uncensored
parameters:
weight: 1
layer_range: [8, 40]
- model: NousResearch/Meta-Llama-3-8B
parameters:
weight: 0.3
layer_range: [8, 40]
- model: NousResearch/Meta-Llama-3-8B-Instruct
parameters:
weight: 1
layer_range: [0, 32]
merge_method: task_arithmetic
base_model: NousResearch/Meta-Llama-3-8B-Instruct
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 = "Nhoodie/Meta-Llama-3-8b-Extended-Lexi-Uninstruct-function-calling-json-mode-Task-Arithmetic-v0.0A"
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"])
``` | {"tags": ["merge", "mergekit", "lazymergekit", "hiieu/Meta-Llama-3-8B-Instruct-function-calling-json-mode", "Orenguteng/Lexi-Llama-3-8B-Uncensored", "NousResearch/Meta-Llama-3-8B", "NousResearch/Meta-Llama-3-8B-Instruct"], "base_model": ["hiieu/Meta-Llama-3-8B-Instruct-function-calling-json-mode", "Orenguteng/Lexi-Llama-3-8B-Uncensored", "NousResearch/Meta-Llama-3-8B", "NousResearch/Meta-Llama-3-8B-Instruct"]} | Nhoodie/Meta-Llama-3-8b-Extended-Lexi-Uninstruct-function-calling-json-mode-Task-Arithmetic-v0.0A | null | [
"merge",
"mergekit",
"lazymergekit",
"hiieu/Meta-Llama-3-8B-Instruct-function-calling-json-mode",
"Orenguteng/Lexi-Llama-3-8B-Uncensored",
"NousResearch/Meta-Llama-3-8B",
"NousResearch/Meta-Llama-3-8B-Instruct",
"base_model:hiieu/Meta-Llama-3-8B-Instruct-function-calling-json-mode",
"base_model:Orenguteng/Lexi-Llama-3-8B-Uncensored",
"base_model:NousResearch/Meta-Llama-3-8B",
"base_model:NousResearch/Meta-Llama-3-8B-Instruct",
"region:us"
]
| null | 2024-04-26T00:20:17+00:00 |
null | peft |
<!-- 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. -->
# GUE_prom_prom_300_all-seqsight_4096_512_27M-L1_f
This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_4096_512_27M](https://huggingface.co/mahdibaghbanzadeh/seqsight_4096_512_27M) on the [mahdibaghbanzadeh/GUE_prom_prom_300_all](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_prom_prom_300_all) dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2119
- F1 Score: 0.9138
- Accuracy: 0.9139
## 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: 0.0005
- train_batch_size: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 10000
### Training results
| Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:|
| 0.3648 | 0.54 | 200 | 0.2612 | 0.8949 | 0.8949 |
| 0.267 | 1.08 | 400 | 0.2421 | 0.9046 | 0.9046 |
| 0.2578 | 1.62 | 600 | 0.2327 | 0.9095 | 0.9095 |
| 0.241 | 2.16 | 800 | 0.2284 | 0.9121 | 0.9122 |
| 0.2369 | 2.7 | 1000 | 0.2228 | 0.9122 | 0.9122 |
| 0.2325 | 3.24 | 1200 | 0.2205 | 0.9150 | 0.9150 |
| 0.2298 | 3.78 | 1400 | 0.2147 | 0.9159 | 0.9159 |
| 0.2268 | 4.32 | 1600 | 0.2126 | 0.9162 | 0.9162 |
| 0.2181 | 4.86 | 1800 | 0.2131 | 0.9187 | 0.9187 |
| 0.2168 | 5.41 | 2000 | 0.2078 | 0.9204 | 0.9204 |
| 0.2148 | 5.95 | 2200 | 0.2081 | 0.9197 | 0.9198 |
