pipeline_tag
stringclasses 48
values | library_name
stringclasses 198
values | text
stringlengths 1
900k
| metadata
stringlengths 2
438k
| id
stringlengths 5
122
| last_modified
null | tags
sequencelengths 1
1.84k
| sha
null | created_at
stringlengths 25
25
| arxiv
sequencelengths 0
201
| languages
sequencelengths 0
1.83k
| tags_str
stringlengths 17
9.34k
| text_str
stringlengths 0
389k
| text_lists
sequencelengths 0
722
| processed_texts
sequencelengths 1
723
|
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
sentence-similarity | sentence-transformers |
# mteb-pt/average_pt_nilc_wang2vec_skip_s600
This is an adaptation of pre-trained Portuguese Wang2Vec Word Embeddings to a [sentence-transformers](https://www.SBERT.net) model.
The original pre-trained word embeddings can be found at: [http://nilc.icmc.usp.br/nilc/index.php/repositorio-de-word-embeddings-do-nilc](http://nilc.icmc.usp.br/nilc/index.php/repositorio-de-word-embeddings-do-nilc).
This model maps sentences & paragraphs to a 600 dimensional dense vector space and can be used for tasks like clustering or semantic search.
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('mteb-pt/average_pt_nilc_wang2vec_skip_s600')
embeddings = model.encode(sentences)
print(embeddings)
```
## Evaluation Results
For an automated evaluation of this model, see the *Portuguese MTEB Leaderboard*: [mteb-pt/leaderboard](https://huggingface.co/spaces/mteb-pt/leaderboard)
## Full Model Architecture
```
SentenceTransformer(
(0): WordEmbeddings(
(emb_layer): Embedding(929607, 600)
)
(1): Pooling({'word_embedding_dimension': 600, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
)
```
## Citing & Authors
```bibtex
@inproceedings{hartmann2017portuguese,
title = {Portuguese Word Embeddings: Evaluating on Word Analogies and Natural Language Tasks},
author = {Hartmann, Nathan S and
Fonseca, Erick R and
Shulby, Christopher D and
Treviso, Marcos V and
Rodrigues, J{'{e}}ssica S and
Alu{'{\i}}sio, Sandra Maria},
year = {2017},
publisher = {SBC},
booktitle = {Brazilian Symposium in Information and Human Language Technology - STIL},
url = {https://sol.sbc.org.br/index.php/stil/article/view/4008}
}
``` | {"language": ["pt"], "library_name": "sentence-transformers", "tags": ["sentence-transformers", "feature-extraction", "sentence-similarity"], "pipeline_tag": "sentence-similarity"} | pt-mteb/average_pt_nilc_wang2vec_skip_s600 | null | [
"sentence-transformers",
"feature-extraction",
"sentence-similarity",
"pt",
"endpoints_compatible",
"region:us"
] | null | 2024-04-17T17:38:39+00:00 | [] | [
"pt"
] | TAGS
#sentence-transformers #feature-extraction #sentence-similarity #pt #endpoints_compatible #region-us
|
# mteb-pt/average_pt_nilc_wang2vec_skip_s600
This is an adaptation of pre-trained Portuguese Wang2Vec Word Embeddings to a sentence-transformers model.
The original pre-trained word embeddings can be found at: URL
This model maps sentences & paragraphs to a 600 dimensional dense vector space and can be used for tasks like clustering or semantic search.
## Usage (Sentence-Transformers)
Using this model becomes easy when you have sentence-transformers installed:
Then you can use the model like this:
## Evaluation Results
For an automated evaluation of this model, see the *Portuguese MTEB Leaderboard*: mteb-pt/leaderboard
## Full Model Architecture
## Citing & Authors
| [
"# mteb-pt/average_pt_nilc_wang2vec_skip_s600\n\nThis is an adaptation of pre-trained Portuguese Wang2Vec Word Embeddings to a sentence-transformers model. \n\nThe original pre-trained word embeddings can be found at: URL \n\nThis model maps sentences & paragraphs to a 600 dimensional dense vector space and can be used for tasks like clustering or semantic search.",
"## Usage (Sentence-Transformers)\n\nUsing this model becomes easy when you have sentence-transformers installed:\n\n\n\nThen you can use the model like this:",
"## Evaluation Results\n\nFor an automated evaluation of this model, see the *Portuguese MTEB Leaderboard*: mteb-pt/leaderboard",
"## Full Model Architecture",
"## Citing & Authors"
] | [
"TAGS\n#sentence-transformers #feature-extraction #sentence-similarity #pt #endpoints_compatible #region-us \n",
"# mteb-pt/average_pt_nilc_wang2vec_skip_s600\n\nThis is an adaptation of pre-trained Portuguese Wang2Vec Word Embeddings to a sentence-transformers model. \n\nThe original pre-trained word embeddings can be found at: URL \n\nThis model maps sentences & paragraphs to a 600 dimensional dense vector space and can be used for tasks like clustering or semantic search.",
"## Usage (Sentence-Transformers)\n\nUsing this model becomes easy when you have sentence-transformers installed:\n\n\n\nThen you can use the model like this:",
"## Evaluation Results\n\nFor an automated evaluation of this model, see the *Portuguese MTEB Leaderboard*: mteb-pt/leaderboard",
"## Full Model Architecture",
"## Citing & Authors"
] |
feature-extraction | 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. -->
# finetuned_bge_ver17
This model is a fine-tuned version of [BAAI/bge-m3](https://huggingface.co/BAAI/bge-m3) 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: 3e-05
- train_batch_size: 32
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 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: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 15.0
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2
| {"license": "mit", "tags": ["generated_from_trainer"], "base_model": "BAAI/bge-m3", "model-index": [{"name": "finetuned_bge_ver17", "results": []}]} | comet24082002/finetuned_bge_ver17 | null | [
"transformers",
"tensorboard",
"safetensors",
"xlm-roberta",
"feature-extraction",
"generated_from_trainer",
"base_model:BAAI/bge-m3",
"license:mit",
"endpoints_compatible",
"region:us"
] | null | 2024-04-17T17:40:46+00:00 | [] | [] | TAGS
#transformers #tensorboard #safetensors #xlm-roberta #feature-extraction #generated_from_trainer #base_model-BAAI/bge-m3 #license-mit #endpoints_compatible #region-us
|
# finetuned_bge_ver17
This model is a fine-tuned version of BAAI/bge-m3 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: 3e-05
- train_batch_size: 32
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 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: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 15.0
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2
| [
"# finetuned_bge_ver17\n\nThis model is a fine-tuned version of BAAI/bge-m3 on an unknown dataset.",
"## Model description\n\nMore information needed",
"## Intended uses & limitations\n\nMore information needed",
"## Training and evaluation data\n\nMore information needed",
"## Training procedure",
"### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 3e-05\n- train_batch_size: 32\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 2\n- total_train_batch_size: 64\n- total_eval_batch_size: 16\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- lr_scheduler_warmup_ratio: 0.1\n- num_epochs: 15.0\n- mixed_precision_training: Native AMP",
"### Training results",
"### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.1.2\n- Datasets 2.18.0\n- Tokenizers 0.15.2"
] | [
"TAGS\n#transformers #tensorboard #safetensors #xlm-roberta #feature-extraction #generated_from_trainer #base_model-BAAI/bge-m3 #license-mit #endpoints_compatible #region-us \n",
"# finetuned_bge_ver17\n\nThis model is a fine-tuned version of BAAI/bge-m3 on an unknown dataset.",
"## Model description\n\nMore information needed",
"## Intended uses & limitations\n\nMore information needed",
"## Training and evaluation data\n\nMore information needed",
"## Training procedure",
"### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 3e-05\n- train_batch_size: 32\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 2\n- total_train_batch_size: 64\n- total_eval_batch_size: 16\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- lr_scheduler_warmup_ratio: 0.1\n- num_epochs: 15.0\n- mixed_precision_training: Native AMP",
"### Training results",
"### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.1.2\n- Datasets 2.18.0\n- Tokenizers 0.15.2"
] |
reinforcement-learning | stable-baselines3 |
# **Proximal Policy Optimization** Agent playing **LunarLander-v2**
This is a trained model of a **Proximal Policy Optimization** 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": "Proximal Policy Optimization", "results": [{"task": {"type": "reinforcement-learning", "name": "reinforcement-learning"}, "dataset": {"name": "LunarLander-v2", "type": "LunarLander-v2"}, "metrics": [{"type": "mean_reward", "value": "260.68 +/- 16.65", "name": "mean_reward", "verified": false}]}]}]} | MohamedAtta-AI/ppo-LunarLander-v2 | null | [
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] | null | 2024-04-17T17:41:42+00:00 | [] | [] | TAGS
#stable-baselines3 #LunarLander-v2 #deep-reinforcement-learning #reinforcement-learning #model-index #region-us
|
# Proximal Policy Optimization Agent playing LunarLander-v2
This is a trained model of a Proximal Policy Optimization agent playing LunarLander-v2
using the stable-baselines3 library.
## Usage (with Stable-baselines3)
TODO: Add your code
| [
"# Proximal Policy Optimization Agent playing LunarLander-v2\nThis is a trained model of a Proximal Policy Optimization agent playing LunarLander-v2\nusing the stable-baselines3 library.",
"## Usage (with Stable-baselines3)\nTODO: Add your code"
] | [
"TAGS\n#stable-baselines3 #LunarLander-v2 #deep-reinforcement-learning #reinforcement-learning #model-index #region-us \n",
"# Proximal Policy Optimization Agent playing LunarLander-v2\nThis is a trained model of a Proximal Policy Optimization agent playing LunarLander-v2\nusing the stable-baselines3 library.",
"## Usage (with Stable-baselines3)\nTODO: Add your code"
] |
sentence-similarity | sentence-transformers |
# phoenixSP/embedding-finetuned-model-v1
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 384 dimensional dense vector space and can be used for tasks like clustering or semantic search.
<!--- Describe your model here -->
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('phoenixSP/embedding-finetuned-model-v1')
embeddings = model.encode(sentences)
print(embeddings)
```
## Evaluation Results
<!--- Describe how your model was evaluated -->
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=phoenixSP/embedding-finetuned-model-v1)
## Training
The model was trained with the parameters:
**DataLoader**:
`torch.utils.data.dataloader.DataLoader` of length 238 with parameters:
```
{'batch_size': 10, 'sampler': 'torch.utils.data.sampler.SequentialSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
```
**Loss**:
`sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss` with parameters:
```
{'scale': 20.0, 'similarity_fct': 'cos_sim'}
```
Parameters of the fit()-Method:
```
{
"epochs": 25,
"evaluation_steps": 50,
"evaluator": "sentence_transformers.evaluation.InformationRetrievalEvaluator.InformationRetrievalEvaluator",
"max_grad_norm": 1,
"optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
"optimizer_params": {
"lr": 2e-05
},
"scheduler": "WarmupLinear",
"steps_per_epoch": null,
"warmup_steps": 595,
"weight_decay": 0.01
}
```
## Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 512, 'do_lower_case': True}) with Transformer model: BertModel
(1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
(2): Normalize()
)
```
## Citing & Authors
<!--- Describe where people can find more information --> | {"library_name": "sentence-transformers", "tags": ["sentence-transformers", "feature-extraction", "sentence-similarity"], "pipeline_tag": "sentence-similarity"} | phoenixSP/embedding-finetuned-model-v1 | null | [
"sentence-transformers",
"safetensors",
"bert",
"feature-extraction",
"sentence-similarity",
"endpoints_compatible",
"region:us"
] | null | 2024-04-17T17:42:40+00:00 | [] | [] | TAGS
#sentence-transformers #safetensors #bert #feature-extraction #sentence-similarity #endpoints_compatible #region-us
|
# phoenixSP/embedding-finetuned-model-v1
This is a sentence-transformers model: It maps sentences & paragraphs to a 384 dimensional dense vector space and can be used for tasks like clustering or semantic search.
## Usage (Sentence-Transformers)
Using this model becomes easy when you have sentence-transformers installed:
Then you can use the model like this:
## Evaluation Results
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: URL
## Training
The model was trained with the parameters:
DataLoader:
'URL.dataloader.DataLoader' of length 238 with parameters:
Loss:
'sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss' with parameters:
Parameters of the fit()-Method:
## Full Model Architecture
## Citing & Authors
| [
"# phoenixSP/embedding-finetuned-model-v1\n\nThis is a sentence-transformers model: It maps sentences & paragraphs to a 384 dimensional dense vector space and can be used for tasks like clustering or semantic search.",
"## Usage (Sentence-Transformers)\n\nUsing this model becomes easy when you have sentence-transformers installed:\n\n\n\nThen you can use the model like this:",
"## Evaluation Results\n\n\n\nFor an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: URL",
"## Training\nThe model was trained with the parameters:\n\nDataLoader:\n\n'URL.dataloader.DataLoader' of length 238 with parameters:\n\n\nLoss:\n\n'sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss' with parameters:\n \n\nParameters of the fit()-Method:",
"## Full Model Architecture",
"## Citing & Authors"
] | [
"TAGS\n#sentence-transformers #safetensors #bert #feature-extraction #sentence-similarity #endpoints_compatible #region-us \n",
"# phoenixSP/embedding-finetuned-model-v1\n\nThis is a sentence-transformers model: It maps sentences & paragraphs to a 384 dimensional dense vector space and can be used for tasks like clustering or semantic search.",
"## Usage (Sentence-Transformers)\n\nUsing this model becomes easy when you have sentence-transformers installed:\n\n\n\nThen you can use the model like this:",
"## Evaluation Results\n\n\n\nFor an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: URL",
"## Training\nThe model was trained with the parameters:\n\nDataLoader:\n\n'URL.dataloader.DataLoader' of length 238 with parameters:\n\n\nLoss:\n\n'sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss' with parameters:\n \n\nParameters of the fit()-Method:",
"## Full Model Architecture",
"## Citing & Authors"
] |
sentence-similarity | sentence-transformers |
# mteb-pt/average_pt_nilc_word2vec_skip_s600
This is an adaptation of pre-trained Portuguese Word2Vec Word Embeddings to a [sentence-transformers](https://www.SBERT.net) model.
The original pre-trained word embeddings can be found at: [http://nilc.icmc.usp.br/nilc/index.php/repositorio-de-word-embeddings-do-nilc](http://nilc.icmc.usp.br/nilc/index.php/repositorio-de-word-embeddings-do-nilc).
This model maps sentences & paragraphs to a 600 dimensional dense vector space and can be used for tasks like clustering or semantic search.
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('mteb-pt/average_pt_nilc_word2vec_skip_s600')
embeddings = model.encode(sentences)
print(embeddings)
```
## Evaluation Results
For an automated evaluation of this model, see the *Portuguese MTEB Leaderboard*: [mteb-pt/leaderboard](https://huggingface.co/spaces/mteb-pt/leaderboard)
## Full Model Architecture
```
SentenceTransformer(
(0): WordEmbeddings(
(emb_layer): Embedding(929607, 600)
)
(1): Pooling({'word_embedding_dimension': 600, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
)
```
## Citing & Authors
```bibtex
@inproceedings{hartmann2017portuguese,
title = {Portuguese Word Embeddings: Evaluating on Word Analogies and Natural Language Tasks},
author = {Hartmann, Nathan S and
Fonseca, Erick R and
Shulby, Christopher D and
Treviso, Marcos V and
Rodrigues, J{'{e}}ssica S and
Alu{'{\i}}sio, Sandra Maria},
year = {2017},
publisher = {SBC},
booktitle = {Brazilian Symposium in Information and Human Language Technology - STIL},
url = {https://sol.sbc.org.br/index.php/stil/article/view/4008}
}
``` | {"language": ["pt"], "library_name": "sentence-transformers", "tags": ["sentence-transformers", "feature-extraction", "sentence-similarity"], "pipeline_tag": "sentence-similarity"} | pt-mteb/average_pt_nilc_word2vec_skip_s600 | null | [
"sentence-transformers",
"feature-extraction",
"sentence-similarity",
"pt",
"endpoints_compatible",
"region:us"
] | null | 2024-04-17T17:43:55+00:00 | [] | [
"pt"
] | TAGS
#sentence-transformers #feature-extraction #sentence-similarity #pt #endpoints_compatible #region-us
|
# mteb-pt/average_pt_nilc_word2vec_skip_s600
This is an adaptation of pre-trained Portuguese Word2Vec Word Embeddings to a sentence-transformers model.
The original pre-trained word embeddings can be found at: URL
This model maps sentences & paragraphs to a 600 dimensional dense vector space and can be used for tasks like clustering or semantic search.
## Usage (Sentence-Transformers)
Using this model becomes easy when you have sentence-transformers installed:
Then you can use the model like this:
## Evaluation Results
For an automated evaluation of this model, see the *Portuguese MTEB Leaderboard*: mteb-pt/leaderboard
## Full Model Architecture
## Citing & Authors
| [
"# mteb-pt/average_pt_nilc_word2vec_skip_s600\n\nThis is an adaptation of pre-trained Portuguese Word2Vec Word Embeddings to a sentence-transformers model. \n\nThe original pre-trained word embeddings can be found at: URL \n\nThis model maps sentences & paragraphs to a 600 dimensional dense vector space and can be used for tasks like clustering or semantic search.",
"## Usage (Sentence-Transformers)\n\nUsing this model becomes easy when you have sentence-transformers installed:\n\n\n\nThen you can use the model like this:",
"## Evaluation Results\n\nFor an automated evaluation of this model, see the *Portuguese MTEB Leaderboard*: mteb-pt/leaderboard",
"## Full Model Architecture",
"## Citing & Authors"
] | [
"TAGS\n#sentence-transformers #feature-extraction #sentence-similarity #pt #endpoints_compatible #region-us \n",
"# mteb-pt/average_pt_nilc_word2vec_skip_s600\n\nThis is an adaptation of pre-trained Portuguese Word2Vec Word Embeddings to a sentence-transformers model. \n\nThe original pre-trained word embeddings can be found at: URL \n\nThis model maps sentences & paragraphs to a 600 dimensional dense vector space and can be used for tasks like clustering or semantic search.",
"## Usage (Sentence-Transformers)\n\nUsing this model becomes easy when you have sentence-transformers installed:\n\n\n\nThen you can use the model like this:",
"## Evaluation Results\n\nFor an automated evaluation of this model, see the *Portuguese MTEB Leaderboard*: mteb-pt/leaderboard",
"## Full Model Architecture",
"## Citing & Authors"
] |
text-generation | transformers | # nbeerbower/MaidFlameSoup-7B AWQ
- Model creator: [nbeerbower](https://huggingface.co/nbeerbower)
- Original model: [MaidFlameSoup-7B](https://huggingface.co/nbeerbower/MaidFlameSoup-7B)
## Model Summary
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
## 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/MaidFlameSoup-7B-AWQ"
system_message = "You are MaidFlameSoup, incarnated as a powerful AI."
# 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
## Prompt template: ChatML
```plaintext
<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
```
| {"license": "apache-2.0", "library_name": "transformers", "tags": ["mergekit", "merge", "finetuned", "quantized", "4-bit", "AWQ", "transformers", "pytorch", "mistral", "text-generation"], "base_model": ["nbeerbower/flammen13-mistral-7B", "nbeerbower/Flammen-Kunoichi-7B", "nbeerbower/flammen10-mistral-7B", "nbeerbower/flammen11X-mistral-7B", "nbeerbower/Maidphin-Kunoichi-7B"], "pipeline_tag": "text-generation", "inference": false, "prompt_template": "<|im_start|>system\n{system_message}<|im_end|>\n<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant\n", "quantized_by": "Suparious"} | solidrust/MaidFlameSoup-7B-AWQ | null | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"mergekit",
"merge",
"finetuned",
"quantized",
"4-bit",
"AWQ",
"pytorch",
"base_model:nbeerbower/flammen13-mistral-7B",
"base_model:nbeerbower/Flammen-Kunoichi-7B",
"base_model:nbeerbower/flammen10-mistral-7B",
"base_model:nbeerbower/flammen11X-mistral-7B",
"base_model:nbeerbower/Maidphin-Kunoichi-7B",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-04-17T17:45:33+00:00 | [] | [] | TAGS
#transformers #safetensors #mistral #text-generation #mergekit #merge #finetuned #quantized #4-bit #AWQ #pytorch #base_model-nbeerbower/flammen13-mistral-7B #base_model-nbeerbower/Flammen-Kunoichi-7B #base_model-nbeerbower/flammen10-mistral-7B #base_model-nbeerbower/flammen11X-mistral-7B #base_model-nbeerbower/Maidphin-Kunoichi-7B #license-apache-2.0 #autotrain_compatible #text-generation-inference #region-us
| # nbeerbower/MaidFlameSoup-7B AWQ
- Model creator: nbeerbower
- Original model: MaidFlameSoup-7B
## Model Summary
This is a merge of pre-trained language models created using mergekit.
## How to use
### Install the necessary packages
### Example Python code
### 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 - using Loader: AutoAWQ
- vLLM - version 0.2.2 or later for support for all model types.
- Hugging Face Text Generation Inference (TGI)
- Transformers version 4.35.0 and later, from any code or client that supports Transformers
- AutoAWQ - for use from Python code
## Prompt template: ChatML
| [
"# nbeerbower/MaidFlameSoup-7B AWQ\n\n- Model creator: nbeerbower\n- Original model: MaidFlameSoup-7B",
"## Model Summary\n\nThis is a merge of pre-trained language models created using mergekit.",
"## How to use",
"### Install the necessary packages",
"### Example Python code",
"### About AWQ\n\nAWQ 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.\n\nAWQ models are currently supported on Linux and Windows, with NVidia GPUs only. macOS users: please use GGUF models instead.\n\nIt is supported by:\n\n- Text Generation Webui - using Loader: AutoAWQ\n- vLLM - version 0.2.2 or later for support for all model types.\n- Hugging Face Text Generation Inference (TGI)\n- Transformers version 4.35.0 and later, from any code or client that supports Transformers\n- AutoAWQ - for use from Python code",
"## Prompt template: ChatML"
] | [
"TAGS\n#transformers #safetensors #mistral #text-generation #mergekit #merge #finetuned #quantized #4-bit #AWQ #pytorch #base_model-nbeerbower/flammen13-mistral-7B #base_model-nbeerbower/Flammen-Kunoichi-7B #base_model-nbeerbower/flammen10-mistral-7B #base_model-nbeerbower/flammen11X-mistral-7B #base_model-nbeerbower/Maidphin-Kunoichi-7B #license-apache-2.0 #autotrain_compatible #text-generation-inference #region-us \n",
"# nbeerbower/MaidFlameSoup-7B AWQ\n\n- Model creator: nbeerbower\n- Original model: MaidFlameSoup-7B",
"## Model Summary\n\nThis is a merge of pre-trained language models created using mergekit.",
"## How to use",
"### Install the necessary packages",
"### Example Python code",
"### About AWQ\n\nAWQ 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.\n\nAWQ models are currently supported on Linux and Windows, with NVidia GPUs only. macOS users: please use GGUF models instead.\n\nIt is supported by:\n\n- Text Generation Webui - using Loader: AutoAWQ\n- vLLM - version 0.2.2 or later for support for all model types.\n- Hugging Face Text Generation Inference (TGI)\n- Transformers version 4.35.0 and later, from any code or client that supports Transformers\n- AutoAWQ - for use from Python code",
"## Prompt template: ChatML"
] |
null | transformers | ## About
<!-- ### quantize_version: 1 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: -->
<!-- ### vocab_type: -->
static quants of https://huggingface.co/icefog72/WizardIceLemonTeaRP-32k
<!-- provided-files -->
weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
## 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/WizardIceLemonTeaRP-32k-GGUF/resolve/main/WizardIceLemonTeaRP-32k.Q2_K.gguf) | Q2_K | 2.8 | |
| [GGUF](https://huggingface.co/mradermacher/WizardIceLemonTeaRP-32k-GGUF/resolve/main/WizardIceLemonTeaRP-32k.IQ3_XS.gguf) | IQ3_XS | 3.1 | |
| [GGUF](https://huggingface.co/mradermacher/WizardIceLemonTeaRP-32k-GGUF/resolve/main/WizardIceLemonTeaRP-32k.Q3_K_S.gguf) | Q3_K_S | 3.3 | |
| [GGUF](https://huggingface.co/mradermacher/WizardIceLemonTeaRP-32k-GGUF/resolve/main/WizardIceLemonTeaRP-32k.IQ3_S.gguf) | IQ3_S | 3.3 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/WizardIceLemonTeaRP-32k-GGUF/resolve/main/WizardIceLemonTeaRP-32k.IQ3_M.gguf) | IQ3_M | 3.4 | |
| [GGUF](https://huggingface.co/mradermacher/WizardIceLemonTeaRP-32k-GGUF/resolve/main/WizardIceLemonTeaRP-32k.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/WizardIceLemonTeaRP-32k-GGUF/resolve/main/WizardIceLemonTeaRP-32k.Q3_K_L.gguf) | Q3_K_L | 3.9 | |
| [GGUF](https://huggingface.co/mradermacher/WizardIceLemonTeaRP-32k-GGUF/resolve/main/WizardIceLemonTeaRP-32k.IQ4_XS.gguf) | IQ4_XS | 4.0 | |
| [GGUF](https://huggingface.co/mradermacher/WizardIceLemonTeaRP-32k-GGUF/resolve/main/WizardIceLemonTeaRP-32k.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/WizardIceLemonTeaRP-32k-GGUF/resolve/main/WizardIceLemonTeaRP-32k.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/WizardIceLemonTeaRP-32k-GGUF/resolve/main/WizardIceLemonTeaRP-32k.Q5_K_S.gguf) | Q5_K_S | 5.1 | |
| [GGUF](https://huggingface.co/mradermacher/WizardIceLemonTeaRP-32k-GGUF/resolve/main/WizardIceLemonTeaRP-32k.Q5_K_M.gguf) | Q5_K_M | 5.2 | |
| [GGUF](https://huggingface.co/mradermacher/WizardIceLemonTeaRP-32k-GGUF/resolve/main/WizardIceLemonTeaRP-32k.Q6_K.gguf) | Q6_K | 6.0 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/WizardIceLemonTeaRP-32k-GGUF/resolve/main/WizardIceLemonTeaRP-32k.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality |
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"], "library_name": "transformers", "base_model": "icefog72/WizardIceLemonTeaRP-32k", "quantized_by": "mradermacher"} | mradermacher/WizardIceLemonTeaRP-32k-GGUF | null | [
"transformers",
"gguf",
"en",
"base_model:icefog72/WizardIceLemonTeaRP-32k",
"endpoints_compatible",
"region:us"
] | null | 2024-04-17T17:45:36+00:00 | [] | [
"en"
] | TAGS
#transformers #gguf #en #base_model-icefog72/WizardIceLemonTeaRP-32k #endpoints_compatible #region-us
| About
-----
static quants of URL
weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
Usage
-----
If you are unsure how to use GGUF files, refer to one of TheBloke's
READMEs 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)
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
!URL
And here are Artefact2's thoughts on the matter:
URL
FAQ / Model Request
-------------------
See URL for some answers to
questions you might have and/or if you want some other model quantized.
Thanks
------
I thank my company, nethype GmbH, for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
| [] | [
"TAGS\n#transformers #gguf #en #base_model-icefog72/WizardIceLemonTeaRP-32k #endpoints_compatible #region-us \n"
] |
image-classification | transformers |
# 10fishmodel
Autogenerated by HuggingPics🤗🖼️
Create your own image classifier for **anything** by running [the demo on Google Colab](https://colab.research.google.com/github/nateraw/huggingpics/blob/main/HuggingPics.ipynb).
Report any issues with the demo at the [github repo](https://github.com/nateraw/huggingpics).
## Example Images
#### Anglerfish
#### Arapaima Gigas
#### Catfish
#### Crocodiles
#### Dolphin
#### Koi fish
#### Shark
#### Stingray
#### Swordfish
#### Whale
 | {"tags": ["image-classification", "pytorch", "huggingpics"], "metrics": ["accuracy"]} | NeroZ02/10fishmodel | null | [
"transformers",
"tensorboard",
"safetensors",
"vit",
"image-classification",
"pytorch",
"huggingpics",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-04-17T17:45:58+00:00 | [] | [] | TAGS
#transformers #tensorboard #safetensors #vit #image-classification #pytorch #huggingpics #model-index #autotrain_compatible #endpoints_compatible #region-us
|
# 10fishmodel
Autogenerated by HuggingPics️
Create your own image classifier for anything by running the demo on Google Colab.
Report any issues with the demo at the github repo.
## Example Images
#### Anglerfish
!Anglerfish
#### Arapaima Gigas
!Arapaima Gigas
#### Catfish
!Catfish
#### Crocodiles
!Crocodiles
#### Dolphin
!Dolphin
#### Koi fish
!Koi fish
#### Shark
!Shark
#### Stingray
!Stingray
#### Swordfish
!Swordfish
#### Whale
!Whale | [
"# 10fishmodel\n\n\nAutogenerated by HuggingPics️\n\nCreate your own image classifier for anything by running the demo on Google Colab.\n\nReport any issues with the demo at the github repo.",
"## Example Images",
"#### Anglerfish\n\n!Anglerfish",
"#### Arapaima Gigas\n\n!Arapaima Gigas",
"#### Catfish\n\n!Catfish",
"#### Crocodiles\n\n!Crocodiles",
"#### Dolphin\n\n!Dolphin",
"#### Koi fish\n\n!Koi fish",
"#### Shark\n\n!Shark",
"#### Stingray\n\n!Stingray",
"#### Swordfish\n\n!Swordfish",
"#### Whale\n\n!Whale"
] | [
"TAGS\n#transformers #tensorboard #safetensors #vit #image-classification #pytorch #huggingpics #model-index #autotrain_compatible #endpoints_compatible #region-us \n",
"# 10fishmodel\n\n\nAutogenerated by HuggingPics️\n\nCreate your own image classifier for anything by running the demo on Google Colab.\n\nReport any issues with the demo at the github repo.",
"## Example Images",
"#### Anglerfish\n\n!Anglerfish",
"#### Arapaima Gigas\n\n!Arapaima Gigas",
"#### Catfish\n\n!Catfish",
"#### Crocodiles\n\n!Crocodiles",
"#### Dolphin\n\n!Dolphin",
"#### Koi fish\n\n!Koi fish",
"#### Shark\n\n!Shark",
"#### Stingray\n\n!Stingray",
"#### Swordfish\n\n!Swordfish",
"#### Whale\n\n!Whale"
] |
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. -->
# multilingual-e5-large-guardrail-toxicity-classifier-training_templated
This model is a fine-tuned version of [intfloat/multilingual-e5-large](https://huggingface.co/intfloat/multilingual-e5-large) on an unknown dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-06
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
### Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2+cu121
- Datasets 2.17.0
- Tokenizers 0.15.2
| {"license": "mit", "tags": ["generated_from_trainer"], "base_model": "intfloat/multilingual-e5-large", "model-index": [{"name": "multilingual-e5-large-guardrail-toxicity-classifier-training_templated", "results": []}]} | tosh97/multilingual-e5-large-guardrail-toxicity-classifier-training_templated | null | [
"transformers",
"safetensors",
"xlm-roberta",
"text-classification",
"generated_from_trainer",
"base_model:intfloat/multilingual-e5-large",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-04-17T17:47:11+00:00 | [] | [] | TAGS
#transformers #safetensors #xlm-roberta #text-classification #generated_from_trainer #base_model-intfloat/multilingual-e5-large #license-mit #autotrain_compatible #endpoints_compatible #region-us
|
# multilingual-e5-large-guardrail-toxicity-classifier-training_templated
This model is a fine-tuned version of intfloat/multilingual-e5-large on an unknown dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-06
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
### Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2+cu121
- Datasets 2.17.0
- Tokenizers 0.15.2
| [
"# multilingual-e5-large-guardrail-toxicity-classifier-training_templated\n\nThis model is a fine-tuned version of intfloat/multilingual-e5-large on an unknown dataset.",
"## Model description\n\nMore information needed",
"## Intended uses & limitations\n\nMore information needed",
"## Training and evaluation data\n\nMore information needed",
"## Training procedure",
"### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 1e-06\n- train_batch_size: 16\n- eval_batch_size: 16\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 10",
"### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.1.2+cu121\n- Datasets 2.17.0\n- Tokenizers 0.15.2"
] | [
"TAGS\n#transformers #safetensors #xlm-roberta #text-classification #generated_from_trainer #base_model-intfloat/multilingual-e5-large #license-mit #autotrain_compatible #endpoints_compatible #region-us \n",
"# multilingual-e5-large-guardrail-toxicity-classifier-training_templated\n\nThis model is a fine-tuned version of intfloat/multilingual-e5-large on an unknown dataset.",
"## Model description\n\nMore information needed",
"## Intended uses & limitations\n\nMore information needed",
"## Training and evaluation data\n\nMore information needed",
"## Training procedure",
"### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 1e-06\n- train_batch_size: 16\n- eval_batch_size: 16\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 10",
"### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.1.2+cu121\n- Datasets 2.17.0\n- Tokenizers 0.15.2"
] |
null | transformers | ## About
<!-- ### quantize_version: 1 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: -->
<!-- ### vocab_type: -->
static quants of https://huggingface.co/allenai/tulu-2-dpo-70b
<!-- provided-files -->
weighted/imatrix quants are available at https://huggingface.co/mradermacher/tulu-2-dpo-70b-i1-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/tulu-2-dpo-70b-GGUF/resolve/main/tulu-2-dpo-70b.Q2_K.gguf) | Q2_K | 25.6 | |
| [GGUF](https://huggingface.co/mradermacher/tulu-2-dpo-70b-GGUF/resolve/main/tulu-2-dpo-70b.IQ3_XS.gguf) | IQ3_XS | 28.4 | |
| [GGUF](https://huggingface.co/mradermacher/tulu-2-dpo-70b-GGUF/resolve/main/tulu-2-dpo-70b.IQ3_S.gguf) | IQ3_S | 30.0 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/tulu-2-dpo-70b-GGUF/resolve/main/tulu-2-dpo-70b.Q3_K_S.gguf) | Q3_K_S | 30.0 | |
| [GGUF](https://huggingface.co/mradermacher/tulu-2-dpo-70b-GGUF/resolve/main/tulu-2-dpo-70b.IQ3_M.gguf) | IQ3_M | 31.0 | |
| [GGUF](https://huggingface.co/mradermacher/tulu-2-dpo-70b-GGUF/resolve/main/tulu-2-dpo-70b.Q3_K_M.gguf) | Q3_K_M | 33.4 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/tulu-2-dpo-70b-GGUF/resolve/main/tulu-2-dpo-70b.Q3_K_L.gguf) | Q3_K_L | 36.2 | |
| [GGUF](https://huggingface.co/mradermacher/tulu-2-dpo-70b-GGUF/resolve/main/tulu-2-dpo-70b.IQ4_XS.gguf) | IQ4_XS | 37.3 | |
| [GGUF](https://huggingface.co/mradermacher/tulu-2-dpo-70b-GGUF/resolve/main/tulu-2-dpo-70b.Q4_K_S.gguf) | Q4_K_S | 39.3 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/tulu-2-dpo-70b-GGUF/resolve/main/tulu-2-dpo-70b.Q4_K_M.gguf) | Q4_K_M | 41.5 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/tulu-2-dpo-70b-GGUF/resolve/main/tulu-2-dpo-70b.Q5_K_S.gguf) | Q5_K_S | 47.6 | |
| [GGUF](https://huggingface.co/mradermacher/tulu-2-dpo-70b-GGUF/resolve/main/tulu-2-dpo-70b.Q5_K_M.gguf) | Q5_K_M | 48.9 | |
| [PART 1](https://huggingface.co/mradermacher/tulu-2-dpo-70b-GGUF/resolve/main/tulu-2-dpo-70b.Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/tulu-2-dpo-70b-GGUF/resolve/main/tulu-2-dpo-70b.Q6_K.gguf.part2of2) | Q6_K | 56.7 | very good quality |
| [PART 1](https://huggingface.co/mradermacher/tulu-2-dpo-70b-GGUF/resolve/main/tulu-2-dpo-70b.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/tulu-2-dpo-70b-GGUF/resolve/main/tulu-2-dpo-70b.Q8_0.gguf.part2of2) | Q8_0 | 73.4 | fast, best quality |
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": "other", "library_name": "transformers", "datasets": ["HuggingFaceH4/ultrafeedback_binarized", "allenai/tulu-v2-sft-mixture"], "base_model": "allenai/tulu-2-dpo-70b", "license_link": "https://allenai.org/impact-license", "license_name": "ai2-impact-license-low-risk", "quantized_by": "mradermacher"} | mradermacher/tulu-2-dpo-70b-GGUF | null | [
"transformers",
"gguf",
"en",
"dataset:HuggingFaceH4/ultrafeedback_binarized",
"dataset:allenai/tulu-v2-sft-mixture",
"base_model:allenai/tulu-2-dpo-70b",
"license:other",
"endpoints_compatible",
"region:us"
] | null | 2024-04-17T17:50:45+00:00 | [] | [
"en"
] | TAGS
#transformers #gguf #en #dataset-HuggingFaceH4/ultrafeedback_binarized #dataset-allenai/tulu-v2-sft-mixture #base_model-allenai/tulu-2-dpo-70b #license-other #endpoints_compatible #region-us
| About
-----
static quants of URL
weighted/imatrix quants are available at URL
Usage
-----
If you are unsure how to use GGUF files, refer to one of TheBloke's
READMEs 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)
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
!URL
And here are Artefact2's thoughts on the matter:
URL
FAQ / Model Request
-------------------
See URL for some answers to
questions you might have and/or if you want some other model quantized.
Thanks
------
I thank my company, nethype GmbH, for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
| [] | [
"TAGS\n#transformers #gguf #en #dataset-HuggingFaceH4/ultrafeedback_binarized #dataset-allenai/tulu-v2-sft-mixture #base_model-allenai/tulu-2-dpo-70b #license-other #endpoints_compatible #region-us \n"
] |
null | transformers | ## About
<!-- ### quantize_version: 1 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: -->
<!-- ### vocab_type: -->
static quants of https://huggingface.co/Usaid/ContextClassy-Merged-V1
<!-- provided-files -->
weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
## 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/ContextClassy-Merged-V1-GGUF/resolve/main/ContextClassy-Merged-V1.Q2_K.gguf) | Q2_K | 2.8 | |
| [GGUF](https://huggingface.co/mradermacher/ContextClassy-Merged-V1-GGUF/resolve/main/ContextClassy-Merged-V1.IQ3_XS.gguf) | IQ3_XS | 3.1 | |
| [GGUF](https://huggingface.co/mradermacher/ContextClassy-Merged-V1-GGUF/resolve/main/ContextClassy-Merged-V1.Q3_K_S.gguf) | Q3_K_S | 3.3 | |
| [GGUF](https://huggingface.co/mradermacher/ContextClassy-Merged-V1-GGUF/resolve/main/ContextClassy-Merged-V1.IQ3_S.gguf) | IQ3_S | 3.3 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/ContextClassy-Merged-V1-GGUF/resolve/main/ContextClassy-Merged-V1.IQ3_M.gguf) | IQ3_M | 3.4 | |
| [GGUF](https://huggingface.co/mradermacher/ContextClassy-Merged-V1-GGUF/resolve/main/ContextClassy-Merged-V1.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/ContextClassy-Merged-V1-GGUF/resolve/main/ContextClassy-Merged-V1.Q3_K_L.gguf) | Q3_K_L | 3.9 | |
| [GGUF](https://huggingface.co/mradermacher/ContextClassy-Merged-V1-GGUF/resolve/main/ContextClassy-Merged-V1.IQ4_XS.gguf) | IQ4_XS | 4.0 | |
| [GGUF](https://huggingface.co/mradermacher/ContextClassy-Merged-V1-GGUF/resolve/main/ContextClassy-Merged-V1.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/ContextClassy-Merged-V1-GGUF/resolve/main/ContextClassy-Merged-V1.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/ContextClassy-Merged-V1-GGUF/resolve/main/ContextClassy-Merged-V1.Q5_K_S.gguf) | Q5_K_S | 5.1 | |
| [GGUF](https://huggingface.co/mradermacher/ContextClassy-Merged-V1-GGUF/resolve/main/ContextClassy-Merged-V1.Q5_K_M.gguf) | Q5_K_M | 5.2 | |
| [GGUF](https://huggingface.co/mradermacher/ContextClassy-Merged-V1-GGUF/resolve/main/ContextClassy-Merged-V1.Q6_K.gguf) | Q6_K | 6.0 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/ContextClassy-Merged-V1-GGUF/resolve/main/ContextClassy-Merged-V1.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality |
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"], "library_name": "transformers", "tags": [], "base_model": "Usaid/ContextClassy-Merged-V1", "quantized_by": "mradermacher"} | mradermacher/ContextClassy-Merged-V1-GGUF | null | [
"transformers",
"gguf",
"en",
"base_model:Usaid/ContextClassy-Merged-V1",
"endpoints_compatible",
"region:us"
] | null | 2024-04-17T17:51:32+00:00 | [] | [
"en"
] | TAGS
#transformers #gguf #en #base_model-Usaid/ContextClassy-Merged-V1 #endpoints_compatible #region-us
| About
-----
static quants of URL
weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
Usage
-----
If you are unsure how to use GGUF files, refer to one of TheBloke's
READMEs 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)
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
!URL
And here are Artefact2's thoughts on the matter:
URL
FAQ / Model Request
-------------------
See URL for some answers to
questions you might have and/or if you want some other model quantized.
Thanks
------
I thank my company, nethype GmbH, for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
| [] | [
"TAGS\n#transformers #gguf #en #base_model-Usaid/ContextClassy-Merged-V1 #endpoints_compatible #region-us \n"
] |
text2text-generation | transformers |
# FLAN-T5 Base Text to SQL Model
This model was fine-tuned on [Google's FLAN-T5 base](https://huggingface.co/google/flan-t5-base) using [SParC](https://yale-lily.github.io/sparc), [Spider](https://yale-lily.github.io/spider), and [CoSQL](https://yale-lily.github.io/cosql) datasets.
Purpose of this model is to create SQL queries from natural-language text.
In order to achieve accuracte results, database schema was incorporated to the prompt during training.
GitHub repository can be found [here](https://github.com/alpecevit/text2sql).
## Requirements
```bash
pip install transformers==4.38.2
pip install torch==2.2.2
```
## Usage
Please exercise caution when formatting the input.
```python
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
tokenizer = AutoTokenizer.from_pretrained("alpecevit/flan-t5-base-text2sql")
model = AutoModelForSeq2SeqLM.from_pretrained("alpecevit/flan-t5-base-text2sql")
input_text = """
transform question and schema to SQL query. question: Who are the top 5 most paid employess by first name, last name, and salary ? schema: employee(salary, bdate, dno, ssn, fname, sex, superssn, address, minit, lname), department(dnumber, mgrstartdate, dname, mgrssn), dept_locations(dnumber, dlocation), project(pnumber, dnum, pname, plocation), works_on(pno, hours, essn), dependent(bdate, essn, dependent_name, sex, relationship).
"""
token_input = tokenizer(input_text, return_tensors="pt").input_ids
output = model.generate(token_input, max_new_tokens=128)
query = tokenizer.decode(output[0], skip_special_tokens=True)
print("Predicted Query:", query)
```
*Output:*
```
SELECT fname, lname, salary FROM employee ORDER BY salary DESC LIMIT 5
```
## Evaluation
The fine-tuned model was evaluated using the combination of test splits of the above datasets. [ROUGE](https://huggingface.co/spaces/evaluate-metric/rouge) metrics were utilized for the assessment, and the results are outlined below.
```
{'rouge1': 0.8740305983060861, 'rouge2': 0.7763397400315798, 'rougeL': 0.8449832130213266, 'rougeLsum': 0.8447120646910007}
``` | {"library_name": "transformers"} | alpecevit/flan-t5-base-text2sql | null | [
"transformers",
"safetensors",
"t5",
"text2text-generation",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-04-17T17:52:14+00:00 | [] | [] | TAGS
#transformers #safetensors #t5 #text2text-generation #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us
|
# FLAN-T5 Base Text to SQL Model
This model was fine-tuned on Google's FLAN-T5 base using SParC, Spider, and CoSQL datasets.
Purpose of this model is to create SQL queries from natural-language text.
In order to achieve accuracte results, database schema was incorporated to the prompt during training.
GitHub repository can be found here.
## Requirements
## Usage
Please exercise caution when formatting the input.
*Output:*
## Evaluation
The fine-tuned model was evaluated using the combination of test splits of the above datasets. ROUGE metrics were utilized for the assessment, and the results are outlined below.
| [
"# FLAN-T5 Base Text to SQL Model\n\nThis model was fine-tuned on Google's FLAN-T5 base using SParC, Spider, and CoSQL datasets.\n\nPurpose of this model is to create SQL queries from natural-language text.\n\nIn order to achieve accuracte results, database schema was incorporated to the prompt during training.\n\nGitHub repository can be found here.",
"## Requirements",
"## Usage\n\nPlease exercise caution when formatting the input.\n\n\n\n*Output:*",
"## Evaluation\n\nThe fine-tuned model was evaluated using the combination of test splits of the above datasets. ROUGE metrics were utilized for the assessment, and the results are outlined below."
] | [
"TAGS\n#transformers #safetensors #t5 #text2text-generation #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n",
"# FLAN-T5 Base Text to SQL Model\n\nThis model was fine-tuned on Google's FLAN-T5 base using SParC, Spider, and CoSQL datasets.\n\nPurpose of this model is to create SQL queries from natural-language text.\n\nIn order to achieve accuracte results, database schema was incorporated to the prompt during training.\n\nGitHub repository can be found here.",
"## Requirements",
"## Usage\n\nPlease exercise caution when formatting the input.\n\n\n\n*Output:*",
"## Evaluation\n\nThe fine-tuned model was evaluated using the combination of test splits of the above datasets. ROUGE metrics were utilized for the assessment, and the results are outlined below."
] |
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. -->
# imdb-spoiler-distilbertOrigDatasetLR3
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5819
- Accuracy: 0.6863
- Recall: 0.787
- Precision: 0.6550
- F1: 0.7150
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 3e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Recall | Precision | F1 |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|:---------:|:------:|
| 0.6356 | 0.12 | 500 | 0.6284 | 0.6763 | 0.7873 | 0.6442 | 0.7086 |
| 0.6047 | 0.25 | 1000 | 0.5933 | 0.6781 | 0.774 | 0.6495 | 0.7063 |
| 0.602 | 0.38 | 1500 | 0.5956 | 0.678 | 0.5305 | 0.7525 | 0.6223 |
| 0.5869 | 0.5 | 2000 | 0.6089 | 0.6877 | 0.7338 | 0.6719 | 0.7015 |
| 0.5776 | 0.62 | 2500 | 0.5846 | 0.6934 | 0.6983 | 0.6915 | 0.6949 |
| 0.5799 | 0.75 | 3000 | 0.6320 | 0.6851 | 0.7595 | 0.6612 | 0.7069 |
| 0.5793 | 0.88 | 3500 | 0.5819 | 0.6863 | 0.787 | 0.6550 | 0.7150 |
| 0.5684 | 1.0 | 4000 | 0.5720 | 0.6941 | 0.6723 | 0.7030 | 0.6873 |
| 0.5249 | 1.12 | 4500 | 0.5846 | 0.6946 | 0.6515 | 0.7130 | 0.6809 |
| 0.5117 | 1.25 | 5000 | 0.6313 | 0.6871 | 0.7652 | 0.6618 | 0.7098 |
| 0.5032 | 1.38 | 5500 | 0.6299 | 0.6933 | 0.62 | 0.7264 | 0.6690 |
| 0.4922 | 1.5 | 6000 | 0.6192 | 0.693 | 0.6677 | 0.7033 | 0.6850 |
| 0.4911 | 1.62 | 6500 | 0.6103 | 0.6939 | 0.6895 | 0.6956 | 0.6925 |
| 0.4967 | 1.75 | 7000 | 0.6010 | 0.6963 | 0.6787 | 0.7034 | 0.6908 |
| 0.4908 | 1.88 | 7500 | 0.6058 | 0.6963 | 0.682 | 0.7020 | 0.6919 |
| 0.4914 | 2.0 | 8000 | 0.6026 | 0.6964 | 0.664 | 0.7100 | 0.6862 |
| 0.3773 | 2.12 | 8500 | 0.7974 | 0.6904 | 0.6252 | 0.7189 | 0.6688 |
| 0.3788 | 2.25 | 9000 | 0.7835 | 0.6894 | 0.6985 | 0.6860 | 0.6922 |
| 0.3726 | 2.38 | 9500 | 0.7925 | 0.6824 | 0.6198 | 0.7085 | 0.6612 |
| 0.3785 | 2.5 | 10000 | 0.8013 | 0.6825 | 0.6687 | 0.6877 | 0.6781 |
| 0.372 | 2.62 | 10500 | 0.7720 | 0.6843 | 0.66 | 0.6936 | 0.6764 |
| 0.3489 | 2.75 | 11000 | 0.8167 | 0.6885 | 0.6697 | 0.6958 | 0.6825 |
| 0.3668 | 2.88 | 11500 | 0.8052 | 0.6855 | 0.6535 | 0.6982 | 0.6751 |
| 0.3567 | 3.0 | 12000 | 0.7942 | 0.687 | 0.691 | 0.6855 | 0.6882 |
### Framework versions
- Transformers 4.39.3
- Pytorch 2.2.2+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
| {"license": "apache-2.0", "tags": ["generated_from_trainer"], "metrics": ["accuracy", "recall", "precision", "f1"], "base_model": "distilbert-base-uncased", "model-index": [{"name": "imdb-spoiler-distilbertOrigDatasetLR3", "results": []}]} | Zritze/imdb-spoiler-distilbertOrigDatasetLR3 | null | [
"transformers",
"safetensors",
"distilbert",
"text-classification",
"generated_from_trainer",
"base_model:distilbert-base-uncased",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-04-17T17:53:27+00:00 | [] | [] | TAGS
#transformers #safetensors #distilbert #text-classification #generated_from_trainer #base_model-distilbert-base-uncased #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us
| imdb-spoiler-distilbertOrigDatasetLR3
=====================================
This model is a fine-tuned version of distilbert-base-uncased on the None dataset.
It achieves the following results on the evaluation set:
* Loss: 0.5819
* Accuracy: 0.6863
* Recall: 0.787
* Precision: 0.6550
* F1: 0.7150
Model description
-----------------
More information needed
Intended uses & limitations
---------------------------
More information needed
Training and evaluation data
----------------------------
More information needed
Training procedure
------------------
### Training hyperparameters
The following hyperparameters were used during training:
* learning\_rate: 3e-05
* train\_batch\_size: 8
* eval\_batch\_size: 8
* seed: 42
* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
* lr\_scheduler\_type: linear
* num\_epochs: 3
### Training results
### Framework versions
* Transformers 4.39.3
* Pytorch 2.2.2+cu121
* Datasets 2.18.0
* Tokenizers 0.15.2
| [
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 3e-05\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 3",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.39.3\n* Pytorch 2.2.2+cu121\n* Datasets 2.18.0\n* Tokenizers 0.15.2"
] | [
"TAGS\n#transformers #safetensors #distilbert #text-classification #generated_from_trainer #base_model-distilbert-base-uncased #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n",
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 3e-05\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 3",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.39.3\n* Pytorch 2.2.2+cu121\n* Datasets 2.18.0\n* Tokenizers 0.15.2"
] |
text-generation | transformers |
# Mamba
<!-- Provide a quick summary of what the model is/does. -->
This repository contains the `transfromers` compatible `mamba-2.8b`. The checkpoints are untouched, but the full `config.json` and tokenizer are pushed to this repo.
# Usage
You need to install `transformers` from `main` until `transformers=4.39.0` is released.
```bash
pip install git+https://github.com/huggingface/transformers@main
```
We also recommend you to install both `causal_conv_1d` and `mamba-ssm` using:
```bash
pip install causal-conv1d>=1.2.0
pip install mamba-ssm
```
If any of these two is not installed, the "eager" implementation will be used. Otherwise the more optimised `cuda` kernels will be used.
## Generation
You can use the classic `generate` API:
```python
>>> from transformers import MambaConfig, MambaForCausalLM, AutoTokenizer
>>> import torch
>>> tokenizer = AutoTokenizer.from_pretrained("state-spaces/mamba-790m-hf")
>>> model = MambaForCausalLM.from_pretrained("state-spaces/mamba-790m-hf")
>>> input_ids = tokenizer("Hey how are you doing?", return_tensors="pt")["input_ids"]
>>> out = model.generate(input_ids, max_new_tokens=10)
>>> print(tokenizer.batch_decode(out))
["Hey how are you doing?\n\nI'm good.\n\nHow are"]
```
| {"language": ["en"], "license": "mit"} | voidful/mamba-790m-chat | null | [
"transformers",
"safetensors",
"mamba",
"text-generation",
"en",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-04-17T17:53:45+00:00 | [] | [
"en"
] | TAGS
#transformers #safetensors #mamba #text-generation #en #license-mit #autotrain_compatible #endpoints_compatible #region-us
|
# Mamba
This repository contains the 'transfromers' compatible 'mamba-2.8b'. The checkpoints are untouched, but the full 'URL' and tokenizer are pushed to this repo.
# Usage
You need to install 'transformers' from 'main' until 'transformers=4.39.0' is released.
We also recommend you to install both 'causal_conv_1d' and 'mamba-ssm' using:
If any of these two is not installed, the "eager" implementation will be used. Otherwise the more optimised 'cuda' kernels will be used.
## Generation
You can use the classic 'generate' API:
| [
"# Mamba\n\n\nThis repository contains the 'transfromers' compatible 'mamba-2.8b'. The checkpoints are untouched, but the full 'URL' and tokenizer are pushed to this repo.",
"# Usage\n\nYou need to install 'transformers' from 'main' until 'transformers=4.39.0' is released. \n\n\nWe also recommend you to install both 'causal_conv_1d' and 'mamba-ssm' using: \n\n\n\nIf any of these two is not installed, the \"eager\" implementation will be used. Otherwise the more optimised 'cuda' kernels will be used.",
"## Generation\nYou can use the classic 'generate' API:"
] | [
"TAGS\n#transformers #safetensors #mamba #text-generation #en #license-mit #autotrain_compatible #endpoints_compatible #region-us \n",
"# Mamba\n\n\nThis repository contains the 'transfromers' compatible 'mamba-2.8b'. The checkpoints are untouched, but the full 'URL' and tokenizer are pushed to this repo.",
"# Usage\n\nYou need to install 'transformers' from 'main' until 'transformers=4.39.0' is released. \n\n\nWe also recommend you to install both 'causal_conv_1d' and 'mamba-ssm' using: \n\n\n\nIf any of these two is not installed, the \"eager\" implementation will be used. Otherwise the more optimised 'cuda' kernels will be used.",
"## Generation\nYou can use the classic 'generate' API:"
] |
sentence-similarity | sentence-transformers |
# phoenixSP/embedding-finetuned-model-v2
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
<!--- Describe your model here -->
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('phoenixSP/embedding-finetuned-model-v2')
embeddings = model.encode(sentences)
print(embeddings)
```
## Evaluation Results
<!--- Describe how your model was evaluated -->
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=phoenixSP/embedding-finetuned-model-v2)
## Training
The model was trained with the parameters:
**DataLoader**:
`torch.utils.data.dataloader.DataLoader` of length 238 with parameters:
```
{'batch_size': 10, 'sampler': 'torch.utils.data.sampler.SequentialSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
```
**Loss**:
`sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss` with parameters:
```
{'scale': 20.0, 'similarity_fct': 'cos_sim'}
```
Parameters of the fit()-Method:
```
{
"epochs": 25,
"evaluation_steps": 50,
"evaluator": "sentence_transformers.evaluation.InformationRetrievalEvaluator.InformationRetrievalEvaluator",
"max_grad_norm": 1,
"optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
"optimizer_params": {
"lr": 2e-05
},
"scheduler": "WarmupLinear",
"steps_per_epoch": null,
"warmup_steps": 595,
"weight_decay": 0.01
}
```
## Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 384, 'do_lower_case': False}) with Transformer model: MPNetModel
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
(2): Normalize()
)
```
## Citing & Authors
<!--- Describe where people can find more information --> | {"library_name": "sentence-transformers", "tags": ["sentence-transformers", "feature-extraction", "sentence-similarity"], "pipeline_tag": "sentence-similarity"} | phoenixSP/embedding-finetuned-model-v2 | null | [
"sentence-transformers",
"safetensors",
"mpnet",
"feature-extraction",
"sentence-similarity",
"endpoints_compatible",
"region:us"
] | null | 2024-04-17T17:55:22+00:00 | [] | [] | TAGS
#sentence-transformers #safetensors #mpnet #feature-extraction #sentence-similarity #endpoints_compatible #region-us
|
# phoenixSP/embedding-finetuned-model-v2
This is a sentence-transformers model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
## Usage (Sentence-Transformers)
Using this model becomes easy when you have sentence-transformers installed:
Then you can use the model like this:
## Evaluation Results
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: URL
## Training
The model was trained with the parameters:
DataLoader:
'URL.dataloader.DataLoader' of length 238 with parameters:
Loss:
'sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss' with parameters:
Parameters of the fit()-Method:
## Full Model Architecture
## Citing & Authors
| [
"# phoenixSP/embedding-finetuned-model-v2\n\nThis is a sentence-transformers model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.",
"## Usage (Sentence-Transformers)\n\nUsing this model becomes easy when you have sentence-transformers installed:\n\n\n\nThen you can use the model like this:",
"## Evaluation Results\n\n\n\nFor an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: URL",
"## Training\nThe model was trained with the parameters:\n\nDataLoader:\n\n'URL.dataloader.DataLoader' of length 238 with parameters:\n\n\nLoss:\n\n'sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss' with parameters:\n \n\nParameters of the fit()-Method:",
"## Full Model Architecture",
"## Citing & Authors"
] | [
"TAGS\n#sentence-transformers #safetensors #mpnet #feature-extraction #sentence-similarity #endpoints_compatible #region-us \n",
"# phoenixSP/embedding-finetuned-model-v2\n\nThis is a sentence-transformers model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.",
"## Usage (Sentence-Transformers)\n\nUsing this model becomes easy when you have sentence-transformers installed:\n\n\n\nThen you can use the model like this:",
"## Evaluation Results\n\n\n\nFor an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: URL",
"## Training\nThe model was trained with the parameters:\n\nDataLoader:\n\n'URL.dataloader.DataLoader' of length 238 with parameters:\n\n\nLoss:\n\n'sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss' with parameters:\n \n\nParameters of the fit()-Method:",
"## Full Model Architecture",
"## Citing & Authors"
] |
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. -->
# mistral-journal-finetune-aipi
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 2.7849
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2.5e-05
- train_batch_size: 2
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1
- training_steps: 500
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-------:|:----:|:---------------:|
| 1.3541 | 0.6757 | 25 | 1.4800 |
| 0.8644 | 1.3514 | 50 | 1.4804 |
| 0.8449 | 2.0270 | 75 | 1.5426 |
| 0.5501 | 2.7027 | 100 | 1.6733 |
| 0.2691 | 3.3784 | 125 | 1.8077 |
| 0.2187 | 4.0541 | 150 | 1.9603 |
| 0.1408 | 4.7297 | 175 | 2.0132 |
| 0.0892 | 5.4054 | 200 | 2.2048 |
| 0.0891 | 6.0811 | 225 | 2.2487 |
| 0.0633 | 6.7568 | 250 | 2.2303 |
| 0.0516 | 7.4324 | 275 | 2.2637 |
| 0.0479 | 8.1081 | 300 | 2.2366 |
| 0.0486 | 8.7838 | 325 | 2.3266 |
| 0.0435 | 9.4595 | 350 | 2.5567 |
| 0.0389 | 10.1351 | 375 | 2.6020 |
| 0.04 | 10.8108 | 400 | 2.7252 |
| 0.0341 | 11.4865 | 425 | 2.6801 |
| 0.0357 | 12.1622 | 450 | 2.7342 |
| 0.0363 | 12.8378 | 475 | 2.7706 |
| 0.0342 | 13.5135 | 500 | 2.7849 |
### Framework versions
- PEFT 0.10.1.dev0
- Transformers 4.40.0.dev0
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.19.0 | {"license": "apache-2.0", "library_name": "peft", "tags": ["generated_from_trainer"], "base_model": "mistralai/Mistral-7B-v0.1", "model-index": [{"name": "mistral-journal-finetune-aipi", "results": []}]} | wintercoming6/mistral-journal-finetune-aipi | null | [
"peft",
"safetensors",
"generated_from_trainer",
"base_model:mistralai/Mistral-7B-v0.1",
"license:apache-2.0",
"region:us"
] | null | 2024-04-17T17:55:44+00:00 | [] | [] | TAGS
#peft #safetensors #generated_from_trainer #base_model-mistralai/Mistral-7B-v0.1 #license-apache-2.0 #region-us
| mistral-journal-finetune-aipi
=============================
This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on an unknown dataset.
It achieves the following results on the evaluation set:
* Loss: 2.7849
Model description
-----------------
More information needed
Intended uses & limitations
---------------------------
More information needed
Training and evaluation data
----------------------------
More information needed
Training procedure
------------------
### Training hyperparameters
The following hyperparameters were used during training:
* learning\_rate: 2.5e-05
* train\_batch\_size: 2
* eval\_batch\_size: 8
* seed: 42
* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
* lr\_scheduler\_type: linear
* lr\_scheduler\_warmup\_steps: 1
* training\_steps: 500
* mixed\_precision\_training: Native AMP
### Training results
### Framework versions
* PEFT 0.10.1.dev0
* Transformers 4.40.0.dev0
* Pytorch 2.2.1+cu121
* Datasets 2.18.0
* Tokenizers 0.19.0
| [
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2.5e-05\n* train\\_batch\\_size: 2\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_steps: 1\n* training\\_steps: 500\n* mixed\\_precision\\_training: Native AMP",
"### Training results",
"### Framework versions\n\n\n* PEFT 0.10.1.dev0\n* Transformers 4.40.0.dev0\n* Pytorch 2.2.1+cu121\n* Datasets 2.18.0\n* Tokenizers 0.19.0"
] | [
"TAGS\n#peft #safetensors #generated_from_trainer #base_model-mistralai/Mistral-7B-v0.1 #license-apache-2.0 #region-us \n",
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2.5e-05\n* train\\_batch\\_size: 2\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_steps: 1\n* training\\_steps: 500\n* mixed\\_precision\\_training: Native AMP",
"### Training results",
"### Framework versions\n\n\n* PEFT 0.10.1.dev0\n* Transformers 4.40.0.dev0\n* Pytorch 2.2.1+cu121\n* Datasets 2.18.0\n* Tokenizers 0.19.0"
] |
text-generation | transformers |
# Tess-2.0-Mixtral-8x22B
Tess, short for Tesoro (Treasure in Italian), is a general purpose Large Language Model series. Tess-2.0-Mixtral-8x22B was trained on the mistral-community/Mixtral-8x22B-v0.1 base.
# Prompt Format
```
SYSTEM: <ANY SYSTEM CONTEXT>
USER:
ASSISTANT:
```
# Training Methodology
Tess-2.0-Mixtral-8x22B was trained on the Tess-2.0 dataset. Tess-2.0 dataset and the training methodology follows LIMA (Less-Is-More) principles, and contains ~25K high-quality code and general training samples. The dataset is highly uncensored, hence the model will almost always follow instructions.
The model was only fine-tuned for 1-epoch to try and preserve its entropy as much as possible.
# Sample code to run inference
```python
import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
model_path = "migtissera/Tess-2.0-Mixtral-8x22B"
output_file_path = "./conversations.jsonl"
model = AutoModelForCausalLM.from_pretrained(
model_path,
torch_dtype=torch.float16,
device_map="auto",
load_in_8bit=False,
trust_remote_code=True,
)
tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
def generate_text(instruction):
tokens = tokenizer.encode(instruction)
tokens = torch.LongTensor(tokens).unsqueeze(0)
tokens = tokens.to("cuda")
instance = {
"input_ids": tokens,
"top_p": 1.0,
"temperature": 0.5,
"generate_len": 1024,
"top_k": 50,
}
length = len(tokens[0])
with torch.no_grad():
rest = model.generate(
input_ids=tokens,
max_length=length + instance["generate_len"],
use_cache=True,
do_sample=True,
top_p=instance["top_p"],
temperature=instance["temperature"],
top_k=instance["top_k"],
num_return_sequences=1,
)
output = rest[0][length:]
string = tokenizer.decode(output, skip_special_tokens=True)
answer = string.split("USER:")[0].strip()
return f"{answer}"
conversation = f"SYSTEM: Answer the question thoughtfully and intelligently. Always answer without hesitation."
while True:
user_input = input("You: ")
llm_prompt = f"{conversation} \nUSER: {user_input} \nASSISTANT: "
answer = generate_text(llm_prompt)
print(answer)
conversation = f"{llm_prompt}{answer}"
json_data = {"prompt": user_input, "answer": answer}
## Save your conversation
with open(output_file_path, "a") as output_file:
output_file.write(json.dumps(json_data) + "\n")
```
# Join My General AI Discord (NeuroLattice):
https://discord.gg/Hz6GrwGFKD
# Limitations & Biases:
While this model aims for accuracy, it can occasionally produce inaccurate or misleading results.
Despite diligent efforts in refining the pretraining data, there remains a possibility for the generation of inappropriate, biased, or offensive content.
Exercise caution and cross-check information when necessary. This is an uncensored model.
| {"license": "apache-2.0"} | blockblockblock/Tess-2.0-Mixtral-8x22B-bpw4 | null | [
"transformers",
"safetensors",
"mixtral",
"text-generation",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"4-bit",
"region:us"
] | null | 2024-04-17T17:55:50+00:00 | [] | [] | TAGS
#transformers #safetensors #mixtral #text-generation #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us
|
!Tesoro
# Tess-2.0-Mixtral-8x22B
Tess, short for Tesoro (Treasure in Italian), is a general purpose Large Language Model series. Tess-2.0-Mixtral-8x22B was trained on the mistral-community/Mixtral-8x22B-v0.1 base.
# Prompt Format
# Training Methodology
Tess-2.0-Mixtral-8x22B was trained on the Tess-2.0 dataset. Tess-2.0 dataset and the training methodology follows LIMA (Less-Is-More) principles, and contains ~25K high-quality code and general training samples. The dataset is highly uncensored, hence the model will almost always follow instructions.
The model was only fine-tuned for 1-epoch to try and preserve its entropy as much as possible.
# Sample code to run inference
# Join My General AI Discord (NeuroLattice):
URL
# Limitations & Biases:
While this model aims for accuracy, it can occasionally produce inaccurate or misleading results.
Despite diligent efforts in refining the pretraining data, there remains a possibility for the generation of inappropriate, biased, or offensive content.
Exercise caution and cross-check information when necessary. This is an uncensored model.
| [
"# Tess-2.0-Mixtral-8x22B\nTess, short for Tesoro (Treasure in Italian), is a general purpose Large Language Model series. Tess-2.0-Mixtral-8x22B was trained on the mistral-community/Mixtral-8x22B-v0.1 base.",
"# Prompt Format",
"# Training Methodology\nTess-2.0-Mixtral-8x22B was trained on the Tess-2.0 dataset. Tess-2.0 dataset and the training methodology follows LIMA (Less-Is-More) principles, and contains ~25K high-quality code and general training samples. The dataset is highly uncensored, hence the model will almost always follow instructions.\n\nThe model was only fine-tuned for 1-epoch to try and preserve its entropy as much as possible.",
"# Sample code to run inference",
"# Join My General AI Discord (NeuroLattice):\nURL",
"# Limitations & Biases:\n\nWhile this model aims for accuracy, it can occasionally produce inaccurate or misleading results. \n\nDespite diligent efforts in refining the pretraining data, there remains a possibility for the generation of inappropriate, biased, or offensive content. \n\nExercise caution and cross-check information when necessary. This is an uncensored model."
] | [
"TAGS\n#transformers #safetensors #mixtral #text-generation #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us \n",
"# Tess-2.0-Mixtral-8x22B\nTess, short for Tesoro (Treasure in Italian), is a general purpose Large Language Model series. Tess-2.0-Mixtral-8x22B was trained on the mistral-community/Mixtral-8x22B-v0.1 base.",
"# Prompt Format",
"# Training Methodology\nTess-2.0-Mixtral-8x22B was trained on the Tess-2.0 dataset. Tess-2.0 dataset and the training methodology follows LIMA (Less-Is-More) principles, and contains ~25K high-quality code and general training samples. The dataset is highly uncensored, hence the model will almost always follow instructions.\n\nThe model was only fine-tuned for 1-epoch to try and preserve its entropy as much as possible.",
"# Sample code to run inference",
"# Join My General AI Discord (NeuroLattice):\nURL",
"# Limitations & Biases:\n\nWhile this model aims for accuracy, it can occasionally produce inaccurate or misleading results. \n\nDespite diligent efforts in refining the pretraining data, there remains a possibility for the generation of inappropriate, biased, or offensive content. \n\nExercise caution and cross-check information when necessary. This is an uncensored model."
] |
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 [TIES](https://arxiv.org/abs/2306.01708) merge method using [amazingvince/Not-WizardLM-2-7B](https://huggingface.co/amazingvince/Not-WizardLM-2-7B) as a base.
### Models Merged
The following models were included in the merge:
* [TFMC/Japanese-Starling-ChatV-7B](https://huggingface.co/TFMC/Japanese-Starling-ChatV-7B)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
models:
- model: amazingvince/Not-WizardLM-2-7B
#no parameters necessary for base model
- model: amazingvince/Not-WizardLM-2-7B
parameters:
density: 0.5
weight: 0.5
- model: TFMC/Japanese-Starling-ChatV-7B
parameters:
density: 0.5
weight: 0.5
merge_method: ties
base_model: amazingvince/Not-WizardLM-2-7B
parameters:
normalize: false
int8_mask: true
dtype: float16
```
| {"library_name": "transformers", "tags": ["mergekit", "merge"], "base_model": ["TFMC/Japanese-Starling-ChatV-7B", "amazingvince/Not-WizardLM-2-7B"]} | Exveria/merge003 | null | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"mergekit",
"merge",
"arxiv:2306.01708",
"base_model:TFMC/Japanese-Starling-ChatV-7B",
"base_model:amazingvince/Not-WizardLM-2-7B",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-04-17T17:59:35+00:00 | [
"2306.01708"
] | [] | TAGS
#transformers #safetensors #mistral #text-generation #mergekit #merge #arxiv-2306.01708 #base_model-TFMC/Japanese-Starling-ChatV-7B #base_model-amazingvince/Not-WizardLM-2-7B #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us
| # merge
This is a merge of pre-trained language models created using mergekit.
## Merge Details
### Merge Method
This model was merged using the TIES merge method using amazingvince/Not-WizardLM-2-7B as a base.