| 0.2126 | 6.49 | 2400 | 0.2026 | 0.9233 | 0.9233 |
| 0.2109 | 7.03 | 2600 | 0.2017 | 0.9225 | 0.9225 |
| 0.2055 | 7.57 | 2800 | 0.2005 | 0.9231 | 0.9231 |
| 0.2081 | 8.11 | 3000 | 0.1986 | 0.9250 | 0.925 |
| 0.2072 | 8.65 | 3200 | 0.1968 | 0.9235 | 0.9235 |
| 0.1997 | 9.19 | 3400 | 0.1984 | 0.9238 | 0.9238 |
| 0.2 | 9.73 | 3600 | 0.1942 | 0.9255 | 0.9255 |
| 0.2062 | 10.27 | 3800 | 0.1926 | 0.9257 | 0.9257 |
| 0.2019 | 10.81 | 4000 | 0.1918 | 0.9247 | 0.9247 |
| 0.1989 | 11.35 | 4200 | 0.1949 | 0.9260 | 0.9260 |
| 0.1976 | 11.89 | 4400 | 0.1921 | 0.9252 | 0.9252 |
| 0.1981 | 12.43 | 4600 | 0.1902 | 0.9265 | 0.9265 |
| 0.1984 | 12.97 | 4800 | 0.1902 | 0.9250 | 0.925 |
| 0.1951 | 13.51 | 5000 | 0.1914 | 0.9260 | 0.9260 |
| 0.1977 | 14.05 | 5200 | 0.1885 | 0.9263 | 0.9264 |
| 0.1909 | 14.59 | 5400 | 0.1909 | 0.9268 | 0.9269 |
| 0.1932 | 15.14 | 5600 | 0.1888 | 0.9268 | 0.9269 |
| 0.1894 | 15.68 | 5800 | 0.1894 | 0.9245 | 0.9245 |
| 0.1935 | 16.22 | 6000 | 0.1893 | 0.9270 | 0.9270 |
| 0.1894 | 16.76 | 6200 | 0.1879 | 0.9272 | 0.9272 |
| 0.1914 | 17.3 | 6400 | 0.1878 | 0.9270 | 0.9270 |
| 0.1912 | 17.84 | 6600 | 0.1871 | 0.9257 | 0.9257 |
| 0.1875 | 18.38 | 6800 | 0.1873 | 0.9260 | 0.9260 |
| 0.1917 | 18.92 | 7000 | 0.1868 | 0.9279 | 0.9279 |
| 0.19 | 19.46 | 7200 | 0.1869 | 0.9260 | 0.9260 |
| 0.1865 | 20.0 | 7400 | 0.1863 | 0.9267 | 0.9267 |
| 0.1909 | 20.54 | 7600 | 0.1853 | 0.9274 | 0.9274 |
| 0.1864 | 21.08 | 7800 | 0.1853 | 0.9275 | 0.9275 |
| 0.1875 | 21.62 | 8000 | 0.1854 | 0.9265 | 0.9265 |
| 0.1866 | 22.16 | 8200 | 0.1852 | 0.9277 | 0.9277 |
| 0.1836 | 22.7 | 8400 | 0.1856 | 0.9277 | 0.9277 |
| 0.1888 | 23.24 | 8600 | 0.1851 | 0.9275 | 0.9275 |
| 0.1847 | 23.78 | 8800 | 0.1850 | 0.9269 | 0.9269 |
| 0.1903 | 24.32 | 9000 | 0.1850 | 0.9279 | 0.9279 |
| 0.1844 | 24.86 | 9200 | 0.1849 | 0.9274 | 0.9274 |
| 0.1842 | 25.41 | 9400 | 0.1852 | 0.9280 | 0.9280 |
| 0.1867 | 25.95 | 9600 | 0.1850 | 0.9282 | 0.9282 |
| 0.1848 | 26.49 | 9800 | 0.1848 | 0.9277 | 0.9277 |
| 0.1847 | 27.03 | 10000 | 0.1848 | 0.9279 | 0.9279 |
### Framework versions
- PEFT 0.9.0
- Transformers 4.38.2
- Pytorch 2.2.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2 | {"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_4096_512_27M", "model-index": [{"name": "GUE_prom_prom_300_all-seqsight_4096_512_27M-L1_f", "results": []}]} | mahdibaghbanzadeh/GUE_prom_prom_300_all-seqsight_4096_512_27M-L1_f | null | [
"peft",
"safetensors",
"generated_from_trainer",
"base_model:mahdibaghbanzadeh/seqsight_4096_512_27M",
"region:us"
]
| null | 2024-04-26T00:21:22+00:00 |
text-generation | transformers | # merge
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
## Merge Details
### Merge Method
This model was merged using the SLERP merge method.