### Models Merged
The following models were included in the merge:
* TFMC/Japanese-Starling-ChatV-7B
### Configuration
The following YAML configuration was used to produce this model:
| [
"# merge\n\nThis is a merge of pre-trained language models created using mergekit.",
"## Merge Details",
"### Merge Method\n\nThis model was merged using the TIES merge method using amazingvince/Not-WizardLM-2-7B as a base.",
"### Models Merged\n\nThe following models were included in the merge:\n* TFMC/Japanese-Starling-ChatV-7B",
"### Configuration\n\nThe following YAML configuration was used to produce this model:"
] | [
"TAGS\n#transformers #safetensors #mistral #text-generation #mergekit #merge #arxiv-2306.01708 #base_model-TFMC/Japanese-Starling-ChatV-7B #base_model-amazingvince/Not-WizardLM-2-7B #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n",
"# merge\n\nThis is a merge of pre-trained language models created using mergekit.",
"## Merge Details",
"### Merge Method\n\nThis model was merged using the TIES merge method using amazingvince/Not-WizardLM-2-7B as a base.",
"### Models Merged\n\nThe following models were included in the merge:\n* TFMC/Japanese-Starling-ChatV-7B",
"### Configuration\n\nThe following YAML configuration was used to produce this model:"
] |
null | peft | ## Training procedure
The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float16
### Framework versions
- PEFT 0.4.0
| {"library_name": "peft"} | 123addy/chat-fine-tuned-llama2 | null | [
"peft",
"region:us"
] | null | 2024-04-17T17:59:44+00:00 | [] | [] | TAGS
#peft #region-us
| ## Training procedure
The following 'bitsandbytes' quantization config was used during training:
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float16
### Framework versions
- PEFT 0.4.0
| [
"## Training procedure\n\n\nThe following 'bitsandbytes' quantization config was used during training:\n- load_in_8bit: False\n- load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: False\n- bnb_4bit_compute_dtype: float16",
"### Framework versions\n\n\n- PEFT 0.4.0"
] | [
"TAGS\n#peft #region-us \n",
"## Training procedure\n\n\nThe following 'bitsandbytes' quantization config was used during training:\n- load_in_8bit: False\n- load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: False\n- bnb_4bit_compute_dtype: float16",
"### Framework versions\n\n\n- PEFT 0.4.0"
] |
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": []} | eeshanpatel/T5-Conditional-Generation | null | [
"transformers",
"safetensors",
"t5",
"text2text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-04-17T17:59:49+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #safetensors #t5 #text2text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
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:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
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.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
| [
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] | [
"TAGS\n#transformers #safetensors #t5 #text2text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
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. -->
# Intent-classification-BERT-cased-Ashu
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: 0.1960
- Accuracy: 0.9321
## 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: 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: 30
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 1.6354 | 0.24 | 10 | 1.3680 | 0.3478 |
| 1.2714 | 0.49 | 20 | 1.0836 | 0.5590 |
| 1.1593 | 0.73 | 30 | 0.7338 | 0.8012 |
| 0.6734 | 0.98 | 40 | 0.4365 | 0.8882 |
| 0.554 | 1.22 | 50 | 0.6694 | 0.8385 |
| 0.5863 | 1.46 | 60 | 0.4113 | 0.8385 |
| 0.3894 | 1.71 | 70 | 0.2667 | 0.9006 |
| 0.3458 | 1.95 | 80 | 0.3299 | 0.8882 |
| 0.3338 | 2.2 | 90 | 0.3247 | 0.8882 |
| 0.2073 | 2.44 | 100 | 0.2303 | 0.8944 |
| 0.2844 | 2.68 | 110 | 0.2886 | 0.8944 |
| 0.4828 | 2.93 | 120 | 0.2475 | 0.9006 |
| 0.2294 | 3.17 | 130 | 0.2751 | 0.8820 |
| 0.3103 | 3.41 | 140 | 0.2409 | 0.8696 |
| 0.1972 | 3.66 | 150 | 0.2038 | 0.9130 |
| 0.1808 | 3.9 | 160 | 0.2399 | 0.9068 |
| 0.1904 | 4.15 | 170 | 0.2559 | 0.9068 |
| 0.2458 | 4.39 | 180 | 0.5942 | 0.8634 |
| 0.1777 | 4.63 | 190 | 0.3048 | 0.8820 |
| 0.2233 | 4.88 | 200 | 0.2170 | 0.9130 |
| 0.2446 | 5.12 | 210 | 0.3414 | 0.8758 |
| 0.1631 | 5.37 | 220 | 0.3601 | 0.8882 |
| 0.3007 | 5.61 | 230 | 0.4856 | 0.8571 |
| 0.2979 | 5.85 | 240 | 0.7301 | 0.8447 |
| 0.3355 | 6.1 | 250 | 0.3030 | 0.8944 |
| 0.2137 | 6.34 | 260 | 0.4366 | 0.8820 |
| 0.3109 | 6.59 | 270 | 0.3117 | 0.8944 |
| 0.1863 | 6.83 | 280 | 0.4387 | 0.8758 |
| 0.2912 | 7.07 | 290 | 0.2516 | 0.9006 |
| 0.1621 | 7.32 | 300 | 0.3174 | 0.9006 |
| 0.2598 | 7.56 | 310 | 0.6467 | 0.8385 |
| 0.351 | 7.8 | 320 | 0.2943 | 0.8820 |
| 0.3232 | 8.05 | 330 | 0.2908 | 0.8944 |
| 0.1534 | 8.29 | 340 | 0.3321 | 0.8944 |
| 0.208 | 8.54 | 350 | 0.4615 | 0.8447 |
| 0.3685 | 8.78 | 360 | 0.4475 | 0.8696 |
| 0.1663 | 9.02 | 370 | 0.4067 | 0.8696 |
| 0.2267 | 9.27 | 380 | 0.4081 | 0.8758 |
| 0.2486 | 9.51 | 390 | 0.5971 | 0.8509 |
| 0.4295 | 9.76 | 400 | 0.2917 | 0.8882 |
| 0.2481 | 10.0 | 410 | 0.3792 | 0.8820 |
| 0.1681 | 10.24 | 420 | 0.3793 | 0.8882 |
| 0.1313 | 10.49 | 430 | 0.3035 | 0.9006 |
| 0.3188 | 10.73 | 440 | 0.3317 | 0.8758 |
| 0.2266 | 10.98 | 450 | 0.4534 | 0.8696 |
| 0.1728 | 11.22 | 460 | 0.3922 | 0.8882 |
| 0.1655 | 11.46 | 470 | 0.2906 | 0.8882 |
| 0.1764 | 11.71 | 480 | 0.3753 | 0.8758 |
| 0.1654 | 11.95 | 490 | 0.3411 | 0.8820 |
| 0.114 | 12.2 | 500 | 0.3693 | 0.8758 |
| 0.2119 | 12.44 | 510 | 0.4721 | 0.8820 |
| 0.1655 | 12.68 | 520 | 0.5551 | 0.8758 |
| 0.2329 | 12.93 | 530 | 0.4987 | 0.8758 |
| 0.2048 | 13.17 | 540 | 0.4264 | 0.8758 |
| 0.2365 | 13.41 | 550 | 0.3291 | 0.9006 |
| 0.1067 | 13.66 | 560 | 0.3542 | 0.9006 |
| 0.1939 | 13.9 | 570 | 0.3957 | 0.9006 |
| 0.2257 | 14.15 | 580 | 0.3690 | 0.8882 |
| 0.1853 | 14.39 | 590 | 0.3377 | 0.9006 |
| 0.2486 | 14.63 | 600 | 0.2423 | 0.9068 |
| 0.147 | 14.88 | 610 | 0.3141 | 0.8882 |
| 0.1639 | 15.12 | 620 | 0.4718 | 0.8758 |
| 0.151 | 15.37 | 630 | 0.6900 | 0.8571 |
| 0.2909 | 15.61 | 640 | 0.3900 | 0.9006 |
| 0.2273 | 15.85 | 650 | 0.3972 | 0.8820 |
| 0.2317 | 16.1 | 660 | 0.3208 | 0.8944 |
| 0.2005 | 16.34 | 670 | 0.3355 | 0.8882 |
| 0.1807 | 16.59 | 680 | 0.4310 | 0.8882 |
| 0.216 | 16.83 | 690 | 0.4881 | 0.8882 |
| 0.1307 | 17.07 | 700 | 0.3590 | 0.8882 |
| 0.234 | 17.32 | 710 | 0.3503 | 0.8758 |
| 0.224 | 17.56 | 720 | 0.3790 | 0.8758 |
| 0.1708 | 17.8 | 730 | 0.2696 | 0.8944 |
| 0.1848 | 18.05 | 740 | 0.2631 | 0.8944 |
| 0.1799 | 18.29 | 750 | 0.2867 | 0.9006 |
| 0.1882 | 18.54 | 760 | 0.4595 | 0.8758 |
| 0.1072 | 18.78 | 770 | 0.3914 | 0.8944 |
| 0.2072 | 19.02 | 780 | 0.3018 | 0.9006 |
| 0.2289 | 19.27 | 790 | 0.2462 | 0.9006 |
| 0.1597 | 19.51 | 800 | 0.2632 | 0.9068 |
| 0.1475 | 19.76 | 810 | 0.3012 | 0.8944 |
| 0.1691 | 20.0 | 820 | 0.2272 | 0.9006 |
| 0.1339 | 20.24 | 830 | 0.2947 | 0.8882 |
| 0.1247 | 20.49 | 840 | 0.3514 | 0.9068 |
| 0.2072 | 20.73 | 850 | 0.3281 | 0.8758 |
| 0.1379 | 20.98 | 860 | 0.3696 | 0.9006 |
| 0.123 | 21.22 | 870 | 0.4604 | 0.8944 |
| 0.1697 | 21.46 | 880 | 0.4491 | 0.8820 |
| 0.1613 | 21.71 | 890 | 0.3338 | 0.9006 |
| 0.1816 | 21.95 | 900 | 0.3421 | 0.9006 |
| 0.2516 | 22.2 | 910 | 0.3395 | 0.9006 |
| 0.1367 | 22.44 | 920 | 0.3416 | 0.9006 |
| 0.1148 | 22.68 | 930 | 0.3901 | 0.8944 |
| 0.123 | 22.93 | 940 | 0.4092 | 0.8944 |
| 0.0922 | 23.17 | 950 | 0.4680 | 0.8820 |
| 0.1294 | 23.41 | 960 | 0.4898 | 0.8944 |
| 0.1986 | 23.66 | 970 | 0.4286 | 0.8882 |
| 0.175 | 23.9 | 980 | 0.4919 | 0.8882 |
| 0.1264 | 24.15 | 990 | 0.5121 | 0.8944 |
| 0.1454 | 24.39 | 1000 | 0.5529 | 0.8944 |
| 0.1986 | 24.63 | 1010 | 0.4504 | 0.8944 |
| 0.2549 | 24.88 | 1020 | 0.3442 | 0.8944 |
| 0.1878 | 25.12 | 1030 | 0.3414 | 0.8882 |
| 0.1313 | 25.37 | 1040 | 0.3944 | 0.8758 |
| 0.0957 | 25.61 | 1050 | 0.4231 | 0.8820 |
| 0.1751 | 25.85 | 1060 | 0.4765 | 0.8820 |
| 0.1389 | 26.1 | 1070 | 0.4927 | 0.8820 |
| 0.1038 | 26.34 | 1080 | 0.4923 | 0.8820 |
| 0.1371 | 26.59 | 1090 | 0.4848 | 0.8820 |
| 0.1576 | 26.83 | 1100 | 0.4765 | 0.8820 |
| 0.1539 | 27.07 | 1110 | 0.4926 | 0.8820 |
| 0.1742 | 27.32 | 1120 | 0.4749 | 0.8820 |
| 0.1365 | 27.56 | 1130 | 0.4717 | 0.8820 |
| 0.1284 | 27.8 | 1140 | 0.4754 | 0.8820 |
| 0.0794 | 28.05 | 1150 | 0.4871 | 0.8820 |
| 0.0934 | 28.29 | 1160 | 0.5052 | 0.8820 |
| 0.1384 | 28.54 | 1170 | 0.5146 | 0.8820 |
| 0.1323 | 28.78 | 1180 | 0.5140 | 0.8820 |
| 0.1352 | 29.02 | 1190 | 0.5068 | 0.8820 |
| 0.1576 | 29.27 | 1200 | 0.5068 | 0.8758 |
| 0.1278 | 29.51 | 1210 | 0.5067 | 0.8758 |
| 0.1256 | 29.76 | 1220 | 0.5071 | 0.8758 |
| 0.0999 | 30.0 | 1230 | 0.5078 | 0.8758 |
### Framework versions
- Transformers 4.38.2
- Pytorch 2.1.2
- Datasets 2.1.0
- Tokenizers 0.15.2
| {"license": "apache-2.0", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "google-bert/bert-base-cased", "model-index": [{"name": "Intent-classification-BERT-cased-Ashu", "results": []}]} | Narkantak/Intent-classification-BERT-cased-Ashu | null | [
"transformers",
"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 | 2024-04-17T18:00:58+00:00 | [] | [] | TAGS
#transformers #safetensors #bert #text-classification #generated_from_trainer #base_model-google-bert/bert-base-cased #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us
| Intent-classification-BERT-cased-Ashu
=====================================
This model is a fine-tuned version of google-bert/bert-base-cased on an unknown dataset.
It achieves the following results on the evaluation set:
* Loss: 0.1960
* Accuracy: 0.9321
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: 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: 30
### Training results
### Framework versions
* Transformers 4.38.2
* Pytorch 2.1.2
* Datasets 2.1.0
* Tokenizers 0.15.2
| [
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0002\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 16\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 30",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.38.2\n* Pytorch 2.1.2\n* Datasets 2.1.0\n* Tokenizers 0.15.2"
] | [
"TAGS\n#transformers #safetensors #bert #text-classification #generated_from_trainer #base_model-google-bert/bert-base-cased #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n",
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0002\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 16\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 30",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.38.2\n* Pytorch 2.1.2\n* Datasets 2.1.0\n* Tokenizers 0.15.2"
] |
text-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": []} | tomaszki/mistral-35 | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-04-17T18:02:53+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #safetensors #llama #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
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:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
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.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
| [
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] | [
"TAGS\n#transformers #safetensors #llama #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
text-generation | transformers | # Model Card for Mixtral-8x22B-Instruct-v0.1-4bit
The Mixtral-8x7B Large Language Model (LLM) is a pretrained generative Sparse Mixture of Experts. The Mixtral-8x7B outperforms Llama 2 70B on most benchmarks we tested.
Model added by [Prince Canuma](https://twitter.com/Prince_Canuma).
For full details of this model please read our [release blog post](https://mistral.ai/news/mixtral-of-experts/).
## Warning
This repo contains weights that are compatible with [vLLM](https://github.com/vllm-project/vllm) serving of the model as well as Hugging Face [transformers](https://github.com/huggingface/transformers) library. It is based on the original Mixtral [torrent release](magnet:?xt=urn:btih:5546272da9065eddeb6fcd7ffddeef5b75be79a7&dn=mixtral-8x7b-32kseqlen&tr=udp%3A%2F%http://2Fopentracker.i2p.rocks%3A6969%2Fannounce&tr=http%3A%2F%http://2Ftracker.openbittorrent.com%3A80%2Fannounce), but the file format and parameter names are different. Please note that model cannot (yet) be instantiated with HF.
## Instruction format
This format must be strictly respected, otherwise the model will generate sub-optimal outputs.
The template used to build a prompt for the Instruct model is defined as follows:
```
<s> [INST] Instruction [/INST] Model answer</s> [INST] Follow-up instruction [/INST]
```
Note that `<s>` and `</s>` are special tokens for beginning of string (BOS) and end of string (EOS) while [INST] and [/INST] are regular strings.
As reference, here is the pseudo-code used to tokenize instructions during fine-tuning:
```python
def tokenize(text):
return tok.encode(text, add_special_tokens=False)
[BOS_ID] +
tokenize("[INST]") + tokenize(USER_MESSAGE_1) + tokenize("[/INST]") +
tokenize(BOT_MESSAGE_1) + [EOS_ID] +
…
tokenize("[INST]") + tokenize(USER_MESSAGE_N) + tokenize("[/INST]") +
tokenize(BOT_MESSAGE_N) + [EOS_ID]
```
In the pseudo-code above, note that the `tokenize` method should not add a BOS or EOS token automatically, but should add a prefix space.
In the Transformers library, one can use [chat templates](https://huggingface.co/docs/transformers/main/en/chat_templating) which make sure the right format is applied.
## Run the model
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "mistralai/Mixtral-8x7B-Instruct-v0.1"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto")
messages = [
{"role": "user", "content": "What is your favourite condiment?"},
{"role": "assistant", "content": "Well, I'm quite partial to a good squeeze of fresh lemon juice. It adds just the right amount of zesty flavour to whatever I'm cooking up in the kitchen!"},
{"role": "user", "content": "Do you have mayonnaise recipes?"}
]
inputs = tokenizer.apply_chat_template(messages, return_tensors="pt").to("cuda")
outputs = model.generate(inputs, max_new_tokens=20)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```
By default, transformers will load the model in full precision. Therefore you might be interested to further reduce down the memory requirements to run the model through the optimizations we offer in HF ecosystem:
### In half-precision
Note `float16` precision only works on GPU devices
<details>
<summary> Click to expand </summary>
```diff
+ import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "mistralai/Mixtral-8x7B-Instruct-v0.1"
tokenizer = AutoTokenizer.from_pretrained(model_id)
+ model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, device_map="auto")
messages = [
{"role": "user", "content": "What is your favourite condiment?"},
{"role": "assistant", "content": "Well, I'm quite partial to a good squeeze of fresh lemon juice. It adds just the right amount of zesty flavour to whatever I'm cooking up in the kitchen!"},
{"role": "user", "content": "Do you have mayonnaise recipes?"}
]
input_ids = tokenizer.apply_chat_template(messages, return_tensors="pt").to("cuda")
outputs = model.generate(input_ids, max_new_tokens=20)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```
</details>
### Lower precision using (8-bit & 4-bit) using `bitsandbytes`
<details>
<summary> Click to expand </summary>
```diff
+ import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "mistralai/Mixtral-8x7B-Instruct-v0.1"
tokenizer = AutoTokenizer.from_pretrained(model_id)
+ model = AutoModelForCausalLM.from_pretrained(model_id, load_in_4bit=True, device_map="auto")
text = "Hello my name is"
messages = [
{"role": "user", "content": "What is your favourite condiment?"},
{"role": "assistant", "content": "Well, I'm quite partial to a good squeeze of fresh lemon juice. It adds just the right amount of zesty flavour to whatever I'm cooking up in the kitchen!"},
{"role": "user", "content": "Do you have mayonnaise recipes?"}
]
input_ids = tokenizer.apply_chat_template(messages, return_tensors="pt").to("cuda")
outputs = model.generate(input_ids, max_new_tokens=20)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```
</details>
### Load the model with Flash Attention 2
<details>
<summary> Click to expand </summary>
```diff
+ import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "mistralai/Mixtral-8x7B-Instruct-v0.1"
tokenizer = AutoTokenizer.from_pretrained(model_id)
+ model = AutoModelForCausalLM.from_pretrained(model_id, use_flash_attention_2=True, device_map="auto")
messages = [
{"role": "user", "content": "What is your favourite condiment?"},
{"role": "assistant", "content": "Well, I'm quite partial to a good squeeze of fresh lemon juice. It adds just the right amount of zesty flavour to whatever I'm cooking up in the kitchen!"},
{"role": "user", "content": "Do you have mayonnaise recipes?"}
]
input_ids = tokenizer.apply_chat_template(messages, return_tensors="pt").to("cuda")
outputs = model.generate(input_ids, max_new_tokens=20)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```
</details>
## Limitations
The Mixtral-8x7B Instruct model is a quick demonstration that the base model can be easily fine-tuned to achieve compelling performance.
It does not have any moderation mechanisms. We're looking forward to engaging with the community on ways to
make the model finely respect guardrails, allowing for deployment in environments requiring moderated outputs.
# The Mistral AI Team
Albert Jiang, Alexandre Sablayrolles, Arthur Mensch, Blanche Savary, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Emma Bou Hanna, Florian Bressand, Gianna Lengyel, Guillaume Bour, Guillaume Lample, Lélio Renard Lavaud, Louis Ternon, Lucile Saulnier, Marie-Anne Lachaux, Pierre Stock, Teven Le Scao, Théophile Gervet, Thibaut Lavril, Thomas Wang, Timothée Lacroix, William El Sayed. | {"language": ["fr", "it", "de", "es", "en"], "license": "apache-2.0", "inference": {"parameters": {"temperature": 0.5}}, "widget": [{"messages": [{"role": "user", "content": "What is your favorite condiment?"}]}]} | prince-canuma/Mixtral-8x22B-Instruct-v0.1-4bit | null | [
"transformers",
"safetensors",
"mixtral",
"text-generation",
"conversational",
"fr",
"it",
"de",
"es",
"en",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"4-bit",
"region:us"
] | null | 2024-04-17T18:03:46+00:00 | [] | [
"fr",
"it",
"de",
"es",
"en"
] | TAGS
#transformers #safetensors #mixtral #text-generation #conversational #fr #it #de #es #en #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us
| # Model Card for Mixtral-8x22B-Instruct-v0.1-4bit
The Mixtral-8x7B Large Language Model (LLM) is a pretrained generative Sparse Mixture of Experts. The Mixtral-8x7B outperforms Llama 2 70B on most benchmarks we tested.
Model added by Prince Canuma.
For full details of this model please read our release blog post.
## Warning
This repo contains weights that are compatible with vLLM serving of the model as well as Hugging Face transformers library. It is based on the original Mixtral torrent release, but the file format and parameter names are different. Please note that model cannot (yet) be instantiated with HF.
## Instruction format
This format must be strictly respected, otherwise the model will generate sub-optimal outputs.
The template used to build a prompt for the Instruct model is defined as follows:
Note that '<s>' and '</s>' are special tokens for beginning of string (BOS) and end of string (EOS) while [INST] and [/INST] are regular strings.
As reference, here is the pseudo-code used to tokenize instructions during fine-tuning:
In the pseudo-code above, note that the 'tokenize' method should not add a BOS or EOS token automatically, but should add a prefix space.
In the Transformers library, one can use chat templates which make sure the right format is applied.
## Run the model
By default, transformers will load the model in full precision. Therefore you might be interested to further reduce down the memory requirements to run the model through the optimizations we offer in HF ecosystem:
### In half-precision
Note 'float16' precision only works on GPU devices
<details>
<summary> Click to expand </summary>
</details>
### Lower precision using (8-bit & 4-bit) using 'bitsandbytes'
<details>
<summary> Click to expand </summary>
</details>
### Load the model with Flash Attention 2
<details>
<summary> Click to expand </summary>
</details>
## Limitations
The Mixtral-8x7B Instruct model is a quick demonstration that the base model can be easily fine-tuned to achieve compelling performance.
It does not have any moderation mechanisms. We're looking forward to engaging with the community on ways to
make the model finely respect guardrails, allowing for deployment in environments requiring moderated outputs.
# The Mistral AI Team
Albert Jiang, Alexandre Sablayrolles, Arthur Mensch, Blanche Savary, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Emma Bou Hanna, Florian Bressand, Gianna Lengyel, Guillaume Bour, Guillaume Lample, Lélio Renard Lavaud, Louis Ternon, Lucile Saulnier, Marie-Anne Lachaux, Pierre Stock, Teven Le Scao, Théophile Gervet, Thibaut Lavril, Thomas Wang, Timothée Lacroix, William El Sayed. | [
"# Model Card for Mixtral-8x22B-Instruct-v0.1-4bit\nThe Mixtral-8x7B Large Language Model (LLM) is a pretrained generative Sparse Mixture of Experts. The Mixtral-8x7B outperforms Llama 2 70B on most benchmarks we tested.\n\nModel added by Prince Canuma.\n\nFor full details of this model please read our release blog post.",
"## Warning\nThis repo contains weights that are compatible with vLLM serving of the model as well as Hugging Face transformers library. It is based on the original Mixtral torrent release, but the file format and parameter names are different. Please note that model cannot (yet) be instantiated with HF.",
"## Instruction format\n\nThis format must be strictly respected, otherwise the model will generate sub-optimal outputs.\n\nThe template used to build a prompt for the Instruct model is defined as follows:\n\nNote that '<s>' and '</s>' are special tokens for beginning of string (BOS) and end of string (EOS) while [INST] and [/INST] are regular strings.\n\nAs reference, here is the pseudo-code used to tokenize instructions during fine-tuning:\n\n\nIn the pseudo-code above, note that the 'tokenize' method should not add a BOS or EOS token automatically, but should add a prefix space. \n\nIn the Transformers library, one can use chat templates which make sure the right format is applied.",
"## Run the model\n\n\n\nBy default, transformers will load the model in full precision. Therefore you might be interested to further reduce down the memory requirements to run the model through the optimizations we offer in HF ecosystem:",
"### In half-precision\n\nNote 'float16' precision only works on GPU devices\n\n<details>\n<summary> Click to expand </summary>\n\n\n</details>",
"### Lower precision using (8-bit & 4-bit) using 'bitsandbytes'\n\n<details>\n<summary> Click to expand </summary>\n\n\n</details>",
"### Load the model with Flash Attention 2\n\n<details>\n<summary> Click to expand </summary>\n\n\n</details>",
"## Limitations\n\nThe Mixtral-8x7B Instruct model is a quick demonstration that the base model can be easily fine-tuned to achieve compelling performance. \nIt does not have any moderation mechanisms. We're looking forward to engaging with the community on ways to\nmake the model finely respect guardrails, allowing for deployment in environments requiring moderated outputs.",
"# The Mistral AI Team\nAlbert Jiang, Alexandre Sablayrolles, Arthur Mensch, Blanche Savary, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Emma Bou Hanna, Florian Bressand, Gianna Lengyel, Guillaume Bour, Guillaume Lample, Lélio Renard Lavaud, Louis Ternon, Lucile Saulnier, Marie-Anne Lachaux, Pierre Stock, Teven Le Scao, Théophile Gervet, Thibaut Lavril, Thomas Wang, Timothée Lacroix, William El Sayed."
] | [
"TAGS\n#transformers #safetensors #mixtral #text-generation #conversational #fr #it #de #es #en #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us \n",
"# Model Card for Mixtral-8x22B-Instruct-v0.1-4bit\nThe Mixtral-8x7B Large Language Model (LLM) is a pretrained generative Sparse Mixture of Experts. The Mixtral-8x7B outperforms Llama 2 70B on most benchmarks we tested.\n\nModel added by Prince Canuma.\n\nFor full details of this model please read our release blog post.",
"## Warning\nThis repo contains weights that are compatible with vLLM serving of the model as well as Hugging Face transformers library. It is based on the original Mixtral torrent release, but the file format and parameter names are different. Please note that model cannot (yet) be instantiated with HF.",
"## Instruction format\n\nThis format must be strictly respected, otherwise the model will generate sub-optimal outputs.\n\nThe template used to build a prompt for the Instruct model is defined as follows:\n\nNote that '<s>' and '</s>' are special tokens for beginning of string (BOS) and end of string (EOS) while [INST] and [/INST] are regular strings.\n\nAs reference, here is the pseudo-code used to tokenize instructions during fine-tuning:\n\n\nIn the pseudo-code above, note that the 'tokenize' method should not add a BOS or EOS token automatically, but should add a prefix space. \n\nIn the Transformers library, one can use chat templates which make sure the right format is applied.",
"## Run the model\n\n\n\nBy default, transformers will load the model in full precision. Therefore you might be interested to further reduce down the memory requirements to run the model through the optimizations we offer in HF ecosystem:",
"### In half-precision\n\nNote 'float16' precision only works on GPU devices\n\n<details>\n<summary> Click to expand </summary>\n\n\n</details>",
"### Lower precision using (8-bit & 4-bit) using 'bitsandbytes'\n\n<details>\n<summary> Click to expand </summary>\n\n\n</details>",
"### Load the model with Flash Attention 2\n\n<details>\n<summary> Click to expand </summary>\n\n\n</details>",
"## Limitations\n\nThe Mixtral-8x7B Instruct model is a quick demonstration that the base model can be easily fine-tuned to achieve compelling performance. \nIt does not have any moderation mechanisms. We're looking forward to engaging with the community on ways to\nmake the model finely respect guardrails, allowing for deployment in environments requiring moderated outputs.",
"# The Mistral AI Team\nAlbert Jiang, Alexandre Sablayrolles, Arthur Mensch, Blanche Savary, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Emma Bou Hanna, Florian Bressand, Gianna Lengyel, Guillaume Bour, Guillaume Lample, Lélio Renard Lavaud, Louis Ternon, Lucile Saulnier, Marie-Anne Lachaux, Pierre Stock, Teven Le Scao, Théophile Gervet, Thibaut Lavril, Thomas Wang, Timothée Lacroix, William El Sayed."
] |
text-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": []} | tomaszki/mistral-35-a | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-04-17T18:06:25+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #safetensors #llama #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
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:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
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.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
| [
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] | [
"TAGS\n#transformers #safetensors #llama #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
null | 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": []} | Enagamirzayev/whisper-small-llm-lingo-adapters_o | null | [
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2024-04-17T18:06:37+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
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:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
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.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
| [
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] | [
"TAGS\n#transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
text-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": []} | bogdanfloris/Mistral-7B-v0.1-4bit | null | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"4-bit",
"region:us"
] | null | 2024-04-17T18:07:02+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #safetensors #mistral #text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
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:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
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.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
| [
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] | [
"TAGS\n#transformers #safetensors #mistral #text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
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. -->
# Whisper Small ZIB2
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the ZIB2 Common Voice dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3366
- Wer: 28.9384
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 1000
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
| 0.2391 | 10.0 | 100 | 0.2837 | 33.5616 |
| 0.0035 | 20.0 | 200 | 0.2701 | 27.7397 |
| 0.0012 | 30.0 | 300 | 0.2847 | 27.5685 |
| 0.0006 | 40.0 | 400 | 0.2990 | 27.9110 |
| 0.0004 | 50.0 | 500 | 0.3118 | 28.5959 |
| 0.0003 | 60.0 | 600 | 0.3221 | 28.5959 |
| 0.0002 | 70.0 | 700 | 0.3287 | 28.7671 |
| 0.0002 | 80.0 | 800 | 0.3333 | 28.9384 |
| 0.0002 | 90.0 | 900 | 0.3357 | 28.9384 |
| 0.0002 | 100.0 | 1000 | 0.3366 | 28.9384 |
### Framework versions
- Transformers 4.39.3
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
| {"language": ["de"], "license": "apache-2.0", "tags": ["generated_from_trainer"], "datasets": ["rmacek/common_voice_zib2"], "metrics": ["wer"], "base_model": "openai/whisper-small", "model-index": [{"name": "Whisper Small ZIB2", "results": [{"task": {"type": "automatic-speech-recognition", "name": "Automatic Speech Recognition"}, "dataset": {"name": "ZIB2 Common Voice", "type": "rmacek/common_voice_zib2", "args": "config: de, split: test"}, "metrics": [{"type": "wer", "value": 28.93835616438356, "name": "Wer"}]}]}]} | rmacek/whisper-small-de | null | [
"transformers",
"tensorboard",
"safetensors",
"whisper",
"automatic-speech-recognition",
"generated_from_trainer",
"de",
"dataset:rmacek/common_voice_zib2",
"base_model:openai/whisper-small",
"license:apache-2.0",
"model-index",
"endpoints_compatible",
"region:us"
] | null | 2024-04-17T18:08:52+00:00 | [] | [
"de"
] | TAGS
#transformers #tensorboard #safetensors #whisper #automatic-speech-recognition #generated_from_trainer #de #dataset-rmacek/common_voice_zib2 #base_model-openai/whisper-small #license-apache-2.0 #model-index #endpoints_compatible #region-us
| Whisper Small ZIB2
==================
This model is a fine-tuned version of openai/whisper-small on the ZIB2 Common Voice dataset.
It achieves the following results on the evaluation set:
* Loss: 0.3366
* Wer: 28.9384
Model description
-----------------
More information needed
Intended uses & limitations
---------------------------
More information needed
Training and evaluation data
----------------------------
More information needed
Training procedure
------------------
### Training hyperparameters
The following hyperparameters were used during training:
* learning\_rate: 1e-05
* train\_batch\_size: 16
* eval\_batch\_size: 8
* seed: 42
* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
* lr\_scheduler\_type: linear
* lr\_scheduler\_warmup\_steps: 500
* training\_steps: 1000
* mixed\_precision\_training: Native AMP
### Training results
### Framework versions
* Transformers 4.39.3
* Pytorch 2.2.1+cu121
* Datasets 2.18.0
* Tokenizers 0.15.2
| [
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 1e-05\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_steps: 500\n* training\\_steps: 1000\n* mixed\\_precision\\_training: Native AMP",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.39.3\n* Pytorch 2.2.1+cu121\n* Datasets 2.18.0\n* Tokenizers 0.15.2"
] | [
"TAGS\n#transformers #tensorboard #safetensors #whisper #automatic-speech-recognition #generated_from_trainer #de #dataset-rmacek/common_voice_zib2 #base_model-openai/whisper-small #license-apache-2.0 #model-index #endpoints_compatible #region-us \n",
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 1e-05\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_steps: 500\n* training\\_steps: 1000\n* mixed\\_precision\\_training: Native AMP",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.39.3\n* Pytorch 2.2.1+cu121\n* Datasets 2.18.0\n* Tokenizers 0.15.2"
] |
reinforcement-learning | ml-agents |
# **ppo** Agent playing **Huggy**
This is a trained model of a **ppo** agent playing **Huggy**
using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
## Usage (with ML-Agents)
The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
- A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
- A *longer tutorial* to understand how works ML-Agents:
https://huggingface.co/learn/deep-rl-course/unit5/introduction
### Resume the training
```bash
mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
```
### Watch your Agent play
You can watch your agent **playing directly in your browser**
1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
2. Step 1: Find your model_id: moczard/ppo-Huggy
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
| {"library_name": "ml-agents", "tags": ["Huggy", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-Huggy"]} | moczard/ppo-Huggy | null | [
"ml-agents",
"tensorboard",
"onnx",
"Huggy",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-Huggy",
"region:us"
] | null | 2024-04-17T18:09:12+00:00 | [] | [] | TAGS
#ml-agents #tensorboard #onnx #Huggy #deep-reinforcement-learning #reinforcement-learning #ML-Agents-Huggy #region-us
|
# ppo Agent playing Huggy
This is a trained model of a ppo agent playing Huggy
using the Unity ML-Agents Library.
## Usage (with ML-Agents)
The Documentation: URL
We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
- A *short tutorial* where you teach Huggy the Dog to fetch the stick and then play with him directly in your
browser: URL
- A *longer tutorial* to understand how works ML-Agents:
URL
### Resume the training
### Watch your Agent play
You can watch your agent playing directly in your browser
1. If the environment is part of ML-Agents official environments, go to URL
2. Step 1: Find your model_id: moczard/ppo-Huggy
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play
| [
"# ppo Agent playing Huggy\n This is a trained model of a ppo agent playing Huggy\n using the Unity ML-Agents Library.\n\n ## Usage (with ML-Agents)\n The Documentation: URL\n\n We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:\n - A *short tutorial* where you teach Huggy the Dog to fetch the stick and then play with him directly in your\n browser: URL\n - A *longer tutorial* to understand how works ML-Agents:\n URL\n\n ### Resume the training\n \n\n ### Watch your Agent play\n You can watch your agent playing directly in your browser\n\n 1. If the environment is part of ML-Agents official environments, go to URL\n 2. Step 1: Find your model_id: moczard/ppo-Huggy\n 3. Step 2: Select your *.nn /*.onnx file\n 4. Click on Watch the agent play"
] | [
"TAGS\n#ml-agents #tensorboard #onnx #Huggy #deep-reinforcement-learning #reinforcement-learning #ML-Agents-Huggy #region-us \n",
"# ppo Agent playing Huggy\n This is a trained model of a ppo agent playing Huggy\n using the Unity ML-Agents Library.\n\n ## Usage (with ML-Agents)\n The Documentation: URL\n\n We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:\n - A *short tutorial* where you teach Huggy the Dog to fetch the stick and then play with him directly in your\n browser: URL\n - A *longer tutorial* to understand how works ML-Agents:\n URL\n\n ### Resume the training\n \n\n ### Watch your Agent play\n You can watch your agent playing directly in your browser\n\n 1. If the environment is part of ML-Agents official environments, go to URL\n 2. Step 1: Find your model_id: moczard/ppo-Huggy\n 3. Step 2: Select your *.nn /*.onnx file\n 4. Click on Watch the agent play"
] |
null | peft | ## Training procedure
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- _load_in_8bit: False
- _load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: float16
- bnb_4bit_quant_storage: uint8
- load_in_4bit: True
- load_in_8bit: False
### Framework versions
- PEFT 0.5.0
# Open Portuguese LLM Leaderboard Evaluation Results
Detailed results can be found [here](https://huggingface.co/datasets/eduagarcia-temp/llm_pt_leaderboard_raw_results/tree/main/recogna-nlp/gembode-2b-base-ultraalpaca-qlora) and on the [🚀 Open Portuguese LLM Leaderboard](https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard)
| Metric | Value |
|--------------------------|--------|
|Average |**32.3**|
|ENEM Challenge (No Images)| 24.14|
|BLUEX (No Images) | 20.31|
|OAB Exams | 25.56|
|Assin2 RTE | 69.75|
|Assin2 STS | 4.16|
|FaQuAD NLI | 52.63|
|HateBR Binary | 33.33|
|PT Hate Speech Binary | 41.65|
|tweetSentBR | 19.15|
| {"library_name": "peft", "model-index": [{"name": "gembode-2b-base-ultraalpaca-qlora", "results": [{"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "ENEM Challenge (No Images)", "type": "eduagarcia/enem_challenge", "split": "train", "args": {"num_few_shot": 3}}, "metrics": [{"type": "acc", "value": 24.14, "name": "accuracy"}], "source": {"url": "https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=recogna-nlp/gembode-2b-base-ultraalpaca-qlora", "name": "Open Portuguese LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "BLUEX (No Images)", "type": "eduagarcia-temp/BLUEX_without_images", "split": "train", "args": {"num_few_shot": 3}}, "metrics": [{"type": "acc", "value": 20.31, "name": "accuracy"}], "source": {"url": "https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=recogna-nlp/gembode-2b-base-ultraalpaca-qlora", "name": "Open Portuguese LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "OAB Exams", "type": "eduagarcia/oab_exams", "split": "train", "args": {"num_few_shot": 3}}, "metrics": [{"type": "acc", "value": 25.56, "name": "accuracy"}], "source": {"url": "https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=recogna-nlp/gembode-2b-base-ultraalpaca-qlora", "name": "Open Portuguese LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "Assin2 RTE", "type": "assin2", "split": "test", "args": {"num_few_shot": 15}}, "metrics": [{"type": "f1_macro", "value": 69.75, "name": "f1-macro"}], "source": {"url": "https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=recogna-nlp/gembode-2b-base-ultraalpaca-qlora", "name": "Open Portuguese LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "Assin2 STS", "type": "eduagarcia/portuguese_benchmark", "split": "test", "args": {"num_few_shot": 15}}, "metrics": [{"type": "pearson", "value": 4.16, "name": "pearson"}], "source": {"url": "https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=recogna-nlp/gembode-2b-base-ultraalpaca-qlora", "name": "Open Portuguese LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "FaQuAD NLI", "type": "ruanchaves/faquad-nli", "split": "test", "args": {"num_few_shot": 15}}, "metrics": [{"type": "f1_macro", "value": 52.63, "name": "f1-macro"}], "source": {"url": "https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=recogna-nlp/gembode-2b-base-ultraalpaca-qlora", "name": "Open Portuguese LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "HateBR Binary", "type": "ruanchaves/hatebr", "split": "test", "args": {"num_few_shot": 25}}, "metrics": [{"type": "f1_macro", "value": 33.33, "name": "f1-macro"}], "source": {"url": "https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=recogna-nlp/gembode-2b-base-ultraalpaca-qlora", "name": "Open Portuguese LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "PT Hate Speech Binary", "type": "hate_speech_portuguese", "split": "test", "args": {"num_few_shot": 25}}, "metrics": [{"type": "f1_macro", "value": 41.65, "name": "f1-macro"}], "source": {"url": "https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=recogna-nlp/gembode-2b-base-ultraalpaca-qlora", "name": "Open Portuguese LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "tweetSentBR", "type": "eduagarcia/tweetsentbr_fewshot", "split": "test", "args": {"num_few_shot": 25}}, "metrics": [{"type": "f1_macro", "value": 19.15, "name": "f1-macro"}], "source": {"url": "https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=recogna-nlp/gembode-2b-base-ultraalpaca-qlora", "name": "Open Portuguese LLM Leaderboard"}}]}]} | recogna-nlp/gembode-2b-base-ultraalpaca-qlora | null | [
"peft",
"model-index",
"has_space",
"region:us"
] | null | 2024-04-17T18:09:20+00:00 | [] | [] | TAGS
#peft #model-index #has_space #region-us
| Training procedure
------------------
The following 'bitsandbytes' quantization config was used during training:
* quant\_method: bitsandbytes
* \_load\_in\_8bit: False
* \_load\_in\_4bit: True
* llm\_int8\_threshold: 6.0
* llm\_int8\_skip\_modules: None
* llm\_int8\_enable\_fp32\_cpu\_offload: False
* llm\_int8\_has\_fp16\_weight: False
* bnb\_4bit\_quant\_type: nf4
* bnb\_4bit\_use\_double\_quant: True
* bnb\_4bit\_compute\_dtype: float16
* bnb\_4bit\_quant\_storage: uint8
* load\_in\_4bit: True
* load\_in\_8bit: False
### Framework versions
* PEFT 0.5.0
Open Portuguese LLM Leaderboard Evaluation Results
==================================================
Detailed results can be found here and on the Open Portuguese LLM Leaderboard
| [
"### Framework versions\n\n\n* PEFT 0.5.0\n\n\nOpen Portuguese LLM Leaderboard Evaluation Results\n==================================================\n\n\nDetailed results can be found here and on the Open Portuguese LLM Leaderboard"
] | [
"TAGS\n#peft #model-index #has_space #region-us \n",
"### Framework versions\n\n\n* PEFT 0.5.0\n\n\nOpen Portuguese LLM Leaderboard Evaluation Results\n==================================================\n\n\nDetailed results can be found here and on the Open Portuguese LLM Leaderboard"
] |
null | peft | ## Training procedure
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- _load_in_8bit: False
- _load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: float16
- bnb_4bit_quant_storage: uint8
- load_in_4bit: True
- load_in_8bit: False
### Framework versions
- PEFT 0.5.0
| {"library_name": "peft"} | recogna-nlp/qwenbode_1_8b_chat_ultraalpaca | null | [
"peft",
"pytorch",
"qwen2",
"has_space",
"region:us"
] | null | 2024-04-17T18:10:14+00:00 | [] | [] | TAGS
#peft #pytorch #qwen2 #has_space #region-us
| ## Training procedure
The following 'bitsandbytes' quantization config was used during training:
- quant_method: bitsandbytes
- _load_in_8bit: False
- _load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: float16
- bnb_4bit_quant_storage: uint8
- load_in_4bit: True
- load_in_8bit: False
### Framework versions
- PEFT 0.5.0
| [
"## Training procedure\n\n\nThe following 'bitsandbytes' quantization config was used during training:\n- quant_method: bitsandbytes\n- _load_in_8bit: False\n- _load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: True\n- bnb_4bit_compute_dtype: float16\n- bnb_4bit_quant_storage: uint8\n- load_in_4bit: True\n- load_in_8bit: False",
"### Framework versions\n\n\n- PEFT 0.5.0"
] | [
"TAGS\n#peft #pytorch #qwen2 #has_space #region-us \n",
"## Training procedure\n\n\nThe following 'bitsandbytes' quantization config was used during training:\n- quant_method: bitsandbytes\n- _load_in_8bit: False\n- _load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: True\n- bnb_4bit_compute_dtype: float16\n- bnb_4bit_quant_storage: uint8\n- load_in_4bit: True\n- load_in_8bit: False",
"### Framework versions\n\n\n- PEFT 0.5.0"
] |
null | peft | ## Training procedure
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- _load_in_8bit: False
- _load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: float16
- bnb_4bit_quant_storage: uint8
- load_in_4bit: True
- load_in_8bit: False
### Framework versions
- PEFT 0.5.0
# Open Portuguese LLM Leaderboard Evaluation Results
Detailed results can be found [here](https://huggingface.co/datasets/eduagarcia-temp/llm_pt_leaderboard_raw_results/tree/main/recogna-nlp/qwenbode_1_8b_chat_ultraalpaca_qlora) and on the [🚀 Open Portuguese LLM Leaderboard](https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard)
| Metric | Value |
|--------------------------|---------|
|Average |**33.68**|
|ENEM Challenge (No Images)| 31.21|
|BLUEX (No Images) | 26.01|
|OAB Exams | 26.20|
|Assin2 RTE | 40.52|
|Assin2 STS | 4.64|
|FaQuAD NLI | 32.15|
|HateBR Binary | 60.10|
|PT Hate Speech Binary | 54.14|
|tweetSentBR | 28.18|
| {"library_name": "peft", "model-index": [{"name": "qwenbode_1_8b_chat_ultraalpaca_qlora", "results": [{"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "ENEM Challenge (No Images)", "type": "eduagarcia/enem_challenge", "split": "train", "args": {"num_few_shot": 3}}, "metrics": [{"type": "acc", "value": 31.21, "name": "accuracy"}], "source": {"url": "https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=recogna-nlp/qwenbode_1_8b_chat_ultraalpaca_qlora", "name": "Open Portuguese LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "BLUEX (No Images)", "type": "eduagarcia-temp/BLUEX_without_images", "split": "train", "args": {"num_few_shot": 3}}, "metrics": [{"type": "acc", "value": 26.01, "name": "accuracy"}], "source": {"url": "https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=recogna-nlp/qwenbode_1_8b_chat_ultraalpaca_qlora", "name": "Open Portuguese LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "OAB Exams", "type": "eduagarcia/oab_exams", "split": "train", "args": {"num_few_shot": 3}}, "metrics": [{"type": "acc", "value": 26.2, "name": "accuracy"}], "source": {"url": "https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=recogna-nlp/qwenbode_1_8b_chat_ultraalpaca_qlora", "name": "Open Portuguese LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "Assin2 RTE", "type": "assin2", "split": "test", "args": {"num_few_shot": 15}}, "metrics": [{"type": "f1_macro", "value": 40.52, "name": "f1-macro"}], "source": {"url": "https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=recogna-nlp/qwenbode_1_8b_chat_ultraalpaca_qlora", "name": "Open Portuguese LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "Assin2 STS", "type": "eduagarcia/portuguese_benchmark", "split": "test", "args": {"num_few_shot": 15}}, "metrics": [{"type": "pearson", "value": 4.64, "name": "pearson"}], "source": {"url": "https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=recogna-nlp/qwenbode_1_8b_chat_ultraalpaca_qlora", "name": "Open Portuguese LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "FaQuAD NLI", "type": "ruanchaves/faquad-nli", "split": "test", "args": {"num_few_shot": 15}}, "metrics": [{"type": "f1_macro", "value": 32.15, "name": "f1-macro"}], "source": {"url": "https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=recogna-nlp/qwenbode_1_8b_chat_ultraalpaca_qlora", "name": "Open Portuguese LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "HateBR Binary", "type": "ruanchaves/hatebr", "split": "test", "args": {"num_few_shot": 25}}, "metrics": [{"type": "f1_macro", "value": 60.1, "name": "f1-macro"}], "source": {"url": "https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=recogna-nlp/qwenbode_1_8b_chat_ultraalpaca_qlora", "name": "Open Portuguese LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "PT Hate Speech Binary", "type": "hate_speech_portuguese", "split": "test", "args": {"num_few_shot": 25}}, "metrics": [{"type": "f1_macro", "value": 54.14, "name": "f1-macro"}], "source": {"url": "https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=recogna-nlp/qwenbode_1_8b_chat_ultraalpaca_qlora", "name": "Open Portuguese LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "tweetSentBR", "type": "eduagarcia/tweetsentbr_fewshot", "split": "test", "args": {"num_few_shot": 25}}, "metrics": [{"type": "f1_macro", "value": 28.18, "name": "f1-macro"}], "source": {"url": "https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=recogna-nlp/qwenbode_1_8b_chat_ultraalpaca_qlora", "name": "Open Portuguese LLM Leaderboard"}}]}]} | recogna-nlp/qwenbode_1_8b_chat_ultraalpaca_qlora | null | [
"peft",
"model-index",
"has_space",
"region:us"
] | null | 2024-04-17T18:10:30+00:00 | [] | [] | TAGS
#peft #model-index #has_space #region-us
| Training procedure
------------------
The following 'bitsandbytes' quantization config was used during training:
* quant\_method: bitsandbytes
* \_load\_in\_8bit: False
* \_load\_in\_4bit: True
* llm\_int8\_threshold: 6.0
* llm\_int8\_skip\_modules: None
* llm\_int8\_enable\_fp32\_cpu\_offload: False
* llm\_int8\_has\_fp16\_weight: False
* bnb\_4bit\_quant\_type: nf4
* bnb\_4bit\_use\_double\_quant: True
* bnb\_4bit\_compute\_dtype: float16
* bnb\_4bit\_quant\_storage: uint8
* load\_in\_4bit: True
* load\_in\_8bit: False
### Framework versions
* PEFT 0.5.0
Open Portuguese LLM Leaderboard Evaluation Results
==================================================
Detailed results can be found here and on the Open Portuguese LLM Leaderboard
| [
"### Framework versions\n\n\n* PEFT 0.5.0\n\n\nOpen Portuguese LLM Leaderboard Evaluation Results\n==================================================\n\n\nDetailed results can be found here and on the Open Portuguese LLM Leaderboard"
] | [
"TAGS\n#peft #model-index #has_space #region-us \n",
"### Framework versions\n\n\n* PEFT 0.5.0\n\n\nOpen Portuguese LLM Leaderboard Evaluation Results\n==================================================\n\n\nDetailed results can be found here and on the Open Portuguese LLM Leaderboard"
] |
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": []} | Enagamirzayev/whisper-small-llm-lingo_o | null | [
"transformers",
"safetensors",
"whisper",
"automatic-speech-recognition",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2024-04-17T18:11:08+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #safetensors #whisper #automatic-speech-recognition #arxiv-1910.09700 #endpoints_compatible #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
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:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
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.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
| [
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] | [
"TAGS\n#transformers #safetensors #whisper #automatic-speech-recognition #arxiv-1910.09700 #endpoints_compatible #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
text-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": []} | indiana500/gpt2-implicit-fine-tuned-classification | null | [
"transformers",
"safetensors",
"gpt2",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-04-17T18:12:19+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #safetensors #gpt2 #text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
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:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
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.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
| [
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] | [
"TAGS\n#transformers #safetensors #gpt2 #text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
null | 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": []} | Julesb5/gemma-7b-it-med1 | null | [
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2024-04-17T18:13:22+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
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:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
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.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
| [
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] | [
"TAGS\n#transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
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. -->
# mbart-Math_problems
This model is a fine-tuned version of [facebook/mbart-large-50](https://huggingface.co/facebook/mbart-large-50) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.9236
- Bleu: 28.8931
- Gen Len: 87.5959
## 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: 5.6e-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: 2
### Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
| 1.4784 | 1.0 | 935 | 1.0135 | 25.551 | 83.9826 |
| 0.7957 | 2.0 | 1870 | 0.9236 | 28.8931 | 87.5959 |
### Framework versions
- Transformers 4.39.3
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
| {"license": "mit", "tags": ["generated_from_trainer"], "metrics": ["bleu"], "base_model": "facebook/mbart-large-50", "model-index": [{"name": "mbart-Math_problems", "results": []}]} | LuisCe/mbart-Math_problems | null | [
"transformers",
"tensorboard",
"safetensors",
"mbart",
"text2text-generation",
"generated_from_trainer",
"base_model:facebook/mbart-large-50",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"has_space",
"region:us"
] | null | 2024-04-17T18:16:55+00:00 | [] | [] | TAGS
#transformers #tensorboard #safetensors #mbart #text2text-generation #generated_from_trainer #base_model-facebook/mbart-large-50 #license-mit #autotrain_compatible #endpoints_compatible #has_space #region-us
| mbart-Math\_problems
====================
This model is a fine-tuned version of facebook/mbart-large-50 on an unknown dataset.
It achieves the following results on the evaluation set:
* Loss: 0.9236
* Bleu: 28.8931
* Gen Len: 87.5959
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: 5.6e-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: 2
### Training results
### Framework versions
* Transformers 4.39.3
* Pytorch 2.2.1+cu121
* Datasets 2.18.0
* Tokenizers 0.15.2
| [
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 5.6e-05\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 2",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.39.3\n* Pytorch 2.2.1+cu121\n* Datasets 2.18.0\n* Tokenizers 0.15.2"
] | [
"TAGS\n#transformers #tensorboard #safetensors #mbart #text2text-generation #generated_from_trainer #base_model-facebook/mbart-large-50 #license-mit #autotrain_compatible #endpoints_compatible #has_space #region-us \n",
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 5.6e-05\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 2",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.39.3\n* Pytorch 2.2.1+cu121\n* Datasets 2.18.0\n* Tokenizers 0.15.2"
] |
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. -->
# model_hh_shp4_200
This model is a fine-tuned version of [meta-llama/Llama-2-7b-chat-hf](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.4445
- Rewards/chosen: -0.1401
- Rewards/rejected: -1.3796
- Rewards/accuracies: 0.6300
- Rewards/margins: 1.2395
- Logps/rejected: -230.1749
- Logps/chosen: -224.4940
- Logits/rejected: -0.7701
- Logits/chosen: -0.7769
## 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: 4
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- training_steps: 1000
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
| 0.0 | 8.0 | 100 | 1.4330 | -0.1080 | -1.3964 | 0.6200 | 1.2883 | -230.1935 | -224.4584 | -0.7684 | -0.7753 |
| 0.0 | 16.0 | 200 | 1.4371 | -0.0911 | -1.3887 | 0.6400 | 1.2976 | -230.1849 | -224.4396 | -0.7692 | -0.7762 |
| 0.0 | 24.0 | 300 | 1.4477 | -0.1125 | -1.3921 | 0.6200 | 1.2795 | -230.1887 | -224.4634 | -0.7693 | -0.7763 |
| 0.0 | 32.0 | 400 | 1.4521 | -0.1143 | -1.4167 | 0.6200 | 1.3024 | -230.2161 | -224.4653 | -0.7696 | -0.7763 |
| 0.0 | 40.0 | 500 | 1.4631 | -0.1153 | -1.3806 | 0.6200 | 1.2653 | -230.1759 | -224.4665 | -0.7701 | -0.7771 |
| 0.0 | 48.0 | 600 | 1.4455 | -0.1180 | -1.3970 | 0.6300 | 1.2791 | -230.1942 | -224.4695 | -0.7698 | -0.7769 |
| 0.0 | 56.0 | 700 | 1.4292 | -0.0800 | -1.3720 | 0.6100 | 1.2920 | -230.1664 | -224.4273 | -0.7704 | -0.7775 |
| 0.0 | 64.0 | 800 | 1.4434 | -0.0943 | -1.3739 | 0.6200 | 1.2796 | -230.1686 | -224.4432 | -0.7703 | -0.7773 |
| 0.0 | 72.0 | 900 | 1.4493 | -0.1016 | -1.4044 | 0.6100 | 1.3028 | -230.2024 | -224.4513 | -0.7704 | -0.7773 |
| 0.0 | 80.0 | 1000 | 1.4445 | -0.1401 | -1.3796 | 0.6300 | 1.2395 | -230.1749 | -224.4940 | -0.7701 | -0.7769 |
### Framework versions
- PEFT 0.10.0
- Transformers 4.39.1
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2 | {"license": "llama2", "library_name": "peft", "tags": ["trl", "dpo", "generated_from_trainer"], "base_model": "meta-llama/Llama-2-7b-chat-hf", "model-index": [{"name": "model_hh_shp4_200", "results": []}]} | guoyu-zhang/model_hh_shp4_200 | null | [
"peft",
"safetensors",
"trl",
"dpo",
"generated_from_trainer",
"base_model:meta-llama/Llama-2-7b-chat-hf",
"license:llama2",
"region:us"
] | null | 2024-04-17T18:17:11+00:00 | [] | [] | TAGS
#peft #safetensors #trl #dpo #generated_from_trainer #base_model-meta-llama/Llama-2-7b-chat-hf #license-llama2 #region-us
| model\_hh\_shp4\_200
====================
This model is a fine-tuned version of meta-llama/Llama-2-7b-chat-hf on an unknown dataset.
It achieves the following results on the evaluation set:
* Loss: 1.4445
* Rewards/chosen: -0.1401
* Rewards/rejected: -1.3796
* Rewards/accuracies: 0.6300
* Rewards/margins: 1.2395
* Logps/rejected: -230.1749
* Logps/chosen: -224.4940
* Logits/rejected: -0.7701
* Logits/chosen: -0.7769
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: 4
* eval\_batch\_size: 1
* seed: 42
* gradient\_accumulation\_steps: 4
* total\_train\_batch\_size: 16
* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
* lr\_scheduler\_type: cosine
* lr\_scheduler\_warmup\_steps: 100
* training\_steps: 1000
### Training results
### Framework versions
* PEFT 0.10.0
* Transformers 4.39.1
* Pytorch 2.2.1+cu121
* Datasets 2.18.0
* Tokenizers 0.15.2
| [
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 4\n* eval\\_batch\\_size: 1\n* seed: 42\n* gradient\\_accumulation\\_steps: 4\n* total\\_train\\_batch\\_size: 16\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: cosine\n* lr\\_scheduler\\_warmup\\_steps: 100\n* training\\_steps: 1000",
"### Training results",
"### Framework versions\n\n\n* PEFT 0.10.0\n* Transformers 4.39.1\n* Pytorch 2.2.1+cu121\n* Datasets 2.18.0\n* Tokenizers 0.15.2"
] | [
"TAGS\n#peft #safetensors #trl #dpo #generated_from_trainer #base_model-meta-llama/Llama-2-7b-chat-hf #license-llama2 #region-us \n",
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 4\n* eval\\_batch\\_size: 1\n* seed: 42\n* gradient\\_accumulation\\_steps: 4\n* total\\_train\\_batch\\_size: 16\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: cosine\n* lr\\_scheduler\\_warmup\\_steps: 100\n* training\\_steps: 1000",
"### Training results",
"### Framework versions\n\n\n* PEFT 0.10.0\n* Transformers 4.39.1\n* Pytorch 2.2.1+cu121\n* Datasets 2.18.0\n* Tokenizers 0.15.2"
] |
null | 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": []} | morioxd/happymakerai_v3 | null | [
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2024-04-17T18:17:12+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
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:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
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.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
| [
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] | [
"TAGS\n#transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
null | transformers |
# MeloTTS
MeloTTS is a **high-quality multi-lingual** text-to-speech library by [MyShell.ai](https://myshell.ai). Supported languages include:
| Model card | Example |
| --- | --- |
| [English](https://huggingface.co/myshell-ai/MeloTTS-English-v2) (American) | [Link](https://myshell-public-repo-hosting.s3.amazonaws.com/myshellttsbase/examples/en/EN-US/speed_1.0/sent_000.wav) |
| [English](https://huggingface.co/myshell-ai/MeloTTS-English-v2) (British) | [Link](https://myshell-public-repo-hosting.s3.amazonaws.com/myshellttsbase/examples/en/EN-BR/speed_1.0/sent_000.wav) |
| [English](https://huggingface.co/myshell-ai/MeloTTS-English-v2) (Indian) | [Link](https://myshell-public-repo-hosting.s3.amazonaws.com/myshellttsbase/examples/en/EN_INDIA/speed_1.0/sent_000.wav) |
| [English](https://huggingface.co/myshell-ai/MeloTTS-English-v2) (Australian) | [Link](https://myshell-public-repo-hosting.s3.amazonaws.com/myshellttsbase/examples/en/EN-AU/speed_1.0/sent_000.wav) |
| [English](https://huggingface.co/myshell-ai/MeloTTS-English-v2) (Default) | [Link](https://myshell-public-repo-hosting.s3.amazonaws.com/myshellttsbase/examples/en/EN-Default/speed_1.0/sent_000.wav) |
| [Spanish](https://huggingface.co/myshell-ai/MeloTTS-Spanish) | [Link](https://myshell-public-repo-hosting.s3.amazonaws.com/myshellttsbase/examples/es/ES/speed_1.0/sent_000.wav) |
| [French](https://huggingface.co/myshell-ai/MeloTTS-French) | [Link](https://myshell-public-repo-hosting.s3.amazonaws.com/myshellttsbase/examples/fr/FR/speed_1.0/sent_000.wav) |
| [Chinese](https://huggingface.co/myshell-ai/MeloTTS-Chinese) (mix EN) | [Link](https://myshell-public-repo-hosting.s3.amazonaws.com/myshellttsbase/examples/zh/ZH/speed_1.0/sent_008.wav) |
| [Japanese](https://huggingface.co/myshell-ai/MeloTTS-Japanese) | [Link](https://myshell-public-repo-hosting.s3.amazonaws.com/myshellttsbase/examples/jp/JP/speed_1.0/sent_000.wav) |
| [Korean](https://huggingface.co/myshell-ai/MeloTTS-Korean/) | [Link](https://myshell-public-repo-hosting.s3.amazonaws.com/myshellttsbase/examples/kr/KR/speed_1.0/sent_000.wav) |
Some other features include:
- The Chinese speaker supports `mixed Chinese and English`.
- Fast enough for `CPU real-time inference`.
## Usage
### Without Installation
An unofficial [live demo](https://huggingface.co/spaces/mrfakename/MeloTTS) is hosted on Hugging Face Spaces.
#### Use it on MyShell
There are hundreds of TTS models on MyShell, much more than MeloTTS. See examples [here](https://github.com/myshell-ai/MeloTTS/blob/main/docs/quick_use.md#use-melotts-without-installation).
More can be found at the widget center of [MyShell.ai](https://app.myshell.ai/robot-workshop).
### Install and Use Locally
Follow the installation steps [here](https://github.com/myshell-ai/MeloTTS/blob/main/docs/install.md#linux-and-macos-install) before using the following snippet:
```python
from melo.api import TTS
# Speed is adjustable
speed = 1.0
# CPU is sufficient for real-time inference.
# You can set it manually to 'cpu' or 'cuda' or 'cuda:0' or 'mps'
device = 'auto' # Will automatically use GPU if available
# English
text = "Did you ever hear a folk tale about a giant turtle?"
model = TTS(language='EN_NEWEST', device=device)
speaker_ids = model.hps.data.spk2id
output_path = 'en-newest.wav'
model.tts_to_file(text, speaker_ids['EN-Newest'], output_path, speed=speed)
```
## Join the Community
**Open Source AI Grant**
We are actively sponsoring open-source AI projects. The sponsorship includes GPU resources, fundings and intellectual support (collaboration with top research labs). We welcome both reseach and engineering projects, as long as the open-source community needs them. Please contact [Zengyi Qin](https://www.qinzy.tech/) if you are interested.
**Contributing**
If you find this work useful, please consider contributing to the GitHub [repo](https://github.com/myshell-ai/MeloTTS).
- Many thanks to [@fakerybakery](https://github.com/fakerybakery) for adding the Web UI and CLI part.
## License
This library is under MIT License, which means it is free for both commercial and non-commercial use.
## Acknowledgements
This implementation is based on [TTS](https://github.com/coqui-ai/TTS), [VITS](https://github.com/jaywalnut310/vits), [VITS2](https://github.com/daniilrobnikov/vits2) and [Bert-VITS2](https://github.com/fishaudio/Bert-VITS2). We appreciate their awesome work.
| {"license": "mit"} | myshell-ai/MeloTTS-English-v3 | null | [
"transformers",
"license:mit",
"endpoints_compatible",
"region:us"
] | null | 2024-04-17T18:18:30+00:00 | [] | [] | TAGS
#transformers #license-mit #endpoints_compatible #region-us
| MeloTTS
=======
MeloTTS is a high-quality multi-lingual text-to-speech library by URL. Supported languages include:
Some other features include:
* The Chinese speaker supports 'mixed Chinese and English'.
* Fast enough for 'CPU real-time inference'.
Usage
-----
### Without Installation
An unofficial live demo is hosted on Hugging Face Spaces.
#### Use it on MyShell
There are hundreds of TTS models on MyShell, much more than MeloTTS. See examples here.
More can be found at the widget center of URL.
### Install and Use Locally
Follow the installation steps here before using the following snippet:
Join the Community
------------------
Open Source AI Grant
We are actively sponsoring open-source AI projects. The sponsorship includes GPU resources, fundings and intellectual support (collaboration with top research labs). We welcome both reseach and engineering projects, as long as the open-source community needs them. Please contact Zengyi Qin if you are interested.
Contributing
If you find this work useful, please consider contributing to the GitHub repo.
* Many thanks to @fakerybakery for adding the Web UI and CLI part.
License
-------
This library is under MIT License, which means it is free for both commercial and non-commercial use.
Acknowledgements
----------------
This implementation is based on TTS, VITS, VITS2 and Bert-VITS2. We appreciate their awesome work.
| [
"### Without Installation\n\n\nAn unofficial live demo is hosted on Hugging Face Spaces.",
"#### Use it on MyShell\n\n\nThere are hundreds of TTS models on MyShell, much more than MeloTTS. See examples here.\nMore can be found at the widget center of URL.",
"### Install and Use Locally\n\n\nFollow the installation steps here before using the following snippet:\n\n\nJoin the Community\n------------------\n\n\nOpen Source AI Grant\n\n\nWe are actively sponsoring open-source AI projects. The sponsorship includes GPU resources, fundings and intellectual support (collaboration with top research labs). We welcome both reseach and engineering projects, as long as the open-source community needs them. Please contact Zengyi Qin if you are interested.\n\n\nContributing\n\n\nIf you find this work useful, please consider contributing to the GitHub repo.\n\n\n* Many thanks to @fakerybakery for adding the Web UI and CLI part.\n\n\nLicense\n-------\n\n\nThis library is under MIT License, which means it is free for both commercial and non-commercial use.\n\n\nAcknowledgements\n----------------\n\n\nThis implementation is based on TTS, VITS, VITS2 and Bert-VITS2. We appreciate their awesome work."
] | [
"TAGS\n#transformers #license-mit #endpoints_compatible #region-us \n",
"### Without Installation\n\n\nAn unofficial live demo is hosted on Hugging Face Spaces.",
"#### Use it on MyShell\n\n\nThere are hundreds of TTS models on MyShell, much more than MeloTTS. See examples here.\nMore can be found at the widget center of URL.",
"### Install and Use Locally\n\n\nFollow the installation steps here before using the following snippet:\n\n\nJoin the Community\n------------------\n\n\nOpen Source AI Grant\n\n\nWe are actively sponsoring open-source AI projects. The sponsorship includes GPU resources, fundings and intellectual support (collaboration with top research labs). We welcome both reseach and engineering projects, as long as the open-source community needs them. Please contact Zengyi Qin if you are interested.\n\n\nContributing\n\n\nIf you find this work useful, please consider contributing to the GitHub repo.\n\n\n* Many thanks to @fakerybakery for adding the Web UI and CLI part.\n\n\nLicense\n-------\n\n\nThis library is under MIT License, which means it is free for both commercial and non-commercial use.\n\n\nAcknowledgements\n----------------\n\n\nThis implementation is based on TTS, VITS, VITS2 and Bert-VITS2. We appreciate their awesome work."
] |
null | 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": ["trl", "sft"]} | elyadenysova/falcon-7b-sileod_2 | null | [
"transformers",
"safetensors",
"trl",
"sft",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2024-04-17T18:21:23+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #safetensors #trl #sft #arxiv-1910.09700 #endpoints_compatible #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
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:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
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.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
| [
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] | [
"TAGS\n#transformers #safetensors #trl #sft #arxiv-1910.09700 #endpoints_compatible #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
text-generation | transformers |
# Model Trained Using AutoTrain
This model was trained using AutoTrain. For more information, please visit [AutoTrain](https://hf.co/docs/autotrain).
# Usage
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
model_path = "PATH_TO_THIS_REPO"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(
model_path,
device_map="auto",
torch_dtype='auto'
).eval()
# Prompt content: "hi"
messages = [
{"role": "user", "content": "hi"}
]
input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt')
output_ids = model.generate(input_ids.to('cuda'))
response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True)
# Model response: "Hello! How can I assist you today?"
print(response)
``` | {"license": "other", "library_name": "transformers", "tags": ["autotrain", "text-generation-inference", "text-generation", "peft"], "widget": [{"messages": [{"role": "user", "content": "What is your favorite condiment?"}]}]} | ikerm11/FTLLAMA222 | null | [
"transformers",
"safetensors",
"autotrain",
"text-generation-inference",
"text-generation",
"peft",
"conversational",
"license:other",
"endpoints_compatible",
"has_space",
"region:us"
] | null | 2024-04-17T18:22:01+00:00 | [] | [] | TAGS
#transformers #safetensors #autotrain #text-generation-inference #text-generation #peft #conversational #license-other #endpoints_compatible #has_space #region-us
|
# Model Trained Using AutoTrain
This model was trained using AutoTrain. For more information, please visit AutoTrain.
# Usage
| [
"# Model Trained Using AutoTrain\n\nThis model was trained using AutoTrain. For more information, please visit AutoTrain.",
"# Usage"
] | [
"TAGS\n#transformers #safetensors #autotrain #text-generation-inference #text-generation #peft #conversational #license-other #endpoints_compatible #has_space #region-us \n",
"# Model Trained Using AutoTrain\n\nThis model was trained using AutoTrain. For more information, please visit AutoTrain.",
"# Usage"
] |
null | adapter-transformers |
# Adapter `ltuzova/classification_tapt_unipelt_adapter` for roberta-base
An [adapter](https://adapterhub.ml) for the `roberta-base` model that was trained on the [BigTMiami/amazon_helpfulness](https://huggingface.co/datasets/BigTMiami/amazon_helpfulness/) dataset and includes a prediction head for classification.
This adapter was created for usage with the **[Adapters](https://github.com/Adapter-Hub/adapters)** library.
## Usage
First, install `adapters`:
```
pip install -U adapters
```
Now, the adapter can be loaded and activated like this:
```python
from adapters import AutoAdapterModel
model = AutoAdapterModel.from_pretrained("roberta-base")
adapter_name = model.load_adapter("ltuzova/classification_tapt_unipelt_adapter", source="hf", set_active=True)
```
## Architecture & Training
<!-- Add some description here -->
## Evaluation results
<!-- Add some description here -->
## Citation
<!-- Add some description here --> | {"tags": ["roberta", "adapter-transformers"], "datasets": ["BigTMiami/amazon_helpfulness"]} | ltuzova/classification_tapt_unipelt_adapter | null | [
"adapter-transformers",
"roberta",
"dataset:BigTMiami/amazon_helpfulness",
"region:us"
] | null | 2024-04-17T18:23:46+00:00 | [] | [] | TAGS
#adapter-transformers #roberta #dataset-BigTMiami/amazon_helpfulness #region-us
|
# Adapter 'ltuzova/classification_tapt_unipelt_adapter' for roberta-base
An adapter for the 'roberta-base' model that was trained on the BigTMiami/amazon_helpfulness dataset and includes a prediction head for classification.
This adapter was created for usage with the Adapters library.
## Usage
First, install 'adapters':
Now, the adapter can be loaded and activated like this:
## Architecture & Training
## Evaluation results
| [
"# Adapter 'ltuzova/classification_tapt_unipelt_adapter' for roberta-base\n\nAn adapter for the 'roberta-base' model that was trained on the BigTMiami/amazon_helpfulness dataset and includes a prediction head for classification.\n\nThis adapter was created for usage with the Adapters library.",
"## Usage\n\nFirst, install 'adapters':\n\n\n\nNow, the adapter can be loaded and activated like this:",
"## Architecture & Training",
"## Evaluation results"
] | [
"TAGS\n#adapter-transformers #roberta #dataset-BigTMiami/amazon_helpfulness #region-us \n",
"# Adapter 'ltuzova/classification_tapt_unipelt_adapter' for roberta-base\n\nAn adapter for the 'roberta-base' model that was trained on the BigTMiami/amazon_helpfulness dataset and includes a prediction head for classification.\n\nThis adapter was created for usage with the Adapters library.",
"## Usage\n\nFirst, install 'adapters':\n\n\n\nNow, the adapter can be loaded and activated like this:",
"## Architecture & Training",
"## Evaluation results"
] |
null | 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": []} | Aviral2412/fineturning3 | null | [
"transformers",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2024-04-17T18:24:29+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #arxiv-1910.09700 #endpoints_compatible #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
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:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
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.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
| [
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] | [
"TAGS\n#transformers #arxiv-1910.09700 #endpoints_compatible #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
text-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": []} | batprem/typhoon-med | null | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"4-bit",
"region:us"
] | null | 2024-04-17T18:30:14+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #safetensors #mistral #text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
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:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
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.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
| [
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] | [
"TAGS\n#transformers #safetensors #mistral #text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
feature-extraction | 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": []} | eeshanpatel/Bart-finetuned-QA | null | [
"transformers",
"safetensors",
"roberta",
"feature-extraction",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2024-04-17T18:31:01+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #safetensors #roberta #feature-extraction #arxiv-1910.09700 #endpoints_compatible #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
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:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
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.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
| [
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] | [
"TAGS\n#transformers #safetensors #roberta #feature-extraction #arxiv-1910.09700 #endpoints_compatible #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
text-classification | transformers |
# albertmartinez/bert-sdg-classification
This model (BERT) is for classifying text with respect to the United Nations sustainable development goals (SDG).