### Models Merged
The following models were included in the merge:
* [google/gemma-1.1-2b-it](https://huggingface.co/google/gemma-1.1-2b-it)
* [google/gemma-2b](https://huggingface.co/google/gemma-2b)
* [beomi/gemma-ko-2b](https://huggingface.co/beomi/gemma-ko-2b) | {"license": "gemma", "library_name": "transformers", "tags": ["mergekit", "merge"], "base_model": ["beomi/gemma-ko-2b", "google/gemma-1.1-2b-it", "google/gemma-2b"]} | lemon-mint/gemma-ko-1.1-2b-it | null | [
"transformers",
"safetensors",
"gemma",
"text-generation",
"mergekit",
"merge",
"conversational",
"base_model:beomi/gemma-ko-2b",
"base_model:google/gemma-1.1-2b-it",
"base_model:google/gemma-2b",
"license:gemma",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-26T00:21:36+00:00 |
null | null | {} | Vasanth/orpo-phi3 | null | [
"region:us"
]
| null | 2024-04-26T00:24:07+00:00 |
|
null | peft |
<!-- 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. -->
# GUE_prom_prom_300_all-seqsight_4096_512_27M-L8_f
This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_4096_512_27M](https://huggingface.co/mahdibaghbanzadeh/seqsight_4096_512_27M) on the [mahdibaghbanzadeh/GUE_prom_prom_300_all](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_prom_prom_300_all) dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1978
- F1 Score: 0.9221
- Accuracy: 0.9221
## 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: 0.0005
- train_batch_size: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 10000
### Training results
| Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:|
| 0.336 | 0.54 | 200 | 0.2405 | 0.9049 | 0.9049 |
| 0.2443 | 1.08 | 400 | 0.2229 | 0.9148 | 0.9149 |
| 0.2309 | 1.62 | 600 | 0.2086 | 0.9189 | 0.9189 |
| 0.2149 | 2.16 | 800 | 0.2024 | 0.9236 | 0.9236 |
| 0.2108 | 2.7 | 1000 | 0.1962 | 0.9206 | 0.9206 |
| 0.2042 | 3.24 | 1200 | 0.1978 | 0.9223 | 0.9223 |
| 0.2021 | 3.78 | 1400 | 0.1917 | 0.9221 | 0.9221 |
| 0.201 | 4.32 | 1600 | 0.1921 | 0.9248 | 0.9248 |
| 0.1925 | 4.86 | 1800 | 0.2013 | 0.9230 | 0.9230 |
| 0.1907 | 5.41 | 2000 | 0.1940 | 0.9240 | 0.9240 |
| 0.1877 | 5.95 | 2200 | 0.1855 | 0.9289 | 0.9289 |
| 0.187 | 6.49 | 2400 | 0.1814 | 0.9302 | 0.9302 |
| 0.1847 | 7.03 | 2600 | 0.1867 | 0.9267 | 0.9267 |
| 0.178 | 7.57 | 2800 | 0.1858 | 0.9275 | 0.9275 |
| 0.1824 | 8.11 | 3000 | 0.1864 | 0.9285 | 0.9285 |
| 0.1798 | 8.65 | 3200 | 0.1816 | 0.9296 | 0.9296 |
| 0.172 | 9.19 | 3400 | 0.1882 | 0.9265 | 0.9265 |
| 0.1734 | 9.73 | 3600 | 0.1801 | 0.9294 | 0.9294 |
| 0.1789 | 10.27 | 3800 | 0.1785 | 0.9304 | 0.9304 |
| 0.1748 | 10.81 | 4000 | 0.1793 | 0.9323 | 0.9323 |
| 0.1704 | 11.35 | 4200 | 0.1770 | 0.9323 | 0.9323 |
| 0.168 | 11.89 | 4400 | 0.1797 | 0.9323 | 0.9323 |
| 0.1686 | 12.43 | 4600 | 0.1743 | 0.9336 | 0.9336 |
| 0.1664 | 12.97 | 4800 | 0.1727 | 0.9324 | 0.9324 |
| 0.1642 | 13.51 | 5000 | 0.1791 | 0.9324 | 0.9324 |
| 0.1653 | 14.05 | 5200 | 0.1755 | 0.9304 | 0.9304 |
| 0.1596 | 14.59 | 5400 | 0.1759 | 0.9312 | 0.9313 |
| 0.1606 | 15.14 | 5600 | 0.1744 | 0.9338 | 0.9338 |
| 0.1563 | 15.68 | 5800 | 0.1790 | 0.9307 | 0.9307 |
| 0.1631 | 16.22 | 6000 | 0.1746 | 0.9307 | 0.9307 |
| 0.1565 | 16.76 | 6200 | 0.1747 | 0.9331 | 0.9331 |
| 0.1579 | 17.3 | 6400 | 0.1746 | 0.9343 | 0.9343 |
| 0.1591 | 17.84 | 6600 | 0.1721 | 0.9336 | 0.9336 |
| 0.1522 | 18.38 | 6800 | 0.1761 | 0.9336 | 0.9336 |
| 0.1571 | 18.92 | 7000 | 0.1733 | 0.9345 | 0.9345 |
| 0.1558 | 19.46 | 7200 | 0.1752 | 0.9333 | 0.9333 |
| 0.1512 | 20.0 | 7400 | 0.1746 | 0.9345 | 0.9345 |
| 0.1563 | 20.54 | 7600 | 0.1724 | 0.9340 | 0.9340 |
| 0.1512 | 21.08 | 7800 | 0.1714 | 0.9343 | 0.9343 |
| 0.1486 | 21.62 | 8000 | 0.1745 | 0.9343 | 0.9343 |
| 0.1496 | 22.16 | 8200 | 0.1735 | 0.9340 | 0.9340 |
| 0.1485 | 22.7 | 8400 | 0.1732 | 0.9350 | 0.9350 |
| 0.1511 | 23.24 | 8600 | 0.1735 | 0.9341 | 0.9341 |
| 0.1485 | 23.78 | 8800 | 0.1741 | 0.9343 | 0.9343 |
| 0.1524 | 24.32 | 9000 | 0.1738 | 0.9338 | 0.9338 |
| 0.1468 | 24.86 | 9200 | 0.1729 | 0.9358 | 0.9358 |
| 0.1482 | 25.41 | 9400 | 0.1743 | 0.9346 | 0.9346 |
| 0.1482 | 25.95 | 9600 | 0.1731 | 0.9343 | 0.9343 |
| 0.1472 | 26.49 | 9800 | 0.1729 | 0.9345 | 0.9345 |
| 0.1457 | 27.03 | 10000 | 0.1730 | 0.9343 | 0.9343 |
### Framework versions
- PEFT 0.9.0
- Transformers 4.38.2
- Pytorch 2.2.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2 | {"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_4096_512_27M", "model-index": [{"name": "GUE_prom_prom_300_all-seqsight_4096_512_27M-L8_f", "results": []}]} | mahdibaghbanzadeh/GUE_prom_prom_300_all-seqsight_4096_512_27M-L8_f | null | [
"peft",
"safetensors",
"generated_from_trainer",
"base_model:mahdibaghbanzadeh/seqsight_4096_512_27M",
"region:us"
]
| null | 2024-04-26T00:24:34+00:00 |
null | null | {} | Sam846/Hazbin_Spanish | null | [
"region:us"
]
| null | 2024-04-26T00:24:38+00:00 |
|
null | peft |
<!-- 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. -->
# GUE_prom_prom_300_all-seqsight_4096_512_27M-L32_f
This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_4096_512_27M](https://huggingface.co/mahdibaghbanzadeh/seqsight_4096_512_27M) on the [mahdibaghbanzadeh/GUE_prom_prom_300_all](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_prom_prom_300_all) dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2070
- F1 Score: 0.9236
- Accuracy: 0.9236
## 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: 0.0005
- train_batch_size: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 10000
### Training results
| Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:|
| 0.3111 | 0.54 | 200 | 0.2260 | 0.9121 | 0.9122 |
| 0.2266 | 1.08 | 400 | 0.2086 | 0.9194 | 0.9194 |
| 0.2153 | 1.62 | 600 | 0.2003 | 0.9220 | 0.9220 |
| 0.202 | 2.16 | 800 | 0.1943 | 0.9234 | 0.9235 |
| 0.1989 | 2.7 | 1000 | 0.1850 | 0.9277 | 0.9277 |
| 0.1927 | 3.24 | 1200 | 0.1920 | 0.9238 | 0.9238 |
| 0.1883 | 3.78 | 1400 | 0.1792 | 0.9299 | 0.9299 |