## Training Hyperparameters
- Num_epoch = 10
- Learning rate = 5e-5
- Batch size = 16
### Training results
| epoch | eval_loss | eval_accuracy | eval_precision | eval_recall | eval_f1 |
|:-----:|:------------------:|:------------------:|:------------------:|:------------------:|:------------------:|
| 1 | 0.8289520740509033 | 0.7644437495113752 | 0.7640369944809821 | 0.7644437495113752 | 0.7554162181382816 |
| 2 | 0.7316043972969055 | 0.792432178875772 | 0.7973419054011932 | 0.792432178875772 | 0.7936523802626467 |
| 3 | 0.7474315762519836 | 0.7989992963802673 | 0.8003484834993271 | 0.7989992963802673 | 0.7980647892639322 |
| 4 | 0.9092283248901367 | 0.8023610351028067 | 0.8028028170382215 | 0.8023610351028067 | 0.8010556735181147 |
| 5 | 1.0973293781280518 | 0.8040028144789305 | 0.806116786873114 | 0.8040028144789305 | 0.8037135940426907 |
| 6 | 1.2260032892227173 | 0.8032210147760144 | 0.8046046540363118 | 0.8032210147760144 | 0.8009496362737498 |
| 7 | 1.3465653657913208 | 0.8082245328746775 | 0.8079189056438383 | 0.8082245328746775 | 0.8070935517356475 |
| 8 | 1.458662509918213 | 0.8132280509733406 | 0.8124031757212116 | 0.8132280509733406 | 0.8124964838774498 |
| 9 | 1.5251907110214233 | 0.8108044718943007 | 0.8112362484949358 | 0.8108044718943007 | 0.8097338645156864 |
| 10 | 1.50314199924469 | 0.8152607302009225 | 0.8143774938584517 | 0.8152607302009225 | 0.8144630791491494 |
| {"license": "mit", "datasets": ["albertmartinez/OSDG"], "metrics": ["accuracy", "precision", "recall", "f1"], "pipeline_tag": "text-classification", "widget": [{"text": "Between the Social and the Spatial - Exploring Multiple Dimensions of Poverty and Social Exclusion, Ashgate. Poverty in Europe and the USA, Exchanging Official Measurement Methods\u201d, Maastricht Graduate School of Governance Working Paper 2007/005. Monitoring Absolute and Relative Poverty, \u2018Not Enough\u2019 Is Not the Same as \u2018Much Less\u2019\u201d, Review of Income and Wealth, 57(2), 247-269. Poverty and Social Exclusion in Britain, The Policy Press, Bristol."}, {"text": "A circular economy is a way of achieving sustainable consumption and production, as well as nature positive outcomes."}]} | albertmartinez/bert-sdg-classification | null | [
"transformers",
"onnx",
"safetensors",
"bert",
"text-classification",
"dataset:albertmartinez/OSDG",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-04-17T18:34:09+00:00 | [] | [] | TAGS
#transformers #onnx #safetensors #bert #text-classification #dataset-albertmartinez/OSDG #license-mit #autotrain_compatible #endpoints_compatible #region-us
| albertmartinez/bert-sdg-classification
======================================
This model (BERT) is for classifying text with respect to the United Nations sustainable development goals (SDG).
Training Hyperparameters
------------------------
* Num\_epoch = 10
* Learning rate = 5e-5
* Batch size = 16
### Training results
| [
"### Training results"
] | [
"TAGS\n#transformers #onnx #safetensors #bert #text-classification #dataset-albertmartinez/OSDG #license-mit #autotrain_compatible #endpoints_compatible #region-us \n",
"### Training results"
] |
null | 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": []} | morioxd/fine_tuned_13b | null | [
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2024-04-17T18:34:25+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
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:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
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.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
| [
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] | [
"TAGS\n#transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
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. -->
# bart-base-combined
This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 2.2529
- Rouge1: 39.474
- Rouge2: 15.406
- Rougel: 27.6651
- Rougelsum: 36.2084
- Gen Len: 75.5717
## 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: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
| 2.5384 | 1.0 | 5435 | 2.3837 | 38.4347 | 14.2933 | 26.4507 | 35.1406 | 80.9404 |
| 2.2422 | 2.0 | 10870 | 2.3314 | 38.8455 | 14.6495 | 27.0452 | 35.4609 | 77.2153 |
| 2.0497 | 3.0 | 16305 | 2.3032 | 39.0212 | 14.8913 | 27.3328 | 35.7033 | 75.7681 |
### Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
| {"license": "apache-2.0", "tags": ["generated_from_trainer"], "metrics": ["rouge"], "base_model": "facebook/bart-base", "model-index": [{"name": "bart-base-combined", "results": []}]} | TerryLaw535/bart-base-combined | null | [
"transformers",
"pytorch",
"tensorboard",
"safetensors",
"bart",
"text2text-generation",
"generated_from_trainer",
"base_model:facebook/bart-base",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-04-17T18:36:06+00:00 | [] | [] | TAGS
#transformers #pytorch #tensorboard #safetensors #bart #text2text-generation #generated_from_trainer #base_model-facebook/bart-base #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us
| bart-base-combined
==================
This model is a fine-tuned version of facebook/bart-base on an unknown dataset.
It achieves the following results on the evaluation set:
* Loss: 2.2529
* Rouge1: 39.474
* Rouge2: 15.406
* Rougel: 27.6651
* Rougelsum: 36.2084
* Gen Len: 75.5717
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: 4
* seed: 42
* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
* lr\_scheduler\_type: linear
* num\_epochs: 3
### Training results
### Framework versions
* Transformers 4.38.2
* Pytorch 2.2.1+cu121
* Datasets 2.18.0
* Tokenizers 0.15.2
| [
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 5e-05\n* train\\_batch\\_size: 4\n* eval\\_batch\\_size: 4\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 3",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.38.2\n* Pytorch 2.2.1+cu121\n* Datasets 2.18.0\n* Tokenizers 0.15.2"
] | [
"TAGS\n#transformers #pytorch #tensorboard #safetensors #bart #text2text-generation #generated_from_trainer #base_model-facebook/bart-base #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n",
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 5e-05\n* train\\_batch\\_size: 4\n* eval\\_batch\\_size: 4\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 3",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.38.2\n* Pytorch 2.2.1+cu121\n* Datasets 2.18.0\n* Tokenizers 0.15.2"
] |
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. -->
# mistral7binstruct_summarize-v3
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the generator dataset.
It achieves the following results on the evaluation set:
- Loss: 1.4494
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_steps: 0.03
- training_steps: 50
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 1.6604 | 0.2137 | 25 | 1.4984 |
| 1.5071 | 0.4274 | 50 | 1.4494 |
### Framework versions
- PEFT 0.10.0
- Transformers 4.40.0
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1 | {"license": "apache-2.0", "library_name": "peft", "tags": ["trl", "sft", "generated_from_trainer"], "datasets": ["generator"], "base_model": "mistralai/Mistral-7B-Instruct-v0.2", "model-index": [{"name": "mistral7binstruct_summarize-v3", "results": []}]} | asahikuroki222/mistral7binstruct_summarize-v3 | null | [
"peft",
"tensorboard",
"safetensors",
"trl",
"sft",
"generated_from_trainer",
"dataset:generator",
"base_model:mistralai/Mistral-7B-Instruct-v0.2",
"license:apache-2.0",
"region:us"
] | null | 2024-04-17T18:37:27+00:00 | [] | [] | TAGS
#peft #tensorboard #safetensors #trl #sft #generated_from_trainer #dataset-generator #base_model-mistralai/Mistral-7B-Instruct-v0.2 #license-apache-2.0 #region-us
| mistral7binstruct\_summarize-v3
===============================
This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.2 on the generator dataset.
It achieves the following results on the evaluation set:
* Loss: 1.4494
Model description
-----------------
More information needed
Intended uses & limitations
---------------------------
More information needed
Training and evaluation data
----------------------------
More information needed
Training procedure
------------------
### Training hyperparameters
The following hyperparameters were used during training:
* learning\_rate: 0.0002
* train\_batch\_size: 1
* eval\_batch\_size: 8
* seed: 42
* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
* lr\_scheduler\_type: constant
* lr\_scheduler\_warmup\_steps: 0.03
* training\_steps: 50
### Training results
### Framework versions
* PEFT 0.10.0
* Transformers 4.40.0
* Pytorch 2.2.1+cu121
* Datasets 2.19.0
* Tokenizers 0.19.1
| [
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0002\n* train\\_batch\\_size: 1\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: constant\n* lr\\_scheduler\\_warmup\\_steps: 0.03\n* training\\_steps: 50",
"### Training results",
"### Framework versions\n\n\n* PEFT 0.10.0\n* Transformers 4.40.0\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1"
] | [
"TAGS\n#peft #tensorboard #safetensors #trl #sft #generated_from_trainer #dataset-generator #base_model-mistralai/Mistral-7B-Instruct-v0.2 #license-apache-2.0 #region-us \n",
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0002\n* train\\_batch\\_size: 1\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: constant\n* lr\\_scheduler\\_warmup\\_steps: 0.03\n* training\\_steps: 50",
"### Training results",
"### Framework versions\n\n\n* PEFT 0.10.0\n* Transformers 4.40.0\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1"
] |
text-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": []} | Grayx/sad_pepe_34 | null | [
"transformers",
"safetensors",
"stablelm",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-04-17T18:37:43+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #safetensors #stablelm #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
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:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
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.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
| [
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] | [
"TAGS\n#transformers #safetensors #stablelm #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
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. -->
# sentiment-bert-base-uncased-ALL-SAMPLES3epochsValidation
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2711
- Accuracy: 0.9392
- F1: 0.9392
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
### Framework versions
- Transformers 4.39.3
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
| {"license": "apache-2.0", "tags": ["generated_from_trainer"], "metrics": ["accuracy", "f1"], "base_model": "bert-base-uncased", "model-index": [{"name": "sentiment-bert-base-uncased-ALL-SAMPLES3epochsValidation", "results": []}]} | AndreiUrsu/sentiment-bert-base-uncased-ALL-SAMPLES3epochsValidation | null | [
"transformers",
"tensorboard",
"safetensors",
"bert",
"text-classification",
"generated_from_trainer",
"base_model:bert-base-uncased",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-04-17T18:44:06+00:00 | [] | [] | TAGS
#transformers #tensorboard #safetensors #bert #text-classification #generated_from_trainer #base_model-bert-base-uncased #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us
|
# sentiment-bert-base-uncased-ALL-SAMPLES3epochsValidation
This model is a fine-tuned version of bert-base-uncased on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2711
- Accuracy: 0.9392
- F1: 0.9392
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
### Framework versions
- Transformers 4.39.3
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
| [
"# sentiment-bert-base-uncased-ALL-SAMPLES3epochsValidation\n\nThis model is a fine-tuned version of bert-base-uncased on an unknown dataset.\nIt achieves the following results on the evaluation set:\n- Loss: 0.2711\n- Accuracy: 0.9392\n- F1: 0.9392",
"## Model description\n\nMore information needed",
"## Intended uses & limitations\n\nMore information needed",
"## Training and evaluation data\n\nMore information needed",
"## Training procedure",
"### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 2e-05\n- train_batch_size: 16\n- eval_batch_size: 16\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 3",
"### Training results",
"### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.2.1+cu121\n- Datasets 2.18.0\n- Tokenizers 0.15.2"
] | [
"TAGS\n#transformers #tensorboard #safetensors #bert #text-classification #generated_from_trainer #base_model-bert-base-uncased #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n",
"# sentiment-bert-base-uncased-ALL-SAMPLES3epochsValidation\n\nThis model is a fine-tuned version of bert-base-uncased on an unknown dataset.\nIt achieves the following results on the evaluation set:\n- Loss: 0.2711\n- Accuracy: 0.9392\n- F1: 0.9392",
"## Model description\n\nMore information needed",
"## Intended uses & limitations\n\nMore information needed",
"## Training and evaluation data\n\nMore information needed",
"## Training procedure",
"### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 2e-05\n- train_batch_size: 16\n- eval_batch_size: 16\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 3",
"### Training results",
"### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.2.1+cu121\n- Datasets 2.18.0\n- Tokenizers 0.15.2"
] |
text-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": []} | KvrParaskevi/gemma-2b-Hotel-Assitant-1 | null | [
"transformers",
"safetensors",
"gemma",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-04-17T18:49:27+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #safetensors #gemma #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
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:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
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.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
| [
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] | [
"TAGS\n#transformers #safetensors #gemma #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
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. -->
# distilbert-base-uncased-lora-text-classification
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.1143
- Accuracy: {'accuracy': 0.885}
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.001
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:-------------------:|
| No log | 1.0 | 250 | 0.3907 | {'accuracy': 0.87} |
| 0.4307 | 2.0 | 500 | 0.4413 | {'accuracy': 0.886} |
| 0.4307 | 3.0 | 750 | 0.7302 | {'accuracy': 0.879} |
| 0.1513 | 4.0 | 1000 | 0.7659 | {'accuracy': 0.882} |
| 0.1513 | 5.0 | 1250 | 0.7540 | {'accuracy': 0.877} |
| 0.0662 | 6.0 | 1500 | 0.8800 | {'accuracy': 0.886} |
| 0.0662 | 7.0 | 1750 | 1.0128 | {'accuracy': 0.885} |
| 0.0086 | 8.0 | 2000 | 1.0446 | {'accuracy': 0.884} |
| 0.0086 | 9.0 | 2250 | 1.1049 | {'accuracy': 0.884} |
| 0.0026 | 10.0 | 2500 | 1.1143 | {'accuracy': 0.885} |
### Framework versions
- PEFT 0.10.0
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2 | {"license": "apache-2.0", "library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "distilbert-base-uncased", "model-index": [{"name": "distilbert-base-uncased-lora-text-classification", "results": []}]} | oliver-chen/distilbert-base-uncased-lora-text-classification | null | [
"peft",
"tensorboard",
"safetensors",
"generated_from_trainer",
"base_model:distilbert-base-uncased",
"license:apache-2.0",
"region:us"
] | null | 2024-04-17T18:49:44+00:00 | [] | [] | TAGS
#peft #tensorboard #safetensors #generated_from_trainer #base_model-distilbert-base-uncased #license-apache-2.0 #region-us
| distilbert-base-uncased-lora-text-classification
================================================
This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset.
It achieves the following results on the evaluation set:
* Loss: 1.1143
* Accuracy: {'accuracy': 0.885}
Model description
-----------------
More information needed
Intended uses & limitations
---------------------------
More information needed
Training and evaluation data
----------------------------
More information needed
Training procedure
------------------
### Training hyperparameters
The following hyperparameters were used during training:
* learning\_rate: 0.001
* train\_batch\_size: 4
* eval\_batch\_size: 4
* seed: 42
* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
* lr\_scheduler\_type: linear
* num\_epochs: 10
### Training results
### Framework versions
* PEFT 0.10.0
* Transformers 4.38.2
* Pytorch 2.2.1+cu121
* Datasets 2.18.0
* Tokenizers 0.15.2
| [
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.001\n* train\\_batch\\_size: 4\n* eval\\_batch\\_size: 4\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 10",
"### Training results",
"### Framework versions\n\n\n* PEFT 0.10.0\n* Transformers 4.38.2\n* Pytorch 2.2.1+cu121\n* Datasets 2.18.0\n* Tokenizers 0.15.2"
] | [
"TAGS\n#peft #tensorboard #safetensors #generated_from_trainer #base_model-distilbert-base-uncased #license-apache-2.0 #region-us \n",
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.001\n* train\\_batch\\_size: 4\n* eval\\_batch\\_size: 4\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 10",
"### Training results",
"### Framework versions\n\n\n* PEFT 0.10.0\n* Transformers 4.38.2\n* Pytorch 2.2.1+cu121\n* Datasets 2.18.0\n* Tokenizers 0.15.2"
] |
reinforcement-learning | transformers |
# TRL Model
This is a [TRL language model](https://github.com/huggingface/trl) that has been fine-tuned with reinforcement learning to
guide the model outputs according to a value, function, or human feedback. The model can be used for text generation.
## Usage
To use this model for inference, first install the TRL library:
```bash
python -m pip install trl
```
You can then generate text as follows:
```python
from transformers import pipeline
generator = pipeline("text-generation", model="baek26//tmp/tmpxgx0g4kx/baek26/billsum_1703_bart-billsum")
outputs = generator("Hello, my llama is cute")
```
If you want to use the model for training or to obtain the outputs from the value head, load the model as follows:
```python
from transformers import AutoTokenizer
from trl import AutoModelForCausalLMWithValueHead
tokenizer = AutoTokenizer.from_pretrained("baek26//tmp/tmpxgx0g4kx/baek26/billsum_1703_bart-billsum")
model = AutoModelForCausalLMWithValueHead.from_pretrained("baek26//tmp/tmpxgx0g4kx/baek26/billsum_1703_bart-billsum")
inputs = tokenizer("Hello, my llama is cute", return_tensors="pt")
outputs = model(**inputs, labels=inputs["input_ids"])
```
| {"license": "apache-2.0", "tags": ["trl", "ppo", "transformers", "reinforcement-learning"]} | baek26/billsum_1703_bart-billsum | null | [
"transformers",
"safetensors",
"bart",
"text2text-generation",
"trl",
"ppo",
"reinforcement-learning",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-04-17T18:51:09+00:00 | [] | [] | TAGS
#transformers #safetensors #bart #text2text-generation #trl #ppo #reinforcement-learning #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us
|
# TRL Model
This is a TRL language model that has been fine-tuned with reinforcement learning to
guide the model outputs according to a value, function, or human feedback. The model can be used for text generation.
## Usage
To use this model for inference, first install the TRL library:
You can then generate text as follows:
If you want to use the model for training or to obtain the outputs from the value head, load the model as follows:
| [
"# TRL Model\n\nThis is a TRL language model that has been fine-tuned with reinforcement learning to\n guide the model outputs according to a value, function, or human feedback. The model can be used for text generation.",
"## Usage\n\nTo use this model for inference, first install the TRL library:\n\n\n\nYou can then generate text as follows:\n\n\n\nIf you want to use the model for training or to obtain the outputs from the value head, load the model as follows:"
] | [
"TAGS\n#transformers #safetensors #bart #text2text-generation #trl #ppo #reinforcement-learning #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n",
"# TRL Model\n\nThis is a TRL language model that has been fine-tuned with reinforcement learning to\n guide the model outputs according to a value, function, or human feedback. The model can be used for text generation.",
"## Usage\n\nTo use this model for inference, first install the TRL library:\n\n\n\nYou can then generate text as follows:\n\n\n\nIf you want to use the model for training or to obtain the outputs from the value head, load the model as follows:"
] |
text-generation | transformers |
# PhwyzardLM 2 7B
This model was converted to GGUF format from [`grimjim/zephyr-beta-wizardLM-2-merge-7B`](https://huggingface.co/grimjim/zephyr-beta-wizardLM-2-merge-7B) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/grimjim/zephyr-beta-wizardLM-2-merge-7B) for more details on the model.
| {"license": "apache-2.0", "library_name": "transformers", "tags": ["mistral", "merge", "gguf-my-repo"], "base_model": ["lucyknada/microsoft_WizardLM-2-7B", "HuggingFaceH4/zephyr-7b-beta"], "pipeline_tag": "text-generation"} | twodgirl/zephyr-beta-wizardLM-2-merge-7B-Q6_K-GGUF | null | [
"transformers",
"gguf",
"mistral",
"merge",
"gguf-my-repo",
"text-generation",
"base_model:lucyknada/microsoft_WizardLM-2-7B",
"base_model:HuggingFaceH4/zephyr-7b-beta",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2024-04-17T18:51:24+00:00 | [] | [] | TAGS
#transformers #gguf #mistral #merge #gguf-my-repo #text-generation #base_model-lucyknada/microsoft_WizardLM-2-7B #base_model-HuggingFaceH4/zephyr-7b-beta #license-apache-2.0 #endpoints_compatible #region-us
|
# PhwyzardLM 2 7B
This model was converted to GGUF format from 'grimjim/zephyr-beta-wizardLM-2-merge-7B' using URL via the URL's GGUF-my-repo space.
Refer to the original model card for more details on the model.
| [
"# PhwyzardLM 2 7B\nThis model was converted to GGUF format from 'grimjim/zephyr-beta-wizardLM-2-merge-7B' using URL via the URL's GGUF-my-repo space.\nRefer to the original model card for more details on the model."
] | [
"TAGS\n#transformers #gguf #mistral #merge #gguf-my-repo #text-generation #base_model-lucyknada/microsoft_WizardLM-2-7B #base_model-HuggingFaceH4/zephyr-7b-beta #license-apache-2.0 #endpoints_compatible #region-us \n",
"# PhwyzardLM 2 7B\nThis model was converted to GGUF format from 'grimjim/zephyr-beta-wizardLM-2-merge-7B' using URL via the URL's GGUF-my-repo space.\nRefer to the original model card for more details on the model."
] |
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. -->
# mistral-20var-ChatBot
This model is a fine-tuned version of [TheBloke/Mistral-7B-Instruct-v0.1-GPTQ](https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.1-GPTQ) on the None dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- training_steps: 250
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- PEFT 0.10.0
- Transformers 4.41.0.dev0
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.19.1 | {"license": "apache-2.0", "library_name": "peft", "tags": ["trl", "sft", "generated_from_trainer"], "base_model": "TheBloke/Mistral-7B-Instruct-v0.1-GPTQ", "model-index": [{"name": "mistral-20var-ChatBot", "results": []}]} | neuralleap/mistral-20var-ChatBot | null | [
"peft",
"tensorboard",
"safetensors",
"trl",
"sft",
"generated_from_trainer",
"base_model:TheBloke/Mistral-7B-Instruct-v0.1-GPTQ",
"license:apache-2.0",
"region:us"
] | null | 2024-04-17T18:52:18+00:00 | [] | [] | TAGS
#peft #tensorboard #safetensors #trl #sft #generated_from_trainer #base_model-TheBloke/Mistral-7B-Instruct-v0.1-GPTQ #license-apache-2.0 #region-us
|
# mistral-20var-ChatBot
This model is a fine-tuned version of TheBloke/Mistral-7B-Instruct-v0.1-GPTQ on the None dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- training_steps: 250
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- PEFT 0.10.0
- Transformers 4.41.0.dev0
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.19.1 | [
"# mistral-20var-ChatBot\n\nThis model is a fine-tuned version of TheBloke/Mistral-7B-Instruct-v0.1-GPTQ on the None dataset.",
"## Model description\n\nMore information needed",
"## Intended uses & limitations\n\nMore information needed",
"## Training and evaluation data\n\nMore information needed",
"## Training procedure",
"### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 0.0002\n- train_batch_size: 8\n- eval_batch_size: 8\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- training_steps: 250\n- mixed_precision_training: Native AMP",
"### Training results",
"### Framework versions\n\n- PEFT 0.10.0\n- Transformers 4.41.0.dev0\n- Pytorch 2.2.1+cu121\n- Datasets 2.18.0\n- Tokenizers 0.19.1"
] | [
"TAGS\n#peft #tensorboard #safetensors #trl #sft #generated_from_trainer #base_model-TheBloke/Mistral-7B-Instruct-v0.1-GPTQ #license-apache-2.0 #region-us \n",
"# mistral-20var-ChatBot\n\nThis model is a fine-tuned version of TheBloke/Mistral-7B-Instruct-v0.1-GPTQ on the None dataset.",
"## Model description\n\nMore information needed",
"## Intended uses & limitations\n\nMore information needed",
"## Training and evaluation data\n\nMore information needed",
"## Training procedure",
"### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 0.0002\n- train_batch_size: 8\n- eval_batch_size: 8\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- training_steps: 250\n- mixed_precision_training: Native AMP",
"### Training results",
"### Framework versions\n\n- PEFT 0.10.0\n- Transformers 4.41.0.dev0\n- Pytorch 2.2.1+cu121\n- Datasets 2.18.0\n- Tokenizers 0.19.1"
] |
null | null | hello | {} | arzoop/trial2 | null | [
"region:us"
] | null | 2024-04-17T18:53:13+00:00 | [] | [] | TAGS
#region-us
| hello | [] | [
"TAGS\n#region-us \n"
] |
text-to-image | diffusers |
<!-- This model card has been generated automatically according to the information the training script had access to. You
should probably proofread and complete it, then remove this comment. -->
# SDXL LoRA DreamBooth - rzhen0615/my_boyfriend_David_LoRA
<Gallery />
## Model description
These are rzhen0615/my_boyfriend_David_LoRA LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.
The weights were trained using [DreamBooth](https://dreambooth.github.io/).
LoRA for the text encoder was enabled: False.
Special VAE used for training: madebyollin/sdxl-vae-fp16-fix.
## Trigger words
You should use a photo of my boyfriend David to trigger the image generation.
## Download model
Weights for this model are available in Safetensors format.
[Download](rzhen0615/my_boyfriend_David_LoRA/tree/main) them in the Files & versions tab.
## Intended uses & limitations
#### How to use
```python
# TODO: add an example code snippet for running this diffusion pipeline
```
#### Limitations and bias
[TODO: provide examples of latent issues and potential remediations]
## Training details
[TODO: describe the data used to train the model] | {"license": "openrail++", "library_name": "diffusers", "tags": ["text-to-image", "text-to-image", "diffusers-training", "diffusers", "lora", "template:sd-lora", "stable-diffusion-xl", "stable-diffusion-xl-diffusers", "text-to-image", "text-to-image", "diffusers-training", "diffusers", "lora", "template:sd-lora", "stable-diffusion-xl", "stable-diffusion-xl-diffusers"], "base_model": "stabilityai/stable-diffusion-xl-base-1.0", "instance_prompt": "a photo of my boyfriend David", "widget": []} | rzhen0615/my_boyfriend_David_LoRA | null | [
"diffusers",
"tensorboard",
"text-to-image",
"diffusers-training",
"lora",
"template:sd-lora",
"stable-diffusion-xl",
"stable-diffusion-xl-diffusers",
"base_model:stabilityai/stable-diffusion-xl-base-1.0",
"license:openrail++",
"region:us"
] | null | 2024-04-17T18:54:13+00:00 | [] | [] | TAGS
#diffusers #tensorboard #text-to-image #diffusers-training #lora #template-sd-lora #stable-diffusion-xl #stable-diffusion-xl-diffusers #base_model-stabilityai/stable-diffusion-xl-base-1.0 #license-openrail++ #region-us
|
# SDXL LoRA DreamBooth - rzhen0615/my_boyfriend_David_LoRA
<Gallery />
## Model description
These are rzhen0615/my_boyfriend_David_LoRA LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.
The weights were trained using DreamBooth.
LoRA for the text encoder was enabled: False.
Special VAE used for training: madebyollin/sdxl-vae-fp16-fix.
## Trigger words
You should use a photo of my boyfriend David to trigger the image generation.
## Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.
## Intended uses & limitations
#### How to use
#### Limitations and bias
[TODO: provide examples of latent issues and potential remediations]
## Training details
[TODO: describe the data used to train the model] | [
"# SDXL LoRA DreamBooth - rzhen0615/my_boyfriend_David_LoRA\n\n<Gallery />",
"## Model description\n\nThese are rzhen0615/my_boyfriend_David_LoRA LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.\n\nThe weights were trained using DreamBooth.\n\nLoRA for the text encoder was enabled: False.\n\nSpecial VAE used for training: madebyollin/sdxl-vae-fp16-fix.",
"## Trigger words\n\nYou should use a photo of my boyfriend David to trigger the image generation.",
"## Download model\n\nWeights for this model are available in Safetensors format.\n\nDownload them in the Files & versions tab.",
"## Intended uses & limitations",
"#### How to use",
"#### Limitations and bias\n\n[TODO: provide examples of latent issues and potential remediations]",
"## Training details\n\n[TODO: describe the data used to train the model]"
] | [
"TAGS\n#diffusers #tensorboard #text-to-image #diffusers-training #lora #template-sd-lora #stable-diffusion-xl #stable-diffusion-xl-diffusers #base_model-stabilityai/stable-diffusion-xl-base-1.0 #license-openrail++ #region-us \n",
"# SDXL LoRA DreamBooth - rzhen0615/my_boyfriend_David_LoRA\n\n<Gallery />",
"## Model description\n\nThese are rzhen0615/my_boyfriend_David_LoRA LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.\n\nThe weights were trained using DreamBooth.\n\nLoRA for the text encoder was enabled: False.\n\nSpecial VAE used for training: madebyollin/sdxl-vae-fp16-fix.",
"## Trigger words\n\nYou should use a photo of my boyfriend David to trigger the image generation.",
"## Download model\n\nWeights for this model are available in Safetensors format.\n\nDownload them in the Files & versions tab.",
"## Intended uses & limitations",
"#### How to use",
"#### Limitations and bias\n\n[TODO: provide examples of latent issues and potential remediations]",
"## Training details\n\n[TODO: describe the data used to train the model]"
] |
text-generation | transformers |
# yk_8x7b_model
yk_8x7b_model is a Mixture of Experts (MoE) made with the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [mlabonne/AlphaMonarch-7B](https://huggingface.co/mlabonne/AlphaMonarch-7B)
* [beowolx/CodeNinja-1.0-OpenChat-7B](https://huggingface.co/beowolx/CodeNinja-1.0-OpenChat-7B)
* [SanjiWatsuki/Kunoichi-DPO-v2-7B](https://huggingface.co/SanjiWatsuki/Kunoichi-DPO-v2-7B)
* [mlabonne/NeuralDaredevil-7B](https://huggingface.co/mlabonne/NeuralDaredevil-7B)
* [HuggingFaceH4/zephyr-7b-beta](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta)
* [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2)
* [teknium/OpenHermes-2.5-Mistral-7B](https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B)
* [meta-math/MetaMath-Mistral-7B](https://huggingface.co/meta-math/MetaMath-Mistral-7B)
## 🧩 Configuration
```yaml
base_model: mistralai/Mistral-7B-Instruct-v0.2
dtype: float16
gate_mode: hidden
experts:
- source_model: mlabonne/AlphaMonarch-7B
positive_prompts:
- "chat"
- "assistant"
- "tell me"
- "explain"
- "I want"
- "help"
- source_model: beowolx/CodeNinja-1.0-OpenChat-7B
positive_prompts:
- "code"
- "python"
- "javascript"
- "programming"
- "algorithm"
- "coding"
- source_model: SanjiWatsuki/Kunoichi-DPO-v2-7B
positive_prompts:
- "storywriting"
- "write"
- "scene"
- "story"
- "character"
- "creative"
- source_model: mlabonne/NeuralDaredevil-7B
positive_prompts:
- "reason"
- "math"
- "mathematics"
- "solve"
- "count"
- "logic"
- source_model: HuggingFaceH4/zephyr-7b-beta
positive_prompts:
- "You are an helpful general-purpose assistant."
- "assist"
- "helpful"
- "support"
- "guide"
- source_model: mistralai/Mistral-7B-Instruct-v0.2
positive_prompts:
- "You are helpful assistant."
- "aid"
- "assist"
- "guide"
- "support"
- source_model: teknium/OpenHermes-2.5-Mistral-7B
positive_prompts:
- "You are helpful a coding assistant."
- "code"
- "programming"
- "debug"
- "scripting"
- "coding"
- source_model: meta-math/MetaMath-Mistral-7B
positive_prompts:
- "You are an assistant good at math."
- "mathematics"
- "calculation"
- "problem solving"
- "arithmetics"
- "math"
```
## 💻 Usage
```python
!pip install -qU transformers bitsandbytes accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "yatinece/yk_8x7b_model"
tokenizer = AutoTokenizer.from_pretrained(model)
pipeline = transformers.pipeline(
"text-generation",
model=model,
model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True},
)
messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in less than 100 words."}]
prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
``` | {"license": "apache-2.0", "tags": ["moe", "frankenmoe", "merge", "mergekit", "lazymergekit", "mlabonne/AlphaMonarch-7B", "beowolx/CodeNinja-1.0-OpenChat-7B", "SanjiWatsuki/Kunoichi-DPO-v2-7B", "mlabonne/NeuralDaredevil-7B", "HuggingFaceH4/zephyr-7b-beta", "mistralai/Mistral-7B-Instruct-v0.2", "teknium/OpenHermes-2.5-Mistral-7B", "meta-math/MetaMath-Mistral-7B"], "base_model": ["mlabonne/AlphaMonarch-7B", "beowolx/CodeNinja-1.0-OpenChat-7B", "SanjiWatsuki/Kunoichi-DPO-v2-7B", "mlabonne/NeuralDaredevil-7B", "HuggingFaceH4/zephyr-7b-beta", "mistralai/Mistral-7B-Instruct-v0.2", "teknium/OpenHermes-2.5-Mistral-7B", "meta-math/MetaMath-Mistral-7B"]} | yatinece/yk_8x7b_model_v1 | null | [
"transformers",
"safetensors",
"mixtral",
"text-generation",
"moe",
"frankenmoe",
"merge",
"mergekit",
"lazymergekit",
"mlabonne/AlphaMonarch-7B",
"beowolx/CodeNinja-1.0-OpenChat-7B",
"SanjiWatsuki/Kunoichi-DPO-v2-7B",
"mlabonne/NeuralDaredevil-7B",
"HuggingFaceH4/zephyr-7b-beta",
"mistralai/Mistral-7B-Instruct-v0.2",
"teknium/OpenHermes-2.5-Mistral-7B",
"meta-math/MetaMath-Mistral-7B",
"conversational",
"base_model:mlabonne/AlphaMonarch-7B",
"base_model:beowolx/CodeNinja-1.0-OpenChat-7B",
"base_model:SanjiWatsuki/Kunoichi-DPO-v2-7B",
"base_model:mlabonne/NeuralDaredevil-7B",
"base_model:HuggingFaceH4/zephyr-7b-beta",
"base_model:mistralai/Mistral-7B-Instruct-v0.2",
"base_model:teknium/OpenHermes-2.5-Mistral-7B",
"base_model:meta-math/MetaMath-Mistral-7B",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-04-17T18:54:46+00:00 | [] | [] | TAGS
#transformers #safetensors #mixtral #text-generation #moe #frankenmoe #merge #mergekit #lazymergekit #mlabonne/AlphaMonarch-7B #beowolx/CodeNinja-1.0-OpenChat-7B #SanjiWatsuki/Kunoichi-DPO-v2-7B #mlabonne/NeuralDaredevil-7B #HuggingFaceH4/zephyr-7b-beta #mistralai/Mistral-7B-Instruct-v0.2 #teknium/OpenHermes-2.5-Mistral-7B #meta-math/MetaMath-Mistral-7B #conversational #base_model-mlabonne/AlphaMonarch-7B #base_model-beowolx/CodeNinja-1.0-OpenChat-7B #base_model-SanjiWatsuki/Kunoichi-DPO-v2-7B #base_model-mlabonne/NeuralDaredevil-7B #base_model-HuggingFaceH4/zephyr-7b-beta #base_model-mistralai/Mistral-7B-Instruct-v0.2 #base_model-teknium/OpenHermes-2.5-Mistral-7B #base_model-meta-math/MetaMath-Mistral-7B #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us
|
# yk_8x7b_model
yk_8x7b_model is a Mixture of Experts (MoE) made with the following models using LazyMergekit:
* mlabonne/AlphaMonarch-7B
* beowolx/CodeNinja-1.0-OpenChat-7B
* SanjiWatsuki/Kunoichi-DPO-v2-7B
* mlabonne/NeuralDaredevil-7B
* HuggingFaceH4/zephyr-7b-beta
* mistralai/Mistral-7B-Instruct-v0.2
* teknium/OpenHermes-2.5-Mistral-7B
* meta-math/MetaMath-Mistral-7B
## Configuration
## Usage
| [
"# yk_8x7b_model\n\nyk_8x7b_model is a Mixture of Experts (MoE) made with the following models using LazyMergekit:\n* mlabonne/AlphaMonarch-7B\n* beowolx/CodeNinja-1.0-OpenChat-7B\n* SanjiWatsuki/Kunoichi-DPO-v2-7B\n* mlabonne/NeuralDaredevil-7B\n* HuggingFaceH4/zephyr-7b-beta\n* mistralai/Mistral-7B-Instruct-v0.2\n* teknium/OpenHermes-2.5-Mistral-7B\n* meta-math/MetaMath-Mistral-7B",
"## Configuration",
"## Usage"
] | [
"TAGS\n#transformers #safetensors #mixtral #text-generation #moe #frankenmoe #merge #mergekit #lazymergekit #mlabonne/AlphaMonarch-7B #beowolx/CodeNinja-1.0-OpenChat-7B #SanjiWatsuki/Kunoichi-DPO-v2-7B #mlabonne/NeuralDaredevil-7B #HuggingFaceH4/zephyr-7b-beta #mistralai/Mistral-7B-Instruct-v0.2 #teknium/OpenHermes-2.5-Mistral-7B #meta-math/MetaMath-Mistral-7B #conversational #base_model-mlabonne/AlphaMonarch-7B #base_model-beowolx/CodeNinja-1.0-OpenChat-7B #base_model-SanjiWatsuki/Kunoichi-DPO-v2-7B #base_model-mlabonne/NeuralDaredevil-7B #base_model-HuggingFaceH4/zephyr-7b-beta #base_model-mistralai/Mistral-7B-Instruct-v0.2 #base_model-teknium/OpenHermes-2.5-Mistral-7B #base_model-meta-math/MetaMath-Mistral-7B #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n",
"# yk_8x7b_model\n\nyk_8x7b_model is a Mixture of Experts (MoE) made with the following models using LazyMergekit:\n* mlabonne/AlphaMonarch-7B\n* beowolx/CodeNinja-1.0-OpenChat-7B\n* SanjiWatsuki/Kunoichi-DPO-v2-7B\n* mlabonne/NeuralDaredevil-7B\n* HuggingFaceH4/zephyr-7b-beta\n* mistralai/Mistral-7B-Instruct-v0.2\n* teknium/OpenHermes-2.5-Mistral-7B\n* meta-math/MetaMath-Mistral-7B",
"## Configuration",
"## Usage"
] |
text-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": []} | heyllm234/sc51 | null | [
"transformers",
"safetensors",
"stablelm",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-04-17T18:55:41+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #safetensors #stablelm #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
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:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
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.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
| [
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] | [
"TAGS\n#transformers #safetensors #stablelm #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
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. -->
# mbart-neutralization
This model is a fine-tuned version of [facebook/mbart-large-50](https://huggingface.co/facebook/mbart-large-50) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 3.0459
- Bleu: 8.565
- Gen Len: 20.9268
## 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: 5.6e-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: 2
### Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|
| No log | 1.0 | 16 | 3.7800 | 7.2466 | 18.8049 |
| No log | 2.0 | 32 | 3.0459 | 8.565 | 20.9268 |
### Framework versions
- Transformers 4.39.3
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
| {"license": "mit", "tags": ["simplification", "generated_from_trainer"], "metrics": ["bleu"], "base_model": "facebook/mbart-large-50", "model-index": [{"name": "mbart-neutralization", "results": []}]} | crrodrvi/mbart-neutralization | null | [
"transformers",
"safetensors",
"mbart",
"text2text-generation",
"simplification",
"generated_from_trainer",
"base_model:facebook/mbart-large-50",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"has_space",
"region:us"
] | null | 2024-04-17T19:00:15+00:00 | [] | [] | TAGS
#transformers #safetensors #mbart #text2text-generation #simplification #generated_from_trainer #base_model-facebook/mbart-large-50 #license-mit #autotrain_compatible #endpoints_compatible #has_space #region-us
| mbart-neutralization
====================
This model is a fine-tuned version of facebook/mbart-large-50 on an unknown dataset.
It achieves the following results on the evaluation set:
* Loss: 3.0459
* Bleu: 8.565
* Gen Len: 20.9268
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: 5.6e-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: 2
### Training results
### Framework versions
* Transformers 4.39.3
* Pytorch 2.2.1+cu121
* Datasets 2.18.0
* Tokenizers 0.15.2
| [
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 5.6e-05\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 2",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.39.3\n* Pytorch 2.2.1+cu121\n* Datasets 2.18.0\n* Tokenizers 0.15.2"
] | [
"TAGS\n#transformers #safetensors #mbart #text2text-generation #simplification #generated_from_trainer #base_model-facebook/mbart-large-50 #license-mit #autotrain_compatible #endpoints_compatible #has_space #region-us \n",
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 5.6e-05\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 2",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.39.3\n* Pytorch 2.2.1+cu121\n* Datasets 2.18.0\n* Tokenizers 0.15.2"
] |
text-generation | transformers | # WestIceLemonTeaRP-32k-7b
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
## Merge Details
Prompt template: Alpaca, maybe ChatML
* measurement.json for quanting exl2 included.
- [4.2bpw-exl2](https://huggingface.co/icefog72/WestIceLemonTeaRP-32k-7b-4.2bpw-exl2)
- [6.5bpw-exl2](https://huggingface.co/icefog72/WestIceLemonTeaRP-32k-7b-6.5bpw-exl2)
- [8bpw-exl2](https://huggingface.co/icefog72/WestIceLemonTeaRP-32k-7b-8bpw-exl2)
thx mradermacher and SilverFan for
* [mradermacher/WestIceLemonTeaRP-32k-GGUF](https://huggingface.co/mradermacher/WestIceLemonTeaRP-32k-GGUF)
* [SilverFan/WestIceLemonTeaRP-7b-32k-GGUF](https://huggingface.co/SilverFan/WestIceLemonTeaRP-7b-32k-GGUF)
### Merge Method
This model was merged using the SLERP merge method.
### Models Merged
The following models were included in the merge:
* [IceLemonTeaRP-32k-7b](https://huggingface.co/icefog72/IceLemonTeaRP-32k-7b)
* WestWizardIceLemonTeaRP
* [SeverusWestLake-7B-DPO](https://huggingface.co/s3nh/SeverusWestLake-7B-DPO)
* WizardIceLemonTeaRP
* [Not-WizardLM-2-7B](https://huggingface.co/amazingvince/Not-WizardLM-2-7B)
* [IceLemonTeaRP-32k-7b](https://huggingface.co/icefog72/IceLemonTeaRP-32k-7b)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
slices:
- sources:
- model: IceLemonTeaRP-32k-7b
layer_range: [0, 32]
- model: WestWizardIceLemonTeaRP
layer_range: [0, 32]
merge_method: slerp
base_model: IceLemonTeaRP-32k-7b
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: float16
```
# [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_icefog72__WestIceLemonTeaRP-32k-7b)
| Metric |Value|
|---------------------------------|----:|
|Avg. |71.27|
|AI2 Reasoning Challenge (25-Shot)|68.77|
|HellaSwag (10-Shot) |86.89|
|MMLU (5-Shot) |64.28|
|TruthfulQA (0-shot) |62.47|
|Winogrande (5-shot) |80.98|
|GSM8k (5-shot) |64.22|
| {"license": "cc-by-nc-4.0", "library_name": "transformers", "tags": ["mergekit", "merge", "alpaca", "mistral", "not-for-all-audiences", "nsfw"], "base_model": ["s3nh/SeverusWestLake-7B-DPO", "icefog72/IceLemonTeaRP-32k-7b", "amazingvince/Not-WizardLM-2-7B"], "model-index": [{"name": "WestIceLemonTeaRP-32k-7b", "results": [{"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "AI2 Reasoning Challenge (25-Shot)", "type": "ai2_arc", "config": "ARC-Challenge", "split": "test", "args": {"num_few_shot": 25}}, "metrics": [{"type": "acc_norm", "value": 68.77, "name": "normalized accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=icefog72/WestIceLemonTeaRP-32k-7b", "name": "Open LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "HellaSwag (10-Shot)", "type": "hellaswag", "split": "validation", "args": {"num_few_shot": 10}}, "metrics": [{"type": "acc_norm", "value": 86.89, "name": "normalized accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=icefog72/WestIceLemonTeaRP-32k-7b", "name": "Open LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "MMLU (5-Shot)", "type": "cais/mmlu", "config": "all", "split": "test", "args": {"num_few_shot": 5}}, "metrics": [{"type": "acc", "value": 64.28, "name": "accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=icefog72/WestIceLemonTeaRP-32k-7b", "name": "Open LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "TruthfulQA (0-shot)", "type": "truthful_qa", "config": "multiple_choice", "split": "validation", "args": {"num_few_shot": 0}}, "metrics": [{"type": "mc2", "value": 62.47}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=icefog72/WestIceLemonTeaRP-32k-7b", "name": "Open LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "Winogrande (5-shot)", "type": "winogrande", "config": "winogrande_xl", "split": "validation", "args": {"num_few_shot": 5}}, "metrics": [{"type": "acc", "value": 80.98, "name": "accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=icefog72/WestIceLemonTeaRP-32k-7b", "name": "Open LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "GSM8k (5-shot)", "type": "gsm8k", "config": "main", "split": "test", "args": {"num_few_shot": 5}}, "metrics": [{"type": "acc", "value": 64.22, "name": "accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=icefog72/WestIceLemonTeaRP-32k-7b", "name": "Open LLM Leaderboard"}}]}]} | icefog72/WestIceLemonTeaRP-32k-7b | null | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"mergekit",
"merge",
"alpaca",
"not-for-all-audiences",
"nsfw",
"base_model:s3nh/SeverusWestLake-7B-DPO",
"base_model:icefog72/IceLemonTeaRP-32k-7b",
"base_model:amazingvince/Not-WizardLM-2-7B",
"license:cc-by-nc-4.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-04-17T19:05:05+00:00 | [] | [] | TAGS
#transformers #safetensors #mistral #text-generation #mergekit #merge #alpaca #not-for-all-audiences #nsfw #base_model-s3nh/SeverusWestLake-7B-DPO #base_model-icefog72/IceLemonTeaRP-32k-7b #base_model-amazingvince/Not-WizardLM-2-7B #license-cc-by-nc-4.0 #model-index #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us
| WestIceLemonTeaRP-32k-7b
========================
!image/png
This is a merge of pre-trained language models created using mergekit.
Merge Details
-------------
Prompt template: Alpaca, maybe ChatML
* URL for quanting exl2 included.
* 4.2bpw-exl2
* 6.5bpw-exl2
* 8bpw-exl2
thx mradermacher and SilverFan for
* mradermacher/WestIceLemonTeaRP-32k-GGUF
* SilverFan/WestIceLemonTeaRP-7b-32k-GGUF
### Merge Method
This model was merged using the SLERP merge method.
### Models Merged
The following models were included in the merge:
* IceLemonTeaRP-32k-7b
* WestWizardIceLemonTeaRP
+ SeverusWestLake-7B-DPO
+ WizardIceLemonTeaRP
- Not-WizardLM-2-7B
- IceLemonTeaRP-32k-7b
### Configuration
The following YAML configuration was used to produce this model:
!image/png
Open LLM Leaderboard Evaluation Results
=======================================
Detailed results can be found here
| [
"### Merge Method\n\n\nThis model was merged using the SLERP merge method.",
"### Models Merged\n\n\nThe following models were included in the merge:\n\n\n* IceLemonTeaRP-32k-7b\n* WestWizardIceLemonTeaRP\n\t+ SeverusWestLake-7B-DPO\n\t+ WizardIceLemonTeaRP\n\t\t- Not-WizardLM-2-7B\n\t\t- IceLemonTeaRP-32k-7b",
"### Configuration\n\n\nThe following YAML configuration was used to produce this model:\n\n\n!image/png\n\n\nOpen LLM Leaderboard Evaluation Results\n=======================================\n\n\nDetailed results can be found here"
] | [
"TAGS\n#transformers #safetensors #mistral #text-generation #mergekit #merge #alpaca #not-for-all-audiences #nsfw #base_model-s3nh/SeverusWestLake-7B-DPO #base_model-icefog72/IceLemonTeaRP-32k-7b #base_model-amazingvince/Not-WizardLM-2-7B #license-cc-by-nc-4.0 #model-index #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n",
"### Merge Method\n\n\nThis model was merged using the SLERP merge method.",
"### Models Merged\n\n\nThe following models were included in the merge:\n\n\n* IceLemonTeaRP-32k-7b\n* WestWizardIceLemonTeaRP\n\t+ SeverusWestLake-7B-DPO\n\t+ WizardIceLemonTeaRP\n\t\t- Not-WizardLM-2-7B\n\t\t- IceLemonTeaRP-32k-7b",
"### Configuration\n\n\nThe following YAML configuration was used to produce this model:\n\n\n!image/png\n\n\nOpen LLM Leaderboard Evaluation Results\n=======================================\n\n\nDetailed results can be found here"
] |
text-generation | transformers |
This is an upscaled fp16 variant of the original Mistral-7b-Instruct-v0.2 base model by Mistral after it has been loaded with nf4 4-bit quantization via bitsandbytes.
The main idea here is to upscale the linear4bit layers to fp16 so that the quantization/dequantization cost doesn't have to paid for each forward pass at inference time.
_Note: The quantization operation to nf4 is not lossless, so the model weights for the linear layers are lossy, which means that this model will not work as well as the official base model._
To use this model, you can just load it via `transformers` in fp16:
```python
import torch
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained(
"predibase/Mistral-7B-Instruct-v0.2-dequantized",
device_map="auto",
torch_dtype=torch.float16,
)
``` | {"license": "apache-2.0", "tags": ["text-generation-inference"]} | predibase/Mistral-7B-Instruct-v0.2-dequantized | null | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"text-generation-inference",
"conversational",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-04-17T19:07:00+00:00 | [] | [] | TAGS
#transformers #safetensors #mistral #text-generation #text-generation-inference #conversational #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us
|
This is an upscaled fp16 variant of the original Mistral-7b-Instruct-v0.2 base model by Mistral after it has been loaded with nf4 4-bit quantization via bitsandbytes.
The main idea here is to upscale the linear4bit layers to fp16 so that the quantization/dequantization cost doesn't have to paid for each forward pass at inference time.
_Note: The quantization operation to nf4 is not lossless, so the model weights for the linear layers are lossy, which means that this model will not work as well as the official base model._
To use this model, you can just load it via 'transformers' in fp16:
| [] | [
"TAGS\n#transformers #safetensors #mistral #text-generation #text-generation-inference #conversational #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n"
] |
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. -->
# model_hh_usp1_200
This model is a fine-tuned version of [meta-llama/Llama-2-7b-chat-hf](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.4318
- Rewards/chosen: 1.1781
- Rewards/rejected: -0.7550
- Rewards/accuracies: 0.6400
- Rewards/margins: 1.9331
- Logps/rejected: -116.8458
- Logps/chosen: -108.3717
- Logits/rejected: -0.0587
- Logits/chosen: -0.0585
## 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: 4
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- training_steps: 1000
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
| 0.0 | 8.0 | 100 | 1.3976 | 1.5497 | -0.4049 | 0.6200 | 1.9546 | -116.4568 | -107.9588 | -0.0493 | -0.0483 |
| 0.0 | 16.0 | 200 | 1.4110 | 1.4142 | -0.5150 | 0.6500 | 1.9292 | -116.5792 | -108.1093 | -0.0538 | -0.0530 |
| 0.0 | 24.0 | 300 | 1.4038 | 1.3748 | -0.6170 | 0.6400 | 1.9918 | -116.6925 | -108.1531 | -0.0554 | -0.0545 |
| 0.0 | 32.0 | 400 | 1.4365 | 1.2965 | -0.6346 | 0.6600 | 1.9311 | -116.7121 | -108.2401 | -0.0555 | -0.0551 |
| 0.0 | 40.0 | 500 | 1.4139 | 1.2582 | -0.6992 | 0.6400 | 1.9574 | -116.7839 | -108.2827 | -0.0582 | -0.0580 |
| 0.0 | 48.0 | 600 | 1.4155 | 1.2234 | -0.7385 | 0.6400 | 1.9619 | -116.8275 | -108.3214 | -0.0572 | -0.0570 |
| 0.0 | 56.0 | 700 | 1.4050 | 1.2174 | -0.7564 | 0.6600 | 1.9738 | -116.8474 | -108.3280 | -0.0586 | -0.0582 |
| 0.0 | 64.0 | 800 | 1.4250 | 1.1984 | -0.7478 | 0.6500 | 1.9462 | -116.8379 | -108.3491 | -0.0589 | -0.0586 |
| 0.0 | 72.0 | 900 | 1.4309 | 1.1891 | -0.7289 | 0.6400 | 1.9180 | -116.8168 | -108.3594 | -0.0588 | -0.0585 |
| 0.0 | 80.0 | 1000 | 1.4318 | 1.1781 | -0.7550 | 0.6400 | 1.9331 | -116.8458 | -108.3717 | -0.0587 | -0.0585 |
### Framework versions
- PEFT 0.10.0
- Transformers 4.39.1
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2 | {"license": "llama2", "library_name": "peft", "tags": ["trl", "dpo", "generated_from_trainer"], "base_model": "meta-llama/Llama-2-7b-chat-hf", "model-index": [{"name": "model_hh_usp1_200", "results": []}]} | guoyu-zhang/model_hh_usp1_200 | null | [
"peft",
"safetensors",
"trl",
"dpo",
"generated_from_trainer",
"base_model:meta-llama/Llama-2-7b-chat-hf",
"license:llama2",
"region:us"
] | null | 2024-04-17T19:10:34+00:00 | [] | [] | TAGS
#peft #safetensors #trl #dpo #generated_from_trainer #base_model-meta-llama/Llama-2-7b-chat-hf #license-llama2 #region-us
| model\_hh\_usp1\_200
====================
This model is a fine-tuned version of meta-llama/Llama-2-7b-chat-hf on an unknown dataset.
It achieves the following results on the evaluation set:
* Loss: 1.4318
* Rewards/chosen: 1.1781
* Rewards/rejected: -0.7550
* Rewards/accuracies: 0.6400
* Rewards/margins: 1.9331
* Logps/rejected: -116.8458
* Logps/chosen: -108.3717
* Logits/rejected: -0.0587
* Logits/chosen: -0.0585
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: 4
* eval\_batch\_size: 1
* seed: 42
* gradient\_accumulation\_steps: 4
* total\_train\_batch\_size: 16
* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
* lr\_scheduler\_type: cosine
* lr\_scheduler\_warmup\_steps: 100
* training\_steps: 1000
### Training results
### Framework versions
* PEFT 0.10.0
* Transformers 4.39.1
* Pytorch 2.2.1+cu121
* Datasets 2.18.0
* Tokenizers 0.15.2
| [
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 4\n* eval\\_batch\\_size: 1\n* seed: 42\n* gradient\\_accumulation\\_steps: 4\n* total\\_train\\_batch\\_size: 16\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: cosine\n* lr\\_scheduler\\_warmup\\_steps: 100\n* training\\_steps: 1000",
"### Training results",
"### Framework versions\n\n\n* PEFT 0.10.0\n* Transformers 4.39.1\n* Pytorch 2.2.1+cu121\n* Datasets 2.18.0\n* Tokenizers 0.15.2"
] | [
"TAGS\n#peft #safetensors #trl #dpo #generated_from_trainer #base_model-meta-llama/Llama-2-7b-chat-hf #license-llama2 #region-us \n",
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 4\n* eval\\_batch\\_size: 1\n* seed: 42\n* gradient\\_accumulation\\_steps: 4\n* total\\_train\\_batch\\_size: 16\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: cosine\n* lr\\_scheduler\\_warmup\\_steps: 100\n* training\\_steps: 1000",
"### Training results",
"### Framework versions\n\n\n* PEFT 0.10.0\n* Transformers 4.39.1\n* Pytorch 2.2.1+cu121\n* Datasets 2.18.0\n* Tokenizers 0.15.2"
] |
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. -->
# lmd-4bars-2048-epochs7
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 4.7679
## 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: 0.005
- train_batch_size: 8
- eval_batch_size: 4
- seed: 1
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.01
- num_epochs: 7
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 4.9268 | 4.17 | 5000 | 4.7679 |
### Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
| {"license": "mit", "tags": ["generated_from_trainer"], "base_model": "gpt2", "model-index": [{"name": "lmd-4bars-2048-epochs7", "results": []}]} | MikeMpapa/lmd-4bars-2048-epochs01 | null | [
"transformers",
"safetensors",
"gpt2",
"text-generation",
"generated_from_trainer",
"base_model:gpt2",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-04-17T19:12:01+00:00 | [] | [] | TAGS
#transformers #safetensors #gpt2 #text-generation #generated_from_trainer #base_model-gpt2 #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us
| lmd-4bars-2048-epochs7
======================
This model is a fine-tuned version of gpt2 on an unknown dataset.
It achieves the following results on the evaluation set:
* Loss: 4.7679
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: 0.005
* train\_batch\_size: 8
* eval\_batch\_size: 4
* seed: 1
* gradient\_accumulation\_steps: 2
* total\_train\_batch\_size: 16
* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
* lr\_scheduler\_type: cosine
* lr\_scheduler\_warmup\_ratio: 0.01
* num\_epochs: 7
### Training results
### Framework versions
* Transformers 4.38.2
* Pytorch 2.2.1+cu121
* Datasets 2.18.0
* Tokenizers 0.15.2
| [
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.005\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 4\n* seed: 1\n* gradient\\_accumulation\\_steps: 2\n* total\\_train\\_batch\\_size: 16\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: cosine\n* lr\\_scheduler\\_warmup\\_ratio: 0.01\n* num\\_epochs: 7",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.38.2\n* Pytorch 2.2.1+cu121\n* Datasets 2.18.0\n* Tokenizers 0.15.2"
] | [
"TAGS\n#transformers #safetensors #gpt2 #text-generation #generated_from_trainer #base_model-gpt2 #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n",
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.005\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 4\n* seed: 1\n* gradient\\_accumulation\\_steps: 2\n* total\\_train\\_batch\\_size: 16\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: cosine\n* lr\\_scheduler\\_warmup\\_ratio: 0.01\n* num\\_epochs: 7",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.38.2\n* Pytorch 2.2.1+cu121\n* Datasets 2.18.0\n* Tokenizers 0.15.2"
] |
text-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": []} | engine58848/ejiwdmes_sn5_61 | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-04-17T19:12:55+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #safetensors #llama #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
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:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
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.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
| [
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] | [
"TAGS\n#transformers #safetensors #llama #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
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. -->
# roberta-depression-detection-v2
This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1526
## 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: 4e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 15
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 0.0638 | 1.0 | 219 | 0.1825 |
| 0.1153 | 2.0 | 438 | 0.1958 |
| 0.0889 | 3.0 | 657 | 0.1526 |
| 0.1195 | 4.0 | 876 | 0.1719 |
| 0.0549 | 5.0 | 1095 | 0.2569 |
| 0.0826 | 6.0 | 1314 | 0.2401 |
| 0.0003 | 7.0 | 1533 | 0.2451 |
| 0.0014 | 8.0 | 1752 | 0.2236 |
| 0.0203 | 9.0 | 1971 | 0.2277 |
| 0.0 | 10.0 | 2190 | 0.2936 |
| 0.0 | 11.0 | 2409 | 0.3109 |
| 0.0 | 12.0 | 2628 | 0.2806 |
| 0.0 | 13.0 | 2847 | 0.2772 |
| 0.0 | 14.0 | 3066 | 0.2792 |
| 0.0 | 15.0 | 3285 | 0.2801 |
### Framework versions
- Transformers 4.26.1
- Pytorch 2.1.0+cpu
- Datasets 2.10.1
- Tokenizers 0.13.2
| {"license": "mit", "tags": ["generated_from_trainer"], "model-index": [{"name": "roberta-depression-detection-v2", "results": []}]} | almafaz/roberta-depression-detection-v2 | null | [
"transformers",
"pytorch",
"tensorboard",
"safetensors",
"roberta",
"text-classification",
"generated_from_trainer",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-04-17T19:14:21+00:00 | [] | [] | TAGS
#transformers #pytorch #tensorboard #safetensors #roberta #text-classification #generated_from_trainer #license-mit #autotrain_compatible #endpoints_compatible #region-us
| roberta-depression-detection-v2
===============================
This model is a fine-tuned version of roberta-base on the None dataset.
It achieves the following results on the evaluation set:
* Loss: 0.1526
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: 4e-05
* train\_batch\_size: 16
* eval\_batch\_size: 16
* seed: 42
* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
* lr\_scheduler\_type: linear
* lr\_scheduler\_warmup\_steps: 500
* num\_epochs: 15
### Training results
### Framework versions
* Transformers 4.26.1
* Pytorch 2.1.0+cpu
* Datasets 2.10.1
* Tokenizers 0.13.2
| [
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 4e-05\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 16\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_steps: 500\n* num\\_epochs: 15",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.26.1\n* Pytorch 2.1.0+cpu\n* Datasets 2.10.1\n* Tokenizers 0.13.2"
] | [
"TAGS\n#transformers #pytorch #tensorboard #safetensors #roberta #text-classification #generated_from_trainer #license-mit #autotrain_compatible #endpoints_compatible #region-us \n",
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 4e-05\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 16\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_steps: 500\n* num\\_epochs: 15",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.26.1\n* Pytorch 2.1.0+cpu\n* Datasets 2.10.1\n* Tokenizers 0.13.2"
] |
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. -->
# cnn_dailymail_3864_bart-base
This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.9201
- Rouge1: 0.2472
- Rouge2: 0.1256
- Rougel: 0.2063
- Rougelsum: 0.2331
- Gen Len: 20.0
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 10
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
| 1.2077 | 0.11 | 500 | 1.0668 | 0.2378 | 0.1128 | 0.1955 | 0.2228 | 20.0 |
| 1.1503 | 0.22 | 1000 | 1.0418 | 0.2376 | 0.1145 | 0.1964 | 0.223 | 20.0 |
| 1.1191 | 0.33 | 1500 | 1.0109 | 0.2409 | 0.1187 | 0.1995 | 0.2268 | 20.0 |
| 1.0828 | 0.45 | 2000 | 1.0048 | 0.2408 | 0.1192 | 0.2004 | 0.227 | 20.0 |
| 1.0546 | 0.56 | 2500 | 0.9911 | 0.2417 | 0.1206 | 0.2008 | 0.2278 | 20.0 |
| 1.0537 | 0.67 | 3000 | 0.9891 | 0.2418 | 0.1201 | 0.2014 | 0.2277 | 20.0 |
| 1.0643 | 0.78 | 3500 | 0.9895 | 0.2396 | 0.1194 | 0.1997 | 0.2259 | 20.0 |
| 1.0375 | 0.89 | 4000 | 0.9775 | 0.2434 | 0.122 | 0.2025 | 0.2293 | 20.0 |
| 1.013 | 1.0 | 4500 | 0.9728 | 0.244 | 0.1218 | 0.2029 | 0.2298 | 20.0 |
| 1.0247 | 1.11 | 5000 | 0.9705 | 0.243 | 0.1206 | 0.2019 | 0.2287 | 20.0 |
| 1.0374 | 1.23 | 5500 | 0.9642 | 0.2432 | 0.1217 | 0.2022 | 0.2292 | 20.0 |
| 1.0084 | 1.34 | 6000 | 0.9609 | 0.2437 | 0.1235 | 0.204 | 0.2299 | 20.0 |
| 1.0195 | 1.45 | 6500 | 0.9603 | 0.243 | 0.1221 | 0.2029 | 0.2291 | 20.0 |
| 0.9642 | 1.56 | 7000 | 0.9559 | 0.2438 | 0.1228 | 0.2035 | 0.2301 | 20.0 |
| 0.9903 | 1.67 | 7500 | 0.9540 | 0.243 | 0.1225 | 0.2029 | 0.2293 | 20.0 |
| 0.976 | 1.78 | 8000 | 0.9518 | 0.2434 | 0.1224 | 0.2025 | 0.2297 | 19.9997 |
| 1.0101 | 1.89 | 8500 | 0.9460 | 0.2452 | 0.1235 | 0.2042 | 0.231 | 20.0 |
| 0.9711 | 2.01 | 9000 | 0.9446 | 0.2431 | 0.1226 | 0.2032 | 0.2295 | 19.9995 |
| 0.9137 | 2.12 | 9500 | 0.9463 | 0.2459 | 0.1239 | 0.205 | 0.2318 | 20.0 |
| 0.9631 | 2.23 | 10000 | 0.9410 | 0.2451 | 0.1234 | 0.2043 | 0.2309 | 19.9999 |
| 0.9309 | 2.34 | 10500 | 0.9399 | 0.2446 | 0.1236 | 0.2042 | 0.2308 | 19.9991 |
| 0.9653 | 2.45 | 11000 | 0.9363 | 0.2444 | 0.1233 | 0.2039 | 0.2308 | 19.9999 |
| 0.9338 | 2.56 | 11500 | 0.9413 | 0.2439 | 0.1224 | 0.2028 | 0.2294 | 20.0 |
| 0.9373 | 2.67 | 12000 | 0.9334 | 0.245 | 0.1241 | 0.2047 | 0.2312 | 19.9996 |
| 0.9661 | 2.79 | 12500 | 0.9334 | 0.2456 | 0.1241 | 0.2051 | 0.2318 | 19.9999 |
| 0.9446 | 2.9 | 13000 | 0.9340 | 0.2447 | 0.1239 | 0.2045 | 0.2309 | 19.9999 |
| 0.9109 | 3.01 | 13500 | 0.9340 | 0.2445 | 0.1234 | 0.2041 | 0.2308 | 19.9999 |
| 0.8955 | 3.12 | 14000 | 0.9357 | 0.2459 | 0.1249 | 0.2055 | 0.2318 | 20.0 |
| 0.9163 | 3.23 | 14500 | 0.9319 | 0.2461 | 0.1239 | 0.205 | 0.2319 | 20.0 |
| 0.9059 | 3.34 | 15000 | 0.9320 | 0.2446 | 0.124 | 0.2044 | 0.2309 | 19.9997 |
| 0.8893 | 3.46 | 15500 | 0.9288 | 0.2462 | 0.1247 | 0.2053 | 0.2322 | 19.9999 |
| 0.8963 | 3.57 | 16000 | 0.9301 | 0.2441 | 0.124 | 0.2043 | 0.2306 | 20.0 |
| 0.8924 | 3.68 | 16500 | 0.9295 | 0.2431 | 0.1236 | 0.2038 | 0.2296 | 19.9997 |
| 0.8832 | 3.79 | 17000 | 0.9267 | 0.2457 | 0.1237 | 0.2049 | 0.2316 | 19.9999 |
| 0.8874 | 3.9 | 17500 | 0.9263 | 0.2458 | 0.125 | 0.2054 | 0.232 | 20.0 |
| 0.8464 | 4.01 | 18000 | 0.9272 | 0.2446 | 0.1234 | 0.2039 | 0.2305 | 20.0 |
| 0.8391 | 4.12 | 18500 | 0.9253 | 0.2453 | 0.1245 | 0.205 | 0.2313 | 20.0 |
| 0.8602 | 4.24 | 19000 | 0.9273 | 0.2464 | 0.1248 | 0.2055 | 0.2322 | 19.9997 |
| 0.8674 | 4.35 | 19500 | 0.9260 | 0.2449 | 0.1242 | 0.2047 | 0.2309 | 20.0 |
| 0.8634 | 4.46 | 20000 | 0.9261 | 0.2462 | 0.1248 | 0.2053 | 0.2322 | 20.0 |
| 0.8522 | 4.57 | 20500 | 0.9259 | 0.2456 | 0.1242 | 0.2052 | 0.2316 | 20.0 |
| 0.8532 | 4.68 | 21000 | 0.9256 | 0.2452 | 0.1242 | 0.2049 | 0.2315 | 20.0 |
| 0.8608 | 4.79 | 21500 | 0.9218 | 0.2446 | 0.1242 | 0.2049 | 0.2309 | 19.9997 |
| 0.8649 | 4.9 | 22000 | 0.9239 | 0.2461 | 0.1243 | 0.2047 | 0.2317 | 19.9997 |
| 0.8329 | 5.02 | 22500 | 0.9260 | 0.2456 | 0.1248 | 0.2052 | 0.2315 | 19.9999 |
| 0.8475 | 5.13 | 23000 | 0.9247 | 0.2449 | 0.1241 | 0.2045 | 0.2309 | 20.0 |
| 0.8595 | 5.24 | 23500 | 0.9246 | 0.2443 | 0.1239 | 0.2044 | 0.2306 | 20.0 |
| 0.8707 | 5.35 | 24000 | 0.9228 | 0.2458 | 0.1246 | 0.2054 | 0.2318 | 19.9997 |
| 0.8565 | 5.46 | 24500 | 0.9243 | 0.245 | 0.1241 | 0.2047 | 0.231 | 20.0 |
| 0.848 | 5.57 | 25000 | 0.9232 | 0.2464 | 0.1256 | 0.206 | 0.2324 | 20.0 |
| 0.8251 | 5.68 | 25500 | 0.9212 | 0.2465 | 0.1253 | 0.2057 | 0.2327 | 20.0 |
| 0.8352 | 5.8 | 26000 | 0.9203 | 0.245 | 0.1242 | 0.2043 | 0.2309 | 19.9996 |
| 0.837 | 5.91 | 26500 | 0.9178 | 0.2464 | 0.1247 | 0.2055 | 0.2321 | 19.9999 |
| 0.8233 | 6.02 | 27000 | 0.9204 | 0.2456 | 0.1247 | 0.2052 | 0.2318 | 20.0 |
| 0.8169 | 6.13 | 27500 | 0.9246 | 0.2454 | 0.1242 | 0.205 | 0.2314 | 20.0 |
| 0.8351 | 6.24 | 28000 | 0.9194 | 0.2453 | 0.1248 | 0.2052 | 0.2312 | 20.0 |
| 0.8275 | 6.35 | 28500 | 0.9221 | 0.2468 | 0.1255 | 0.2062 | 0.2329 | 19.9999 |
| 0.818 | 6.46 | 29000 | 0.9244 | 0.2456 | 0.1243 | 0.205 | 0.2316 | 20.0 |
| 0.8262 | 6.58 | 29500 | 0.9194 | 0.2471 | 0.1256 | 0.2064 | 0.233 | 20.0 |
| 0.8138 | 6.69 | 30000 | 0.9225 | 0.2469 | 0.1257 | 0.2062 | 0.233 | 20.0 |
| 0.8476 | 6.8 | 30500 | 0.9188 | 0.2467 | 0.1254 | 0.2059 | 0.2328 | 20.0 |
| 0.8376 | 6.91 | 31000 | 0.9216 | 0.2473 | 0.1255 | 0.2064 | 0.2331 | 20.0 |
| 0.7947 | 7.02 | 31500 | 0.9218 | 0.2471 | 0.1256 | 0.2061 | 0.2329 | 19.9999 |
| 0.7937 | 7.13 | 32000 | 0.9241 | 0.2465 | 0.1249 | 0.2057 | 0.2324 | 19.9996 |
| 0.8194 | 7.24 | 32500 | 0.9230 | 0.2471 | 0.1259 | 0.2063 | 0.2329 | 20.0 |
| 0.8122 | 7.36 | 33000 | 0.9204 | 0.2458 | 0.125 | 0.2055 | 0.232 | 19.9996 |
| 0.7676 | 7.47 | 33500 | 0.9232 | 0.2468 | 0.1253 | 0.206 | 0.2327 | 20.0 |
| 0.7772 | 7.58 | 34000 | 0.9226 | 0.2463 | 0.1251 | 0.2057 | 0.2323 | 20.0 |
| 0.809 | 7.69 | 34500 | 0.9197 | 0.2469 | 0.1255 | 0.2061 | 0.2329 | 19.9997 |
| 0.7839 | 7.8 | 35000 | 0.9205 | 0.2475 | 0.1261 | 0.2067 | 0.2334 | 19.9997 |
| 0.7936 | 7.91 | 35500 | 0.9186 | 0.2469 | 0.1254 | 0.2061 | 0.2327 | 19.9997 |
| 0.8108 | 8.02 | 36000 | 0.9215 | 0.2472 | 0.1253 | 0.206 | 0.2329 | 20.0 |
| 0.7987 | 8.14 | 36500 | 0.9219 | 0.2473 | 0.1254 | 0.2062 | 0.2331 | 19.9999 |
| 0.7881 | 8.25 | 37000 | 0.9213 | 0.2474 | 0.1253 | 0.206 | 0.233 | 20.0 |
| 0.8007 | 8.36 | 37500 | 0.9215 | 0.2474 | 0.1258 | 0.2064 | 0.2332 | 20.0 |
| 0.7789 | 8.47 | 38000 | 0.9226 | 0.2462 | 0.1252 | 0.2054 | 0.2321 | 20.0 |
| 0.8155 | 8.58 | 38500 | 0.9182 | 0.2465 | 0.1254 | 0.206 | 0.2325 | 19.9999 |
| 0.7863 | 8.69 | 39000 | 0.9187 | 0.2465 | 0.1252 | 0.2059 | 0.2323 | 19.9999 |
| 0.796 | 8.8 | 39500 | 0.9201 | 0.2469 | 0.1254 | 0.206 | 0.2327 | 19.9999 |
| 0.8003 | 8.92 | 40000 | 0.9197 | 0.2463 | 0.1252 | 0.2057 | 0.2323 | 20.0 |
| 0.803 | 9.03 | 40500 | 0.9206 | 0.2465 | 0.1253 | 0.2058 | 0.2323 | 19.9997 |
| 0.79 | 9.14 | 41000 | 0.9221 | 0.2467 | 0.1251 | 0.206 | 0.2326 | 19.9997 |
| 0.7605 | 9.25 | 41500 | 0.9211 | 0.247 | 0.1254 | 0.2059 | 0.2329 | 20.0 |
| 0.7543 | 9.36 | 42000 | 0.9214 | 0.2473 | 0.1258 | 0.2065 | 0.2333 | 19.9999 |
| 0.7959 | 9.47 | 42500 | 0.9203 | 0.2471 | 0.1255 | 0.2061 | 0.2332 | 19.9999 |
| 0.7826 | 9.58 | 43000 | 0.9205 | 0.2469 | 0.1256 | 0.206 | 0.2329 | 20.0 |
| 0.7835 | 9.7 | 43500 | 0.9198 | 0.2466 | 0.1252 | 0.2057 | 0.2326 | 20.0 |
| 0.7809 | 9.81 | 44000 | 0.9205 | 0.2469 | 0.1253 | 0.206 | 0.2328 | 20.0 |
| 0.7899 | 9.92 | 44500 | 0.9201 | 0.2472 | 0.1256 | 0.2063 | 0.2331 | 20.0 |
### Framework versions
- Transformers 4.38.2
- Pytorch 2.0.0+cu117
- Datasets 2.18.0
- Tokenizers 0.15.2
| {"license": "apache-2.0", "tags": ["generated_from_trainer"], "metrics": ["rouge"], "base_model": "facebook/bart-base", "model-index": [{"name": "cnn_dailymail_3864_bart-base", "results": []}]} | baek26/cnn_dailymail_3864_bart-base | null | [
"transformers",
"safetensors",
"bart",
"text2text-generation",
"generated_from_trainer",
"base_model:facebook/bart-base",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-04-17T19:14:38+00:00 | [] | [] | TAGS
#transformers #safetensors #bart #text2text-generation #generated_from_trainer #base_model-facebook/bart-base #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us
| cnn\_dailymail\_3864\_bart-base
===============================
This model is a fine-tuned version of facebook/bart-base on an unknown dataset.