| 0.1866 | 4.32 | 1600 | 0.1842 | 0.9287 | 0.9287 |
| 0.1778 | 4.86 | 1800 | 0.1843 | 0.9287 | 0.9287 |
| 0.1729 | 5.41 | 2000 | 0.1870 | 0.9282 | 0.9282 |
| 0.1718 | 5.95 | 2200 | 0.1780 | 0.9318 | 0.9318 |
| 0.1692 | 6.49 | 2400 | 0.1733 | 0.9321 | 0.9321 |
| 0.1674 | 7.03 | 2600 | 0.1780 | 0.9331 | 0.9331 |
| 0.1588 | 7.57 | 2800 | 0.1773 | 0.9323 | 0.9323 |
| 0.1627 | 8.11 | 3000 | 0.1867 | 0.9260 | 0.9260 |
| 0.1571 | 8.65 | 3200 | 0.1735 | 0.9336 | 0.9336 |
| 0.1501 | 9.19 | 3400 | 0.1852 | 0.9299 | 0.9299 |
| 0.1521 | 9.73 | 3600 | 0.1736 | 0.9316 | 0.9316 |
| 0.1544 | 10.27 | 3800 | 0.1776 | 0.9317 | 0.9318 |
| 0.1517 | 10.81 | 4000 | 0.1773 | 0.9299 | 0.9299 |
| 0.1442 | 11.35 | 4200 | 0.1826 | 0.9272 | 0.9272 |
| 0.1449 | 11.89 | 4400 | 0.1754 | 0.9319 | 0.9319 |
| 0.1438 | 12.43 | 4600 | 0.1752 | 0.9323 | 0.9323 |
| 0.1383 | 12.97 | 4800 | 0.1709 | 0.9345 | 0.9345 |
| 0.1361 | 13.51 | 5000 | 0.1925 | 0.9280 | 0.9280 |
| 0.1364 | 14.05 | 5200 | 0.1788 | 0.9302 | 0.9302 |
| 0.1295 | 14.59 | 5400 | 0.1764 | 0.9351 | 0.9351 |
| 0.1317 | 15.14 | 5600 | 0.1761 | 0.9353 | 0.9353 |
| 0.1278 | 15.68 | 5800 | 0.1838 | 0.9311 | 0.9311 |
| 0.1305 | 16.22 | 6000 | 0.1764 | 0.9356 | 0.9356 |
| 0.1266 | 16.76 | 6200 | 0.1755 | 0.9334 | 0.9334 |
| 0.1262 | 17.3 | 6400 | 0.1762 | 0.9339 | 0.9340 |
| 0.1265 | 17.84 | 6600 | 0.1717 | 0.9353 | 0.9353 |
| 0.1197 | 18.38 | 6800 | 0.1792 | 0.9345 | 0.9345 |
| 0.1227 | 18.92 | 7000 | 0.1753 | 0.9350 | 0.9350 |
| 0.1196 | 19.46 | 7200 | 0.1785 | 0.9353 | 0.9353 |
| 0.1157 | 20.0 | 7400 | 0.1808 | 0.9338 | 0.9338 |
| 0.1201 | 20.54 | 7600 | 0.1810 | 0.9350 | 0.9350 |
| 0.1175 | 21.08 | 7800 | 0.1755 | 0.9360 | 0.9360 |
| 0.1099 | 21.62 | 8000 | 0.1809 | 0.9360 | 0.9360 |
| 0.1137 | 22.16 | 8200 | 0.1809 | 0.9350 | 0.9350 |
| 0.1116 | 22.7 | 8400 | 0.1790 | 0.9348 | 0.9348 |
| 0.1111 | 23.24 | 8600 | 0.1809 | 0.9356 | 0.9356 |
| 0.1122 | 23.78 | 8800 | 0.1831 | 0.9361 | 0.9361 |
| 0.1142 | 24.32 | 9000 | 0.1820 | 0.9336 | 0.9336 |
| 0.1078 | 24.86 | 9200 | 0.1822 | 0.9350 | 0.9350 |
| 0.1091 | 25.41 | 9400 | 0.1845 | 0.9341 | 0.9341 |
| 0.1086 | 25.95 | 9600 | 0.1838 | 0.9334 | 0.9334 |
| 0.1097 | 26.49 | 9800 | 0.1827 | 0.9343 | 0.9343 |
| 0.1059 | 27.03 | 10000 | 0.1825 | 0.9350 | 0.9350 |
### Framework versions
- PEFT 0.9.0
- Transformers 4.38.2
- Pytorch 2.2.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2 | {"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_4096_512_27M", "model-index": [{"name": "GUE_prom_prom_300_all-seqsight_4096_512_27M-L32_f", "results": []}]} | mahdibaghbanzadeh/GUE_prom_prom_300_all-seqsight_4096_512_27M-L32_f | null | [
"peft",
"safetensors",
"generated_from_trainer",
"base_model:mahdibaghbanzadeh/seqsight_4096_512_27M",
"region:us"
]
| null | 2024-04-26T00:24:48+00:00 |
null | null | {} | cinquecentoiso/wizard_book | null | [
"region:us"
]
| null | 2024-04-26T00:25:05+00:00 |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.