It achieves the following results on the evaluation set:
* Loss: 0.9201
* Rouge1: 0.2472
* Rouge2: 0.1256
* Rougel: 0.2063
* Rougelsum: 0.2331
* Gen Len: 20.0
Model description
-----------------
More information needed
Intended uses & limitations
---------------------------
More information needed
Training and evaluation data
----------------------------
More information needed
Training procedure
------------------
### Training hyperparameters
The following hyperparameters were used during training:
* learning\_rate: 5e-05
* train\_batch\_size: 4
* eval\_batch\_size: 4
* seed: 42
* gradient\_accumulation\_steps: 16
* total\_train\_batch\_size: 64
* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
* lr\_scheduler\_type: linear
* lr\_scheduler\_warmup\_steps: 500
* num\_epochs: 10
### Training results
### Framework versions
* Transformers 4.38.2
* Pytorch 2.0.0+cu117
* Datasets 2.18.0
* Tokenizers 0.15.2
| [
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 5e-05\n* train\\_batch\\_size: 4\n* eval\\_batch\\_size: 4\n* seed: 42\n* gradient\\_accumulation\\_steps: 16\n* total\\_train\\_batch\\_size: 64\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_steps: 500\n* num\\_epochs: 10",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.38.2\n* Pytorch 2.0.0+cu117\n* Datasets 2.18.0\n* Tokenizers 0.15.2"
] | [
"TAGS\n#transformers #safetensors #bart #text2text-generation #generated_from_trainer #base_model-facebook/bart-base #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n",
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 5e-05\n* train\\_batch\\_size: 4\n* eval\\_batch\\_size: 4\n* seed: 42\n* gradient\\_accumulation\\_steps: 16\n* total\\_train\\_batch\\_size: 64\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_steps: 500\n* num\\_epochs: 10",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.38.2\n* Pytorch 2.0.0+cu117\n* Datasets 2.18.0\n* Tokenizers 0.15.2"
] |
text-generation | transformers |
# Model Card for Mixtral-8x22B-Instruct-v0.1
The Mixtral-8x22B-Instruct-v0.1 Large Language Model (LLM) is an instruct fine-tuned version of the [Mixtral-8x22B-v0.1](https://huggingface.co/mistralai/Mixtral-8x22B-v0.1).
Model added by [Prince Canuma](https://twitter.com/Prince_Canuma).
## Run the model
```python
from transformers import AutoModelForCausalLM
from mistral_common.protocol.instruct.messages import (
AssistantMessage,
UserMessage,
)
from mistral_common.protocol.instruct.tool_calls import (
Tool,
Function,
)
from mistral_common.tokens.tokenizers.mistral import MistralTokenizer
from mistral_common.tokens.instruct.normalize import ChatCompletionRequest
device = "cuda" # the device to load the model onto
tokenizer_v3 = MistralTokenizer.v3()
mistral_query = ChatCompletionRequest(
tools=[
Tool(
function=Function(
name="get_current_weather",
description="Get the current weather",
parameters={
"type": "object",
"properties": {
"location": {
"type": "string",
"description": "The city and state, e.g. San Francisco, CA",
},
"format": {
"type": "string",
"enum": ["celsius", "fahrenheit"],
"description": "The temperature unit to use. Infer this from the users location.",
},
},
"required": ["location", "format"],
},
)
)
],
messages=[
UserMessage(content="What's the weather like today in Paris"),
],
model="test",
)
encodeds = tokenizer_v3.encode_chat_completion(mistral_query).tokens
model = AutoModelForCausalLM.from_pretrained("mistralai/Mixtral-8x22B-Instruct-v0.1")
model_inputs = encodeds.to(device)
model.to(device)
generated_ids = model.generate(model_inputs, max_new_tokens=1000, do_sample=True)
sp_tokenizer = tokenizer_v3.instruct_tokenizer.tokenizer
decoded = sp_tokenizer.decode(generated_ids[0])
print(decoded)
```
# Instruct tokenizer
The HuggingFace tokenizer included in this release should match our own. To compare:
`pip install mistral-common`
```py
from mistral_common.protocol.instruct.messages import (
AssistantMessage,
UserMessage,
)
from mistral_common.tokens.tokenizers.mistral import MistralTokenizer
from mistral_common.tokens.instruct.normalize import ChatCompletionRequest
from transformers import AutoTokenizer
tokenizer_v3 = MistralTokenizer.v3()
mistral_query = ChatCompletionRequest(
messages=[
UserMessage(content="How many experts ?"),
AssistantMessage(content="8"),
UserMessage(content="How big ?"),
AssistantMessage(content="22B"),
UserMessage(content="Noice 🎉 !"),
],
model="test",
)
hf_messages = mistral_query.model_dump()['messages']
tokenized_mistral = tokenizer_v3.encode_chat_completion(mistral_query).tokens
tokenizer_hf = AutoTokenizer.from_pretrained('mistralai/Mixtral-8x22B-Instruct-v0.1')
tokenized_hf = tokenizer_hf.apply_chat_template(hf_messages, tokenize=True)
assert tokenized_hf == tokenized_mistral
```
# Function calling and special tokens
This tokenizer includes more special tokens, related to function calling :
- [TOOL_CALLS]
- [AVAILABLE_TOOLS]
- [/AVAILABLE_TOOLS]
- [TOOL_RESULT]
- [/TOOL_RESULTS]
If you want to use this model with function calling, please be sure to apply it similarly to what is done in our [SentencePieceTokenizerV3](https://github.com/mistralai/mistral-common/blob/main/src/mistral_common/tokens/tokenizers/sentencepiece.py#L299).
# The Mistral AI Team
Albert Jiang, Alexandre Sablayrolles, Alexis Tacnet, Antoine Roux,
Arthur Mensch, Audrey Herblin-Stoop, Baptiste Bout, Baudouin de Monicault,
Blanche Savary, Bam4d, Caroline Feldman, Devendra Singh Chaplot,
Diego de las Casas, Eleonore Arcelin, Emma Bou Hanna, Etienne Metzger,
Gianna Lengyel, Guillaume Bour, Guillaume Lample, Harizo Rajaona,
Jean-Malo Delignon, Jia Li, Justus Murke, Louis Martin, Louis Ternon,
Lucile Saulnier, Lélio Renard Lavaud, Margaret Jennings, Marie Pellat,
Marie Torelli, Marie-Anne Lachaux, Nicolas Schuhl, Patrick von Platen,
Pierre Stock, Sandeep Subramanian, Sophia Yang, Szymon Antoniak, Teven Le Scao,
Thibaut Lavril, Timothée Lacroix, Théophile Gervet, Thomas Wang,
Valera Nemychnikova, William El Sayed, William Marshall | {"license": "apache-2.0"} | mistral-community/Mixtral-8x22B-Instruct-v0.1-4bit | null | [
"transformers",
"safetensors",
"mixtral",
"text-generation",
"conversational",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"has_space",
"text-generation-inference",
"4-bit",
"region:us"
] | null | 2024-04-17T19:14:50+00:00 | [] | [] | TAGS
#transformers #safetensors #mixtral #text-generation #conversational #license-apache-2.0 #autotrain_compatible #endpoints_compatible #has_space #text-generation-inference #4-bit #region-us
|
# Model Card for Mixtral-8x22B-Instruct-v0.1
The Mixtral-8x22B-Instruct-v0.1 Large Language Model (LLM) is an instruct fine-tuned version of the Mixtral-8x22B-v0.1.
Model added by Prince Canuma.
## Run the model
# Instruct tokenizer
The HuggingFace tokenizer included in this release should match our own. To compare:
'pip install mistral-common'
# Function calling and special tokens
This tokenizer includes more special tokens, related to function calling :
- [TOOL_CALLS]
- [AVAILABLE_TOOLS]
- [/AVAILABLE_TOOLS]
- [TOOL_RESULT]
- [/TOOL_RESULTS]
If you want to use this model with function calling, please be sure to apply it similarly to what is done in our SentencePieceTokenizerV3.
# The Mistral AI Team
Albert Jiang, Alexandre Sablayrolles, Alexis Tacnet, Antoine Roux,
Arthur Mensch, Audrey Herblin-Stoop, Baptiste Bout, Baudouin de Monicault,
Blanche Savary, Bam4d, Caroline Feldman, Devendra Singh Chaplot,
Diego de las Casas, Eleonore Arcelin, Emma Bou Hanna, Etienne Metzger,
Gianna Lengyel, Guillaume Bour, Guillaume Lample, Harizo Rajaona,
Jean-Malo Delignon, Jia Li, Justus Murke, Louis Martin, Louis Ternon,
Lucile Saulnier, Lélio Renard Lavaud, Margaret Jennings, Marie Pellat,
Marie Torelli, Marie-Anne Lachaux, Nicolas Schuhl, Patrick von Platen,
Pierre Stock, Sandeep Subramanian, Sophia Yang, Szymon Antoniak, Teven Le Scao,
Thibaut Lavril, Timothée Lacroix, Théophile Gervet, Thomas Wang,
Valera Nemychnikova, William El Sayed, William Marshall | [
"# Model Card for Mixtral-8x22B-Instruct-v0.1\nThe Mixtral-8x22B-Instruct-v0.1 Large Language Model (LLM) is an instruct fine-tuned version of the Mixtral-8x22B-v0.1.\n\nModel added by Prince Canuma.",
"## Run the model",
"# Instruct tokenizer\nThe HuggingFace tokenizer included in this release should match our own. To compare: \n'pip install mistral-common'",
"# Function calling and special tokens\nThis tokenizer includes more special tokens, related to function calling : \n- [TOOL_CALLS]\n- [AVAILABLE_TOOLS]\n- [/AVAILABLE_TOOLS]\n- [TOOL_RESULT]\n- [/TOOL_RESULTS]\n\nIf you want to use this model with function calling, please be sure to apply it similarly to what is done in our SentencePieceTokenizerV3.",
"# The Mistral AI Team\nAlbert Jiang, Alexandre Sablayrolles, Alexis Tacnet, Antoine Roux,\nArthur Mensch, Audrey Herblin-Stoop, Baptiste Bout, Baudouin de Monicault,\nBlanche Savary, Bam4d, Caroline Feldman, Devendra Singh Chaplot,\nDiego de las Casas, Eleonore Arcelin, Emma Bou Hanna, Etienne Metzger,\nGianna Lengyel, Guillaume Bour, Guillaume Lample, Harizo Rajaona,\nJean-Malo Delignon, Jia Li, Justus Murke, Louis Martin, Louis Ternon,\nLucile Saulnier, Lélio Renard Lavaud, Margaret Jennings, Marie Pellat,\nMarie Torelli, Marie-Anne Lachaux, Nicolas Schuhl, Patrick von Platen,\nPierre Stock, Sandeep Subramanian, Sophia Yang, Szymon Antoniak, Teven Le Scao,\nThibaut Lavril, Timothée Lacroix, Théophile Gervet, Thomas Wang,\nValera Nemychnikova, William El Sayed, William Marshall"
] | [
"TAGS\n#transformers #safetensors #mixtral #text-generation #conversational #license-apache-2.0 #autotrain_compatible #endpoints_compatible #has_space #text-generation-inference #4-bit #region-us \n",
"# Model Card for Mixtral-8x22B-Instruct-v0.1\nThe Mixtral-8x22B-Instruct-v0.1 Large Language Model (LLM) is an instruct fine-tuned version of the Mixtral-8x22B-v0.1.\n\nModel added by Prince Canuma.",
"## Run the model",
"# Instruct tokenizer\nThe HuggingFace tokenizer included in this release should match our own. To compare: \n'pip install mistral-common'",
"# Function calling and special tokens\nThis tokenizer includes more special tokens, related to function calling : \n- [TOOL_CALLS]\n- [AVAILABLE_TOOLS]\n- [/AVAILABLE_TOOLS]\n- [TOOL_RESULT]\n- [/TOOL_RESULTS]\n\nIf you want to use this model with function calling, please be sure to apply it similarly to what is done in our SentencePieceTokenizerV3.",
"# The Mistral AI Team\nAlbert Jiang, Alexandre Sablayrolles, Alexis Tacnet, Antoine Roux,\nArthur Mensch, Audrey Herblin-Stoop, Baptiste Bout, Baudouin de Monicault,\nBlanche Savary, Bam4d, Caroline Feldman, Devendra Singh Chaplot,\nDiego de las Casas, Eleonore Arcelin, Emma Bou Hanna, Etienne Metzger,\nGianna Lengyel, Guillaume Bour, Guillaume Lample, Harizo Rajaona,\nJean-Malo Delignon, Jia Li, Justus Murke, Louis Martin, Louis Ternon,\nLucile Saulnier, Lélio Renard Lavaud, Margaret Jennings, Marie Pellat,\nMarie Torelli, Marie-Anne Lachaux, Nicolas Schuhl, Patrick von Platen,\nPierre Stock, Sandeep Subramanian, Sophia Yang, Szymon Antoniak, Teven Le Scao,\nThibaut Lavril, Timothée Lacroix, Théophile Gervet, Thomas Wang,\nValera Nemychnikova, William El Sayed, William Marshall"
] |
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]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
### Framework versions
- PEFT 0.10.0 | {"library_name": "peft", "base_model": "NousResearch/Llama-2-7b-chat-hf"} | Kunalpal216/llama2-tuned | null | [
"peft",
"pytorch",
"safetensors",
"llama",
"arxiv:1910.09700",
"base_model:NousResearch/Llama-2-7b-chat-hf",
"4-bit",
"region:us"
] | null | 2024-04-17T19:14:51+00:00 | [
"1910.09700"
] | [] | TAGS
#peft #pytorch #safetensors #llama #arxiv-1910.09700 #base_model-NousResearch/Llama-2-7b-chat-hf #4-bit #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
- Developed by:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
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.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
### Framework versions
- PEFT 0.10.0 | [
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\n\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact",
"### Framework versions\n\n- PEFT 0.10.0"
] | [
"TAGS\n#peft #pytorch #safetensors #llama #arxiv-1910.09700 #base_model-NousResearch/Llama-2-7b-chat-hf #4-bit #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\n\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact",
"### Framework versions\n\n- PEFT 0.10.0"
] |
text-generation | transformers | # Jersey Devil 14b
This model is a merge of three self-merged Solar-based models in a 14b (64 layer) configuration. The result of
this "frankenmerge" is a medium-sized model that contains some of the latest funky solar finetunes.
Mergefuel:
- Himitsui/Kaiju-11B
- TheDrummer/Moistral-11B-v2
- akrads/NousHermes-Borealis-SOLAR-10.7B
This model is uncensored and capable of generating objectionable material. However, it is not an explicitely-NSFW model,
and it has never "gone rogue" and tried to insert NSFW content into SFW prompts in my experience. As with any LLM, no
factual claims made by the model should be taken at face value. You know that boilerplate safety disclaimer that most
professional models have? Assume this has it too. This model is for entertainment purposes only.
GGUFs: https://huggingface.co/MarsupialAI/JerseyDevil-14b_iMatrix_GGUF
# Sample output
```
{{[INPUT]}}
Write a detailed and humorous story about a cute and fluffy bunny that goes to a Gwar concert.
{{[OUTPUT]}}
It was a warm summer evening when little Bunny Bop hopped out of his burrow, ready for an adventure. He had heard all about this awesome band called Gwar, who were coming to town tonight. His friends had been buzzing about it for weeks, saying how wild the shows were and how much fun you could have. So, with excitement bubbling up inside him like a fresh carrot juice, Bunny set off on his journey into the big city.
He didn't know exactly where he was going but figured as long as he followed the signs pointing towards the loud music, he couldn't go wrong. As he hopped along, he passed by several other animals also headed to the concert - a group of frogs, a herd of sheep, even a couple of skunks! They all wished him good luck and told him to be careful; they said Gwar fans could get pretty rowdy.
When Bunny finally arrived at the venue, he found himself standing in front of a huge crowd. There were people (and furry creatures) everywhere, all eagerly waiting to get inside. He looked around nervously, feeling a bit overwhelmed by all the noise and activity. But then he spotted a familiar face among the sea of faces: Mr. Fox, one of his neighbors from back home.
“Hey, Mr. Fox!” Bunny cried out excitedly, waving his little paws in greeting. “Are you coming to see Gwar too?”
Mr. Fox grinned at him. “Yep, I sure am. You ready for some heavy metal mayhem?”
Bunny nodded enthusiastically. “I can hardly wait!” Together, they joined the line and slowly made their way into the stadium. Once they got inside, they found their seats near the center stage. The place was packed with fans wearing crazy costumes and waving glow sticks in time to the music blasting over the speakers.
As the opening act started playing, Bunny couldn't help but bounce up and down in excitement. The lights flashed brightly overhead while smoke filled the air around them. He felt like he had never been anywhere more exciting before! When Gwar finally took the stage, everything went wild. Their loud guitars and growling vocals sent shivers down his cottony spine as they launched into their first song.
The lead singer - an enormous, green-skinned creature called Oderus Urungus - seemed particularly interested in Bunny. He pointed directly at him several times during the performance and even encouraged everyone around them to cheer for the cute little rabbit. At first, this made Bunny feel a bit nervous; he wasn't used to so much attention! But soon enough, he let go of his worries and began jumping along with all the other fans.
When one of the band members threw his pick into the crowd, Bunny caught it out of reflex. It landed perfectly in his paws and he clutched it tightly throughout the rest of the show. As each song ended, he heard people around him screaming for an encore until finally, Gwar returned to play another round. They were even louder this time, their energy infectious as it surged through every person in attendance.
After what seemed like hours (but was actually just two sets), Gwar finished their concert with a bang. Bunny found himself exhausted but completely satisfied; it had been the best night ever! As he left the stadium with Mr. Fox, he couldn't stop smiling as he thought about everything he had seen and experienced. This was definitely one adventure that would be hard to top.
As they walked back home through the streets now empty except for stray pieces of trash and discarded glow sticks, Bunny glanced down at the guitar pick still nestled in his furry hand. He knew it might not be worth much money, but to him, it represented something far more valuable: the memory of an unforgettable rock 'n roll journey. And if there ever was another chance to see Gwar live again...well, you better bet little Bunny Bop would be first in line.
```
# Prompt format
Prefers alpaca. | {"language": ["en"], "license": "cc-by-nc-4.0", "tags": ["solar"]} | MarsupialAI/JerseyDevil-14b | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"solar",
"en",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-04-17T19:15:26+00:00 | [] | [
"en"
] | TAGS
#transformers #safetensors #llama #text-generation #solar #en #license-cc-by-nc-4.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us
| # Jersey Devil 14b
!image/jpeg
This model is a merge of three self-merged Solar-based models in a 14b (64 layer) configuration. The result of
this "frankenmerge" is a medium-sized model that contains some of the latest funky solar finetunes.
Mergefuel:
- Himitsui/Kaiju-11B
- TheDrummer/Moistral-11B-v2
- akrads/NousHermes-Borealis-SOLAR-10.7B
This model is uncensored and capable of generating objectionable material. However, it is not an explicitely-NSFW model,
and it has never "gone rogue" and tried to insert NSFW content into SFW prompts in my experience. As with any LLM, no
factual claims made by the model should be taken at face value. You know that boilerplate safety disclaimer that most
professional models have? Assume this has it too. This model is for entertainment purposes only.
GGUFs: URL
# Sample output
# Prompt format
Prefers alpaca. | [
"# Jersey Devil 14b\n\n!image/jpeg\n\nThis model is a merge of three self-merged Solar-based models in a 14b (64 layer) configuration. The result of \nthis \"frankenmerge\" is a medium-sized model that contains some of the latest funky solar finetunes.\n\nMergefuel:\n - Himitsui/Kaiju-11B\n - TheDrummer/Moistral-11B-v2\n - akrads/NousHermes-Borealis-SOLAR-10.7B\n\nThis model is uncensored and capable of generating objectionable material. However, it is not an explicitely-NSFW model, \nand it has never \"gone rogue\" and tried to insert NSFW content into SFW prompts in my experience. As with any LLM, no \nfactual claims made by the model should be taken at face value. You know that boilerplate safety disclaimer that most \nprofessional models have? Assume this has it too. This model is for entertainment purposes only.\n\n\nGGUFs: URL",
"# Sample output",
"# Prompt format\nPrefers alpaca."
] | [
"TAGS\n#transformers #safetensors #llama #text-generation #solar #en #license-cc-by-nc-4.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n",
"# Jersey Devil 14b\n\n!image/jpeg\n\nThis model is a merge of three self-merged Solar-based models in a 14b (64 layer) configuration. The result of \nthis \"frankenmerge\" is a medium-sized model that contains some of the latest funky solar finetunes.\n\nMergefuel:\n - Himitsui/Kaiju-11B\n - TheDrummer/Moistral-11B-v2\n - akrads/NousHermes-Borealis-SOLAR-10.7B\n\nThis model is uncensored and capable of generating objectionable material. However, it is not an explicitely-NSFW model, \nand it has never \"gone rogue\" and tried to insert NSFW content into SFW prompts in my experience. As with any LLM, no \nfactual claims made by the model should be taken at face value. You know that boilerplate safety disclaimer that most \nprofessional models have? Assume this has it too. This model is for entertainment purposes only.\n\n\nGGUFs: URL",
"# Sample output",
"# Prompt format\nPrefers alpaca."
] |
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="gabybaldeon/taxi_v3_v1", 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_v3_v1", "results": [{"task": {"type": "reinforcement-learning", "name": "reinforcement-learning"}, "dataset": {"name": "Taxi-v3", "type": "Taxi-v3"}, "metrics": [{"type": "mean_reward", "value": "7.52 +/- 2.62", "name": "mean_reward", "verified": false}]}]}]} | gabybaldeon/taxi_v3_v1 | null | [
"Taxi-v3",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] | null | 2024-04-17T19:16:52+00:00 | [] | [] | TAGS
#Taxi-v3 #q-learning #reinforcement-learning #custom-implementation #model-index #region-us
|
# Q-Learning Agent playing1 Taxi-v3
This is a trained model of a Q-Learning agent playing Taxi-v3 .
## Usage
| [
"# Q-Learning Agent playing1 Taxi-v3\n This is a trained model of a Q-Learning agent playing Taxi-v3 .\n\n ## Usage"
] | [
"TAGS\n#Taxi-v3 #q-learning #reinforcement-learning #custom-implementation #model-index #region-us \n",
"# Q-Learning Agent playing1 Taxi-v3\n This is a trained model of a Q-Learning agent playing Taxi-v3 .\n\n ## Usage"
] |
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. -->
# gpt2-finetuned-justification-v1
This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4104
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 100
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:-----:|:---------------:|
| 0.2403 | 1.0 | 676 | 0.1991 |
| 0.1824 | 2.0 | 1352 | 0.1990 |
| 0.1366 | 3.0 | 2028 | 0.2091 |
| 0.1098 | 4.0 | 2704 | 0.2222 |
| 0.0997 | 5.0 | 3380 | 0.2386 |
| 0.0724 | 6.0 | 4056 | 0.2535 |
| 0.0608 | 7.0 | 4732 | 0.2694 |
| 0.0516 | 8.0 | 5408 | 0.2861 |
| 0.0409 | 9.0 | 6084 | 0.2941 |
| 0.0356 | 10.0 | 6760 | 0.3040 |
| 0.0319 | 11.0 | 7436 | 0.3124 |
| 0.0265 | 12.0 | 8112 | 0.3184 |
| 0.0242 | 13.0 | 8788 | 0.3235 |
| 0.0225 | 14.0 | 9464 | 0.3261 |
| 0.0197 | 15.0 | 10140 | 0.3330 |
| 0.0183 | 16.0 | 10816 | 0.3372 |
| 0.0185 | 17.0 | 11492 | 0.3410 |
| 0.0157 | 18.0 | 12168 | 0.3394 |
| 0.0155 | 19.0 | 12844 | 0.3468 |
| 0.0147 | 20.0 | 13520 | 0.3522 |
| 0.0135 | 21.0 | 14196 | 0.3532 |
| 0.0135 | 22.0 | 14872 | 0.3538 |
| 0.0125 | 23.0 | 15548 | 0.3605 |
| 0.0123 | 24.0 | 16224 | 0.3594 |
| 0.012 | 25.0 | 16900 | 0.3635 |
| 0.0116 | 26.0 | 17576 | 0.3649 |
| 0.0114 | 27.0 | 18252 | 0.3665 |
| 0.011 | 28.0 | 18928 | 0.3685 |
| 0.0108 | 29.0 | 19604 | 0.3689 |
| 0.0108 | 30.0 | 20280 | 0.3724 |
| 0.0103 | 31.0 | 20956 | 0.3719 |
| 0.0102 | 32.0 | 21632 | 0.3717 |
| 0.01 | 33.0 | 22308 | 0.3764 |
| 0.0102 | 34.0 | 22984 | 0.3751 |
| 0.0094 | 35.0 | 23660 | 0.3787 |
| 0.0099 | 36.0 | 24336 | 0.3789 |
| 0.0096 | 37.0 | 25012 | 0.3857 |
| 0.0094 | 38.0 | 25688 | 0.3825 |
| 0.0093 | 39.0 | 26364 | 0.3831 |
| 0.0091 | 40.0 | 27040 | 0.3878 |
| 0.0091 | 41.0 | 27716 | 0.3857 |
| 0.0089 | 42.0 | 28392 | 0.3863 |
| 0.0089 | 43.0 | 29068 | 0.3878 |
| 0.0089 | 44.0 | 29744 | 0.3895 |
| 0.0087 | 45.0 | 30420 | 0.3885 |
| 0.0088 | 46.0 | 31096 | 0.3900 |
| 0.0084 | 47.0 | 31772 | 0.3930 |
| 0.0087 | 48.0 | 32448 | 0.3916 |
| 0.0084 | 49.0 | 33124 | 0.3907 |
| 0.0083 | 50.0 | 33800 | 0.3922 |
| 0.0083 | 51.0 | 34476 | 0.3937 |
| 0.0082 | 52.0 | 35152 | 0.3934 |
| 0.0082 | 53.0 | 35828 | 0.3976 |
| 0.0081 | 54.0 | 36504 | 0.3959 |
| 0.008 | 55.0 | 37180 | 0.3996 |
| 0.0079 | 56.0 | 37856 | 0.3999 |
| 0.0079 | 57.0 | 38532 | 0.3997 |
| 0.0079 | 58.0 | 39208 | 0.4024 |
| 0.0078 | 59.0 | 39884 | 0.4027 |
| 0.0079 | 60.0 | 40560 | 0.3980 |
| 0.0077 | 61.0 | 41236 | 0.4019 |
| 0.0077 | 62.0 | 41912 | 0.4019 |
| 0.0078 | 63.0 | 42588 | 0.4020 |
| 0.0076 | 64.0 | 43264 | 0.4062 |
| 0.0077 | 65.0 | 43940 | 0.4041 |
| 0.0077 | 66.0 | 44616 | 0.4011 |
| 0.0076 | 67.0 | 45292 | 0.4029 |
| 0.0075 | 68.0 | 45968 | 0.4046 |
| 0.0074 | 69.0 | 46644 | 0.4043 |
| 0.0075 | 70.0 | 47320 | 0.4066 |
| 0.0075 | 71.0 | 47996 | 0.4055 |
| 0.0074 | 72.0 | 48672 | 0.4064 |
| 0.0075 | 73.0 | 49348 | 0.4089 |
| 0.0074 | 74.0 | 50024 | 0.4089 |
| 0.0072 | 75.0 | 50700 | 0.4087 |
| 0.0073 | 76.0 | 51376 | 0.4066 |
| 0.0073 | 77.0 | 52052 | 0.4035 |
| 0.0072 | 78.0 | 52728 | 0.4050 |
| 0.0072 | 79.0 | 53404 | 0.4059 |
| 0.0071 | 80.0 | 54080 | 0.4104 |
| 0.0071 | 81.0 | 54756 | 0.4095 |
| 0.0072 | 82.0 | 55432 | 0.4081 |
| 0.0072 | 83.0 | 56108 | 0.4095 |
| 0.0071 | 84.0 | 56784 | 0.4092 |
| 0.007 | 85.0 | 57460 | 0.4099 |
| 0.007 | 86.0 | 58136 | 0.4070 |
| 0.007 | 87.0 | 58812 | 0.4070 |
| 0.007 | 88.0 | 59488 | 0.4057 |
| 0.0069 | 89.0 | 60164 | 0.4090 |
| 0.0069 | 90.0 | 60840 | 0.4106 |
| 0.007 | 91.0 | 61516 | 0.4096 |
| 0.0069 | 92.0 | 62192 | 0.4106 |
| 0.0069 | 93.0 | 62868 | 0.4101 |
| 0.0069 | 94.0 | 63544 | 0.4099 |
| 0.0068 | 95.0 | 64220 | 0.4104 |
| 0.0068 | 96.0 | 64896 | 0.4106 |
| 0.0068 | 97.0 | 65572 | 0.4102 |
| 0.0067 | 98.0 | 66248 | 0.4102 |
| 0.0067 | 99.0 | 66924 | 0.4104 |
| 0.0067 | 100.0 | 67600 | 0.4104 |
### Framework versions
- Transformers 4.36.2
- Pytorch 2.2.2+cu121
- Datasets 2.16.0
- Tokenizers 0.15.2
| {"tags": ["generated_from_trainer"], "model-index": [{"name": "gpt2-finetuned-justification-v1", "results": []}]} | satyanshu404/gpt2-finetuned-justification-v1 | null | [
"transformers",
"safetensors",
"encoder-decoder",
"text2text-generation",
"generated_from_trainer",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-04-17T19:18:13+00:00 | [] | [] | TAGS
#transformers #safetensors #encoder-decoder #text2text-generation #generated_from_trainer #autotrain_compatible #endpoints_compatible #region-us
| gpt2-finetuned-justification-v1
===============================
This model is a fine-tuned version of [](URL on the None dataset.
It achieves the following results on the evaluation set:
* Loss: 0.4104
Model description
-----------------
More information needed
Intended uses & limitations
---------------------------
More information needed
Training and evaluation data
----------------------------
More information needed
Training procedure
------------------
### Training hyperparameters
The following hyperparameters were used during training:
* learning\_rate: 5e-05
* train\_batch\_size: 1
* eval\_batch\_size: 1
* seed: 42
* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
* lr\_scheduler\_type: linear
* num\_epochs: 100
### Training results
### Framework versions
* Transformers 4.36.2
* Pytorch 2.2.2+cu121
* Datasets 2.16.0
* Tokenizers 0.15.2
| [
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 5e-05\n* train\\_batch\\_size: 1\n* eval\\_batch\\_size: 1\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 100",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.36.2\n* Pytorch 2.2.2+cu121\n* Datasets 2.16.0\n* Tokenizers 0.15.2"
] | [
"TAGS\n#transformers #safetensors #encoder-decoder #text2text-generation #generated_from_trainer #autotrain_compatible #endpoints_compatible #region-us \n",
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 5e-05\n* train\\_batch\\_size: 1\n* eval\\_batch\\_size: 1\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 100",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.36.2\n* Pytorch 2.2.2+cu121\n* Datasets 2.16.0\n* Tokenizers 0.15.2"
] |
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": []} | martinsinnona/visdecode_2024_1 | null | [
"transformers",
"safetensors",
"pix2struct",
"text2text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-04-17T19:19:53+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #safetensors #pix2struct #text2text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
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:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
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.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
| [
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] | [
"TAGS\n#transformers #safetensors #pix2struct #text2text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
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": []} | ManukyanD/flan-t5-for-text2sql | null | [
"transformers",
"safetensors",
"t5",
"text2text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-04-17T19:20:15+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #safetensors #t5 #text2text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
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:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
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.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
| [
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] | [
"TAGS\n#transformers #safetensors #t5 #text2text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
text-generation | transformers |
# KSI-RPG-128k-7B
KSI-RPG-128k-7B is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
* [AlekseiPravdin/KSI-RP-NSK-128k-7B](https://huggingface.co/AlekseiPravdin/KSI-RP-NSK-128k-7B)
* [flammenai/flammen18X-mistral-7B](https://huggingface.co/flammenai/flammen18X-mistral-7B)
## 🧩 Configuration
```yaml
slices:
- sources:
- model: AlekseiPravdin/KSI-RP-NSK-128k-7B
layer_range: [0, 32]
- model: flammenai/flammen18X-mistral-7B
layer_range: [0, 32]
merge_method: slerp
base_model: AlekseiPravdin/KSI-RP-NSK-128k-7B
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
``` | {"license": "apache-2.0", "tags": ["merge", "mergekit", "lazymergekit", "AlekseiPravdin/KSI-RP-NSK-128k-7B", "flammenai/flammen18X-mistral-7B"]} | AlekseiPravdin/KSI-RPG-128k-7B | null | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"merge",
"mergekit",
"lazymergekit",
"AlekseiPravdin/KSI-RP-NSK-128k-7B",
"flammenai/flammen18X-mistral-7B",
"conversational",
"custom_code",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-04-17T19:20:55+00:00 | [] | [] | TAGS
#transformers #safetensors #mistral #text-generation #merge #mergekit #lazymergekit #AlekseiPravdin/KSI-RP-NSK-128k-7B #flammenai/flammen18X-mistral-7B #conversational #custom_code #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us
|
# KSI-RPG-128k-7B
KSI-RPG-128k-7B is a merge of the following models using mergekit:
* AlekseiPravdin/KSI-RP-NSK-128k-7B
* flammenai/flammen18X-mistral-7B
## Configuration
| [
"# KSI-RPG-128k-7B\n\nKSI-RPG-128k-7B is a merge of the following models using mergekit:\n* AlekseiPravdin/KSI-RP-NSK-128k-7B\n* flammenai/flammen18X-mistral-7B",
"## Configuration"
] | [
"TAGS\n#transformers #safetensors #mistral #text-generation #merge #mergekit #lazymergekit #AlekseiPravdin/KSI-RP-NSK-128k-7B #flammenai/flammen18X-mistral-7B #conversational #custom_code #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n",
"# KSI-RPG-128k-7B\n\nKSI-RPG-128k-7B is a merge of the following models using mergekit:\n* AlekseiPravdin/KSI-RP-NSK-128k-7B\n* flammenai/flammen18X-mistral-7B",
"## Configuration"
] |
null | 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": []} | jjezabek/ai_swe-openchat-3.5-0106-set_diff_1-6-epochs | null | [
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2024-04-17T19:23:44+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
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:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
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.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
| [
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] | [
"TAGS\n#transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
text-generation | transformers |
This is an upscaled fp16 variant of the original Llama-2-7b base model by Meta after it has been loaded with nf4 4-bit quantization via bitsandbytes.
The main idea here is to upscale the linear4bit layers to fp16 so that the quantization/dequantization cost doesn't have to paid for each forward pass at inference time.
_Note: The quantization operation to nf4 is not lossless, so the model weights for the linear layers are lossy, which means that this model will not work as well as the official base model._
To use this model, you can just load it via `transformers` in fp16:
```python
import torch
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained(
"predibase/Llama-2-7b-hf-dequantized",
device_map="auto",
torch_dtype=torch.float16,
)
``` | {"license": "apache-2.0", "tags": ["text-generation-inference"]} | predibase/Llama-2-7b-hf-dequantized | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"text-generation-inference",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-04-17T19:24:45+00:00 | [] | [] | TAGS
#transformers #safetensors #llama #text-generation #text-generation-inference #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us
|
This is an upscaled fp16 variant of the original Llama-2-7b base model by Meta after it has been loaded with nf4 4-bit quantization via bitsandbytes.
The main idea here is to upscale the linear4bit layers to fp16 so that the quantization/dequantization cost doesn't have to paid for each forward pass at inference time.
_Note: The quantization operation to nf4 is not lossless, so the model weights for the linear layers are lossy, which means that this model will not work as well as the official base model._
To use this model, you can just load it via 'transformers' in fp16:
| [] | [
"TAGS\n#transformers #safetensors #llama #text-generation #text-generation-inference #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n"
] |
text-generation | transformers | This model contains the weights of pretrained TransVerse model covering text-image-video-audio (tiva), which is built upon
- 1) [Vicuna-7B](https://huggingface.co/lmsys/vicuna-7b-delta-v0) with version 0
- 2) [ImageBind](https://dl.fbaipublicfiles.com/imagebind/imagebind_huge.pth)
- 3) [Stable Diffusion](https://huggingface.co/runwayml/stable-diffusion-v1-5) with version `v1-5`.
- 4) [AudioLDM](https://github.com/haoheliu/AudioLDM) with version `l-full`.
- 5) [ZeroScope](https://huggingface.co/cerspense/zeroscope_v2_576w) with version `v2_576w`.
| {"license": "cc-by-nc-sa-4.0"} | 3it/TransVerse-v1 | null | [
"transformers",
"llama",
"text-generation",
"license:cc-by-nc-sa-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-04-17T19:25:20+00:00 | [] | [] | TAGS
#transformers #llama #text-generation #license-cc-by-nc-sa-4.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us
| This model contains the weights of pretrained TransVerse model covering text-image-video-audio (tiva), which is built upon
- 1) Vicuna-7B with version 0
- 2) ImageBind
- 3) Stable Diffusion with version 'v1-5'.
- 4) AudioLDM with version 'l-full'.
- 5) ZeroScope with version 'v2_576w'.
| [] | [
"TAGS\n#transformers #llama #text-generation #license-cc-by-nc-sa-4.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n"
] |
text-generation | transformers |
This is an upscaled fp16 variant of the original Llama-2-7b-chat base model by Meta after it has been loaded with nf4 4-bit quantization via bitsandbytes.
The main idea here is to upscale the linear4bit layers to fp16 so that the quantization/dequantization cost doesn't have to paid for each forward pass at inference time.
_Note: The quantization operation to nf4 is not lossless, so the model weights for the linear layers are lossy, which means that this model will not work as well as the official base model._
To use this model, you can just load it via `transformers` in fp16:
```python
import torch
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained(
"predibase/Llama-2-7b-chat-hf-dequantized",
device_map="auto",
torch_dtype=torch.float16
)
``` | {"license": "apache-2.0", "tags": ["text-generation-inference"]} | predibase/Llama-2-7b-chat-hf-dequantized | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"text-generation-inference",
"conversational",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-04-17T19:25:56+00:00 | [] | [] | TAGS
#transformers #safetensors #llama #text-generation #text-generation-inference #conversational #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us
|
This is an upscaled fp16 variant of the original Llama-2-7b-chat base model by Meta after it has been loaded with nf4 4-bit quantization via bitsandbytes.
The main idea here is to upscale the linear4bit layers to fp16 so that the quantization/dequantization cost doesn't have to paid for each forward pass at inference time.
_Note: The quantization operation to nf4 is not lossless, so the model weights for the linear layers are lossy, which means that this model will not work as well as the official base model._
To use this model, you can just load it via 'transformers' in fp16:
| [] | [
"TAGS\n#transformers #safetensors #llama #text-generation #text-generation-inference #conversational #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n"
] |
feature-extraction | 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": []} | eeshanpatel/Roberta-triplet-finetuned-v2.0 | null | [
"transformers",
"safetensors",
"roberta",
"feature-extraction",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2024-04-17T19:26:09+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #safetensors #roberta #feature-extraction #arxiv-1910.09700 #endpoints_compatible #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
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:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
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.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
| [
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] | [
"TAGS\n#transformers #safetensors #roberta #feature-extraction #arxiv-1910.09700 #endpoints_compatible #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
text-generation | transformers |
This is an upscaled fp16 variant of the original Codellama-7b-instruct base model by Meta after it has been loaded with nf4 4-bit quantization via bitsandbytes.
The main idea here is to upscale the linear4bit layers to fp16 so that the quantization/dequantization cost doesn't have to paid for each forward pass at inference time.
_Note: The quantization operation to nf4 is not lossless, so the model weights for the linear layers are lossy, which means that this model will not work as well as the official base model._
To use this model, you can just load it via `transformers` in fp16:
```python
import torch
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained(
"predibase/CodeLlama-7b-Instruct-hf-dequantized",
device_map="auto",
torch_dtype=torch.float16
)
``` | {"license": "apache-2.0", "tags": ["text-generation-inference"]} | predibase/CodeLlama-7b-Instruct-hf-dequantized | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"text-generation-inference",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-04-17T19:26:42+00:00 | [] | [] | TAGS
#transformers #safetensors #llama #text-generation #text-generation-inference #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us
|
This is an upscaled fp16 variant of the original Codellama-7b-instruct base model by Meta after it has been loaded with nf4 4-bit quantization via bitsandbytes.
The main idea here is to upscale the linear4bit layers to fp16 so that the quantization/dequantization cost doesn't have to paid for each forward pass at inference time.
_Note: The quantization operation to nf4 is not lossless, so the model weights for the linear layers are lossy, which means that this model will not work as well as the official base model._
To use this model, you can just load it via 'transformers' in fp16:
| [] | [
"TAGS\n#transformers #safetensors #llama #text-generation #text-generation-inference #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n"
] |
text-generation | transformers |
This is an upscaled fp16 variant of the original Llama-2-13b-chat base model by Meta after it has been loaded with nf4 4-bit quantization via bitsandbytes.
The main idea here is to upscale the linear4bit layers to fp16 so that the quantization/dequantization cost doesn't have to paid for each forward pass at inference time.
_Note: The quantization operation to nf4 is not lossless, so the model weights for the linear layers are lossy, which means that this model will not work as well as the official base model._
To use this model, you can just load it via `transformers` in fp16:
```python
import torch
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained(
"predibase/Llama-2-13b-chat-hf-dequantized",
device_map="auto",
torch_dtype=torch.float16
)
``` | {"license": "apache-2.0", "tags": ["text-generation-inference"]} | predibase/Llama-2-13b-chat-hf-dequantized | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"text-generation-inference",
"conversational",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-04-17T19:27:11+00:00 | [] | [] | TAGS
#transformers #safetensors #llama #text-generation #text-generation-inference #conversational #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us
|
This is an upscaled fp16 variant of the original Llama-2-13b-chat base model by Meta after it has been loaded with nf4 4-bit quantization via bitsandbytes.
The main idea here is to upscale the linear4bit layers to fp16 so that the quantization/dequantization cost doesn't have to paid for each forward pass at inference time.
_Note: The quantization operation to nf4 is not lossless, so the model weights for the linear layers are lossy, which means that this model will not work as well as the official base model._
To use this model, you can just load it via 'transformers' in fp16:
| [] | [
"TAGS\n#transformers #safetensors #llama #text-generation #text-generation-inference #conversational #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n"
] |
text-generation | transformers |
This is an upscaled fp16 variant of the original CodeLlama-13b-instruct base model by Meta after it has been loaded with nf4 4-bit quantization via bitsandbytes.
The main idea here is to upscale the linear4bit layers to fp16 so that the quantization/dequantization cost doesn't have to paid for each forward pass at inference time.
_Note: The quantization operation to nf4 is not lossless, so the model weights for the linear layers are lossy, which means that this model will not work as well as the official base model._
To use this model, you can just load it via `transformers` in fp16:
```python
import torch
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained(
"predibase/CodeLlama-13b-Instruct-hf-dequantized",
device_map="auto",
torch_dtype=torch.float16,
)
``` | {"license": "apache-2.0", "tags": ["text-generation-inference"]} | predibase/CodeLlama-13b-Instruct-hf-dequantized | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"text-generation-inference",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-04-17T19:27:35+00:00 | [] | [] | TAGS
#transformers #safetensors #llama #text-generation #text-generation-inference #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us
|
This is an upscaled fp16 variant of the original CodeLlama-13b-instruct base model by Meta after it has been loaded with nf4 4-bit quantization via bitsandbytes.
The main idea here is to upscale the linear4bit layers to fp16 so that the quantization/dequantization cost doesn't have to paid for each forward pass at inference time.
_Note: The quantization operation to nf4 is not lossless, so the model weights for the linear layers are lossy, which means that this model will not work as well as the official base model._
To use this model, you can just load it via 'transformers' in fp16:
| [] | [
"TAGS\n#transformers #safetensors #llama #text-generation #text-generation-inference #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n"
] |
text-generation | transformers |
This is an upscaled fp16 variant of the original Mistral-7B-Instruct-v0.1 base model by Mistral after it has been loaded with nf4 4-bit quantization via bitsandbytes.
The main idea here is to upscale the linear4bit layers to fp16 so that the quantization/dequantization cost doesn't have to paid for each forward pass at inference time.
_Note: The quantization operation to nf4 is not lossless, so the model weights for the linear layers are lossy, which means that this model will not work as well as the official base model._
To use this model, you can just load it via `transformers` in fp16:
```python
import torch
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained(
"predibase/Mistral-7B-Instruct-v0.1-dequantized",
device_map="auto",
torch_dtype=torch.float16,
)
``` | {"license": "apache-2.0", "tags": ["text-generation-inference"]} | predibase/Mistral-7B-Instruct-v0.1-dequantized | null | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"text-generation-inference",
"conversational",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-04-17T19:28:18+00:00 | [] | [] | TAGS
#transformers #safetensors #mistral #text-generation #text-generation-inference #conversational #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us
|
This is an upscaled fp16 variant of the original Mistral-7B-Instruct-v0.1 base model by Mistral after it has been loaded with nf4 4-bit quantization via bitsandbytes.
The main idea here is to upscale the linear4bit layers to fp16 so that the quantization/dequantization cost doesn't have to paid for each forward pass at inference time.
_Note: The quantization operation to nf4 is not lossless, so the model weights for the linear layers are lossy, which means that this model will not work as well as the official base model._
To use this model, you can just load it via 'transformers' in fp16:
| [] | [
"TAGS\n#transformers #safetensors #mistral #text-generation #text-generation-inference #conversational #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n"
] |
null | transformers | ## About
<!-- ### quantize_version: 1 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: -->
<!-- ### vocab_type: -->
static quants of https://huggingface.co/AlekseiPravdin/KSI-RP-NSK-128k-7B
<!-- provided-files -->
weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
## 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/KSI-RP-NSK-128k-7B-GGUF/resolve/main/KSI-RP-NSK-128k-7B.Q2_K.gguf) | Q2_K | 2.8 | |
| [GGUF](https://huggingface.co/mradermacher/KSI-RP-NSK-128k-7B-GGUF/resolve/main/KSI-RP-NSK-128k-7B.IQ3_XS.gguf) | IQ3_XS | 3.1 | |
| [GGUF](https://huggingface.co/mradermacher/KSI-RP-NSK-128k-7B-GGUF/resolve/main/KSI-RP-NSK-128k-7B.Q3_K_S.gguf) | Q3_K_S | 3.3 | |
| [GGUF](https://huggingface.co/mradermacher/KSI-RP-NSK-128k-7B-GGUF/resolve/main/KSI-RP-NSK-128k-7B.IQ3_S.gguf) | IQ3_S | 3.3 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/KSI-RP-NSK-128k-7B-GGUF/resolve/main/KSI-RP-NSK-128k-7B.IQ3_M.gguf) | IQ3_M | 3.4 | |
| [GGUF](https://huggingface.co/mradermacher/KSI-RP-NSK-128k-7B-GGUF/resolve/main/KSI-RP-NSK-128k-7B.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/KSI-RP-NSK-128k-7B-GGUF/resolve/main/KSI-RP-NSK-128k-7B.Q3_K_L.gguf) | Q3_K_L | 3.9 | |
| [GGUF](https://huggingface.co/mradermacher/KSI-RP-NSK-128k-7B-GGUF/resolve/main/KSI-RP-NSK-128k-7B.IQ4_XS.gguf) | IQ4_XS | 4.0 | |
| [GGUF](https://huggingface.co/mradermacher/KSI-RP-NSK-128k-7B-GGUF/resolve/main/KSI-RP-NSK-128k-7B.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/KSI-RP-NSK-128k-7B-GGUF/resolve/main/KSI-RP-NSK-128k-7B.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/KSI-RP-NSK-128k-7B-GGUF/resolve/main/KSI-RP-NSK-128k-7B.Q5_K_S.gguf) | Q5_K_S | 5.1 | |
| [GGUF](https://huggingface.co/mradermacher/KSI-RP-NSK-128k-7B-GGUF/resolve/main/KSI-RP-NSK-128k-7B.Q5_K_M.gguf) | Q5_K_M | 5.2 | |
| [GGUF](https://huggingface.co/mradermacher/KSI-RP-NSK-128k-7B-GGUF/resolve/main/KSI-RP-NSK-128k-7B.Q6_K.gguf) | Q6_K | 6.0 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/KSI-RP-NSK-128k-7B-GGUF/resolve/main/KSI-RP-NSK-128k-7B.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality |
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", "tags": ["merge", "mergekit", "lazymergekit", "AlekseiPravdin/KukulStanta-InfinityRP-7B-slerp", "AlekseiPravdin/NSK-128k-7B-slerp"], "base_model": "AlekseiPravdin/KSI-RP-NSK-128k-7B", "quantized_by": "mradermacher"} | mradermacher/KSI-RP-NSK-128k-7B-GGUF | null | [
"transformers",
"gguf",
"merge",
"mergekit",
"lazymergekit",
"AlekseiPravdin/KukulStanta-InfinityRP-7B-slerp",
"AlekseiPravdin/NSK-128k-7B-slerp",
"en",
"base_model:AlekseiPravdin/KSI-RP-NSK-128k-7B",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2024-04-17T19:28:43+00:00 | [] | [
"en"
] | TAGS
#transformers #gguf #merge #mergekit #lazymergekit #AlekseiPravdin/KukulStanta-InfinityRP-7B-slerp #AlekseiPravdin/NSK-128k-7B-slerp #en #base_model-AlekseiPravdin/KSI-RP-NSK-128k-7B #license-apache-2.0 #endpoints_compatible #region-us
| About
-----
static quants of URL
weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
Usage
-----
If you are unsure how to use GGUF files, refer to one of TheBloke's
READMEs 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)
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
!URL
And here are Artefact2's thoughts on the matter:
URL
FAQ / Model Request
-------------------
See URL for some answers to
questions you might have and/or if you want some other model quantized.
Thanks
------
I thank my company, nethype GmbH, for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
| [] | [
"TAGS\n#transformers #gguf #merge #mergekit #lazymergekit #AlekseiPravdin/KukulStanta-InfinityRP-7B-slerp #AlekseiPravdin/NSK-128k-7B-slerp #en #base_model-AlekseiPravdin/KSI-RP-NSK-128k-7B #license-apache-2.0 #endpoints_compatible #region-us \n"
] |
text-generation | transformers |
This is an upscaled fp16 variant of the original HuggingFaceH4/zephyr-7b-beta model after it has been loaded with nf4 4-bit quantization via bitsandbytes.
The main idea here is to upscale the linear4bit layers to fp16 so that the quantization/dequantization cost doesn't have to paid for each forward pass at inference time.
_Note: The quantization operation to nf4 is not lossless, so the model weights for the linear layers are lossy, which means that this model will not work as well as the official base model._
To use this model, you can just load it via `transformers` in fp16:
```python
import torch
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained(
"predibase/zephyr-7b-beta-dequantized",
device_map="auto",
torch_dtype=torch.float16,
)
``` | {"license": "apache-2.0", "tags": ["text-generation-inference"]} | predibase/zephyr-7b-beta-dequantized | null | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"text-generation-inference",
"conversational",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-04-17T19:28:59+00:00 | [] | [] | TAGS
#transformers #safetensors #mistral #text-generation #text-generation-inference #conversational #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us
|
This is an upscaled fp16 variant of the original HuggingFaceH4/zephyr-7b-beta model after it has been loaded with nf4 4-bit quantization via bitsandbytes.
The main idea here is to upscale the linear4bit layers to fp16 so that the quantization/dequantization cost doesn't have to paid for each forward pass at inference time.
_Note: The quantization operation to nf4 is not lossless, so the model weights for the linear layers are lossy, which means that this model will not work as well as the official base model._
To use this model, you can just load it via 'transformers' in fp16:
| [] | [
"TAGS\n#transformers #safetensors #mistral #text-generation #text-generation-inference #conversational #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n"
] |
null | 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": []} | badrmarani/mymodel-test | null | [
"transformers",
"safetensors",
"resnet",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2024-04-17T19:29:17+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #safetensors #resnet #arxiv-1910.09700 #endpoints_compatible #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
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:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
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.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
| [
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] | [
"TAGS\n#transformers #safetensors #resnet #arxiv-1910.09700 #endpoints_compatible #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
text-generation | transformers |
This is an upscaled fp16 variant of the original Llama-2-70b-chat base model by Meta after it has been loaded with nf4 4-bit quantization via bitsandbytes.
The main idea here is to upscale the linear4bit layers to fp16 so that the quantization/dequantization cost doesn't have to paid for each forward pass at inference time.
_Note: The quantization operation to nf4 is not lossless, so the model weights for the linear layers are lossy, which means that this model will not work as well as the official base model._
To use this model, you can just load it via `transformers` in fp16:
```python
import torch
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained(
"predibase/Llama-2-70b-chat-hf-dequantized",
device_map="auto",
torch_dtype=torch.float16,
)
``` | {"license": "apache-2.0", "tags": ["text-generation-inference"]} | predibase/Llama-2-70b-chat-hf-dequantized | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"text-generation-inference",
"conversational",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-04-17T19:29:22+00:00 | [] | [] | TAGS
#transformers #safetensors #llama #text-generation #text-generation-inference #conversational #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us
|
This is an upscaled fp16 variant of the original Llama-2-70b-chat base model by Meta after it has been loaded with nf4 4-bit quantization via bitsandbytes.
The main idea here is to upscale the linear4bit layers to fp16 so that the quantization/dequantization cost doesn't have to paid for each forward pass at inference time.
_Note: The quantization operation to nf4 is not lossless, so the model weights for the linear layers are lossy, which means that this model will not work as well as the official base model._
To use this model, you can just load it via 'transformers' in fp16:
| [] | [
"TAGS\n#transformers #safetensors #llama #text-generation #text-generation-inference #conversational #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n"
] |
text-generation | transformers |
This is an upscaled fp16 variant of the original NousResearch/Yarn-Mistral-7b-128k base model after it has been loaded with nf4 4-bit quantization via bitsandbytes.
The main idea here is to upscale the linear4bit layers to fp16 so that the quantization/dequantization cost doesn't have to paid for each forward pass at inference time.
_Note: The quantization operation to nf4 is not lossless, so the model weights for the linear layers are lossy, which means that this model will not work as well as the official base model._
To use this model, you can just load it via `transformers` in fp16:
```python
import torch
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained(
"predibase/NousResearch-Yarn-Mistral-7b-128k-dequantized",
device_map="auto",
torch_dtype=torch.float16,
)
``` | {"license": "apache-2.0", "tags": ["text-generation-inference"]} | predibase/NousResearch-Yarn-Mistral-7b-128k-dequantized | null | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"text-generation-inference",
"custom_code",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-04-17T19:29:43+00:00 | [] | [] | TAGS
#transformers #safetensors #mistral #text-generation #text-generation-inference #custom_code #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us
|
This is an upscaled fp16 variant of the original NousResearch/Yarn-Mistral-7b-128k base model after it has been loaded with nf4 4-bit quantization via bitsandbytes.
The main idea here is to upscale the linear4bit layers to fp16 so that the quantization/dequantization cost doesn't have to paid for each forward pass at inference time.
_Note: The quantization operation to nf4 is not lossless, so the model weights for the linear layers are lossy, which means that this model will not work as well as the official base model._
To use this model, you can just load it via 'transformers' in fp16:
| [] | [
"TAGS\n#transformers #safetensors #mistral #text-generation #text-generation-inference #custom_code #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n"
] |
text-generation | transformers |
This is an upscaled fp16 variant of the original CodeLlama-70b-instruct base model by Meta after it has been loaded with nf4 4-bit quantization via bitsandbytes.
The main idea here is to upscale the linear4bit layers to fp16 so that the quantization/dequantization cost doesn't have to paid for each forward pass at inference time.
_Note: The quantization operation to nf4 is not lossless, so the model weights for the linear layers are lossy, which means that this model will not work as well as the official base model._
To use this model, you can just load it via `transformers` in fp16:
```python
import torch
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained(
"predibase/CodeLlama-70B-Instruct-hf-dequantized",
device_map="auto",
torch_dtype=torch.float16,
)
``` | {"license": "apache-2.0", "tags": ["text-generation-inference"]} | predibase/CodeLlama-70B-Instruct-hf-dequantized | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"text-generation-inference",
"conversational",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-04-17T19:30:14+00:00 | [] | [] | TAGS
#transformers #safetensors #llama #text-generation #text-generation-inference #conversational #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us
|
This is an upscaled fp16 variant of the original CodeLlama-70b-instruct base model by Meta after it has been loaded with nf4 4-bit quantization via bitsandbytes.
The main idea here is to upscale the linear4bit layers to fp16 so that the quantization/dequantization cost doesn't have to paid for each forward pass at inference time.
_Note: The quantization operation to nf4 is not lossless, so the model weights for the linear layers are lossy, which means that this model will not work as well as the official base model._
To use this model, you can just load it via 'transformers' in fp16:
| [] | [
"TAGS\n#transformers #safetensors #llama #text-generation #text-generation-inference #conversational #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n"
] |
text-generation | transformers |
This is an upscaled fp16 variant of the original Phi-2 base model by Microsoft after it has been loaded with nf4 4-bit quantization via bitsandbytes.
The main idea here is to upscale the linear4bit layers to fp16 so that the quantization/dequantization cost doesn't have to paid for each forward pass at inference time.
_Note: The quantization operation to nf4 is not lossless, so the model weights for the linear layers are lossy, which means that this model will not work as well as the official base model._
To use this model, you can just load it via `transformers` in fp16:
```python
import torch
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained(
"predibase/phi-2-dequantized",
torch_dtype=torch.float16,
)
``` | {"license": "apache-2.0", "tags": ["text-generation-inference"]} | predibase/phi-2-dequantized | null | [
"transformers",
"safetensors",
"phi",
"text-generation",
"text-generation-inference",
"custom_code",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-04-17T19:30:34+00:00 | [] | [] | TAGS
#transformers #safetensors #phi #text-generation #text-generation-inference #custom_code #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us
|
This is an upscaled fp16 variant of the original Phi-2 base model by Microsoft after it has been loaded with nf4 4-bit quantization via bitsandbytes.
The main idea here is to upscale the linear4bit layers to fp16 so that the quantization/dequantization cost doesn't have to paid for each forward pass at inference time.
_Note: The quantization operation to nf4 is not lossless, so the model weights for the linear layers are lossy, which means that this model will not work as well as the official base model._
To use this model, you can just load it via 'transformers' in fp16:
| [] | [
"TAGS\n#transformers #safetensors #phi #text-generation #text-generation-inference #custom_code #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n"
] |
text-generation | transformers |
This is an upscaled fp16 variant of the original Mistral-7b base model by Mistral after it has been loaded with nf4 4-bit quantization via bitsandbytes.
The main idea here is to upscale the linear4bit layers to fp16 so that the quantization/dequantization cost doesn't have to paid for each forward pass at inference time.
_Note: The quantization operation to nf4 is not lossless, so the model weights for the linear layers are lossy, which means that this model will not work as well as the official base model._
To use this model, you can just load it via `transformers` in fp16:
```python
import torch
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained(
"predibase/Mistral-7B-v0.1-dequantized",
device_map="auto",
torch_dtype=torch.float16,
)
``` | {"license": "apache-2.0", "tags": ["text-generation-inference"]} | predibase/Mistral-7B-v0.1-dequantized | null | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"text-generation-inference",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-04-17T19:31:06+00:00 | [] | [] | TAGS
#transformers #safetensors #mistral #text-generation #text-generation-inference #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us
|
This is an upscaled fp16 variant of the original Mistral-7b base model by Mistral after it has been loaded with nf4 4-bit quantization via bitsandbytes.
The main idea here is to upscale the linear4bit layers to fp16 so that the quantization/dequantization cost doesn't have to paid for each forward pass at inference time.
_Note: The quantization operation to nf4 is not lossless, so the model weights for the linear layers are lossy, which means that this model will not work as well as the official base model._
To use this model, you can just load it via 'transformers' in fp16:
| [] | [
"TAGS\n#transformers #safetensors #mistral #text-generation #text-generation-inference #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n"
] |
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 [TIES](https://arxiv.org/abs/2306.01708) merge method using [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) as a base.
### Models Merged
The following models were included in the merge:
* [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2)
* [BioMistral/BioMistral-7B](https://huggingface.co/BioMistral/BioMistral-7B)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
models:
- model: mistralai/Mistral-7B-v0.1
#no parameters necessary for base model
- model: mistralai/Mistral-7B-Instruct-v0.2
parameters:
density: 0.5
weight: 0.5
- model: BioMistral/BioMistral-7B
parameters:
density: 0.5
weight: 0.5
merge_method: ties
base_model: mistralai/Mistral-7B-v0.1
parameters:
normalize: false
int8_mask: true
dtype: float16
```
| {"library_name": "transformers", "tags": ["mergekit", "merge"], "base_model": ["mistralai/Mistral-7B-v0.1", "mistralai/Mistral-7B-Instruct-v0.2", "BioMistral/BioMistral-7B"]} | mergekit-community/mergekit-ties-cmdmayc | null | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"mergekit",
"merge",
"arxiv:2306.01708",
"base_model:mistralai/Mistral-7B-v0.1",
"base_model:mistralai/Mistral-7B-Instruct-v0.2",
"base_model:BioMistral/BioMistral-7B",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-04-17T19:31:54+00:00 | [
"2306.01708"
] | [] | TAGS
#transformers #safetensors #mistral #text-generation #mergekit #merge #arxiv-2306.01708 #base_model-mistralai/Mistral-7B-v0.1 #base_model-mistralai/Mistral-7B-Instruct-v0.2 #base_model-BioMistral/BioMistral-7B #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us
| # merge
This is a merge of pre-trained language models created using mergekit.
## Merge Details
### Merge Method
This model was merged using the TIES merge method using mistralai/Mistral-7B-v0.1 as a base.
### Models Merged
The following models were included in the merge:
* mistralai/Mistral-7B-Instruct-v0.2
* BioMistral/BioMistral-7B
### Configuration
The following YAML configuration was used to produce this model:
| [
"# merge\n\nThis is a merge of pre-trained language models created using mergekit.",
"## Merge Details",
"### Merge Method\n\nThis model was merged using the TIES merge method using mistralai/Mistral-7B-v0.1 as a base.",
"### Models Merged\n\nThe following models were included in the merge:\n* mistralai/Mistral-7B-Instruct-v0.2\n* BioMistral/BioMistral-7B",
"### Configuration\n\nThe following YAML configuration was used to produce this model:"
] | [
"TAGS\n#transformers #safetensors #mistral #text-generation #mergekit #merge #arxiv-2306.01708 #base_model-mistralai/Mistral-7B-v0.1 #base_model-mistralai/Mistral-7B-Instruct-v0.2 #base_model-BioMistral/BioMistral-7B #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n",
"# merge\n\nThis is a merge of pre-trained language models created using mergekit.",
"## Merge Details",
"### Merge Method\n\nThis model was merged using the TIES merge method using mistralai/Mistral-7B-v0.1 as a base.",
"### Models Merged\n\nThe following models were included in the merge:\n* mistralai/Mistral-7B-Instruct-v0.2\n* BioMistral/BioMistral-7B",
"### Configuration\n\nThe following YAML configuration was used to produce this model:"
] |
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. -->
# remote_sensing_gpt_expt4
This model is a fine-tuned version of [microsoft/phi-1_5](https://huggingface.co/microsoft/phi-1_5) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 3.3855
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 3.4913 | 1.0 | 916 | 3.4388 |
| 3.2788 | 2.0 | 1832 | 3.3951 |
| 3.218 | 3.0 | 2748 | 3.3855 |
### Framework versions
- PEFT 0.9.0
- Transformers 4.36.2
- Pytorch 2.2.1+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0 | {"license": "mit", "library_name": "peft", "tags": ["generated_from_trainer"], "base_model": "microsoft/phi-1_5", "model-index": [{"name": "remote_sensing_gpt_expt4", "results": []}]} | gremlin97/remote_sensing_gpt_expt4 | null | [
"peft",
"safetensors",
"generated_from_trainer",
"base_model:microsoft/phi-1_5",
"license:mit",
"region:us"
] | null | 2024-04-17T19:32:52+00:00 | [] | [] | TAGS
#peft #safetensors #generated_from_trainer #base_model-microsoft/phi-1_5 #license-mit #region-us
| remote\_sensing\_gpt\_expt4
===========================
This model is a fine-tuned version of microsoft/phi-1\_5 on the None dataset.
It achieves the following results on the evaluation set:
* Loss: 3.3855
Model description
-----------------
More information needed
Intended uses & limitations
---------------------------
More information needed
Training and evaluation data
----------------------------
More information needed
Training procedure
------------------
### Training hyperparameters
The following hyperparameters were used during training:
* learning\_rate: 2e-05
* train\_batch\_size: 8
* eval\_batch\_size: 8
* seed: 42
* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
* lr\_scheduler\_type: linear
* num\_epochs: 3.0
### Training results
### Framework versions
* PEFT 0.9.0
* Transformers 4.36.2
* Pytorch 2.2.1+cu121
* Datasets 2.15.0
* Tokenizers 0.15.0
| [
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 3.0",
"### Training results",
"### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.36.2\n* Pytorch 2.2.1+cu121\n* Datasets 2.15.0\n* Tokenizers 0.15.0"
] | [
"TAGS\n#peft #safetensors #generated_from_trainer #base_model-microsoft/phi-1_5 #license-mit #region-us \n",
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 3.0",
"### Training results",
"### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.36.2\n* Pytorch 2.2.1+cu121\n* Datasets 2.15.0\n* Tokenizers 0.15.0"
] |
null | 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": []} | Enagamirzayev/whisper-small-llm-lingo-adapters_p | null | [
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2024-04-17T19:33:15+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
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:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
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.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
| [
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] | [
"TAGS\n#transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
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. -->
# mr_sam_wav2vec2_nigerian_accent_v1
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3400
- Wer: 0.1900
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 32
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1000
- num_epochs: 40
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 4.456 | 6.67 | 500 | 2.9391 | 1.0 |
| 1.0329 | 13.33 | 1000 | 0.4350 | 0.3343 |
| 0.2048 | 20.0 | 1500 | 0.3604 | 0.2488 |
| 0.1054 | 26.67 | 2000 | 0.3545 | 0.2118 |
| 0.0698 | 33.33 | 2500 | 0.3480 | 0.2012 |
| 0.0529 | 40.0 | 3000 | 0.3400 | 0.1900 |
### Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
| {"license": "apache-2.0", "tags": ["generated_from_trainer"], "metrics": ["wer"], "base_model": "facebook/wav2vec2-base", "model-index": [{"name": "mr_sam_wav2vec2_nigerian_accent_v1", "results": []}]} | samuelchiji/mr_sam_wav2vec2_nigerian_accent_v1 | null | [
"transformers",
"tensorboard",
"safetensors",
"wav2vec2",
"automatic-speech-recognition",
"generated_from_trainer",
"base_model:facebook/wav2vec2-base",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2024-04-17T19:36:06+00:00 | [] | [] | TAGS
#transformers #tensorboard #safetensors #wav2vec2 #automatic-speech-recognition #generated_from_trainer #base_model-facebook/wav2vec2-base #license-apache-2.0 #endpoints_compatible #region-us
| mr\_sam\_wav2vec2\_nigerian\_accent\_v1
=======================================
This model is a fine-tuned version of facebook/wav2vec2-base on an unknown dataset.
It achieves the following results on the evaluation set:
* Loss: 0.3400
* Wer: 0.1900
Model description
-----------------
More information needed
Intended uses & limitations
---------------------------
More information needed
Training and evaluation data
----------------------------
More information needed
Training procedure
------------------
### Training hyperparameters
The following hyperparameters were used during training:
* learning\_rate: 0.0001
* train\_batch\_size: 32
* eval\_batch\_size: 8
* seed: 42
* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
* lr\_scheduler\_type: linear
* lr\_scheduler\_warmup\_steps: 1000
* num\_epochs: 40
* mixed\_precision\_training: Native AMP
### Training results
### Framework versions
* Transformers 4.38.2
* Pytorch 2.2.1+cu121
* Datasets 2.18.0
* Tokenizers 0.15.2
| [
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0001\n* train\\_batch\\_size: 32\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_steps: 1000\n* num\\_epochs: 40\n* mixed\\_precision\\_training: Native AMP",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.38.2\n* Pytorch 2.2.1+cu121\n* Datasets 2.18.0\n* Tokenizers 0.15.2"
] | [
"TAGS\n#transformers #tensorboard #safetensors #wav2vec2 #automatic-speech-recognition #generated_from_trainer #base_model-facebook/wav2vec2-base #license-apache-2.0 #endpoints_compatible #region-us \n",
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0001\n* train\\_batch\\_size: 32\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_steps: 1000\n* num\\_epochs: 40\n* mixed\\_precision\\_training: Native AMP",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.38.2\n* Pytorch 2.2.1+cu121\n* Datasets 2.18.0\n* Tokenizers 0.15.2"
] |
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": []} | Enagamirzayev/whisper-small-llm-lingo_p | null | [
"transformers",
"safetensors",
"whisper",
"automatic-speech-recognition",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2024-04-17T19:36:22+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #safetensors #whisper #automatic-speech-recognition #arxiv-1910.09700 #endpoints_compatible #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
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:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
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.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
| [
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] | [
"TAGS\n#transformers #safetensors #whisper #automatic-speech-recognition #arxiv-1910.09700 #endpoints_compatible #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
text-generation | transformers |
# Model Card for Coxcomb
A creative writing model, using the superb [senseable/WestLake-7B-v2](https://huggingface.co/senseable/WestLake-7B-v2) as a base, finetuned on GPT-4 outputs to a diverse variety of prompts. It in no way competes with GPT-4 - it's quality of writing is below it, and it is primarily meant to be run in offline, local environments.
On creative writing benchmarks, it is consistently ranked higher than most other models - [it scores 72.37](https://eqbench.com/creative_writing.html), beating goliath-120b, yi chat, and mistral-large.
It is designed for **single-shot interactions**. You ask it to write a story, and it does. It is NOT designed for chat purposes, roleplay, or follow-up questions.
## Model Details
Trained w/ a 40M parameter lora on [N8Programs/CreativeGPT](https://huggingface.co/datasets/N8Programs/CreativeGPT) for 3 epochs. Overfit slightly (for much better benchmark results).
### Model Description
- **Developed by:** N8Programs
- **Model type:** Mistral
- **Language(s) (NLP):** English
- **License:** Apache 2.0
- **Finetuned from model:** [senseable/WestLake-7B-v2](https://huggingface.co/senseable/WestLake-7B-v2)
## Uses
Bot trained on NSFW (sexual or violent) content but will generate it when asked - it has not been trained with refusals. If you wish to ADD refusal behavior in, further tuning or filtering will be neccessary.
### Direct Use
GGUFs available at [Coxcomb-GGUF](https://huggingface.co/N8Programs/Coxcomb-GGUF)
Should work with transformers (not officially tested).
## Bias, Risks, and Limitations
Tends to generate stories with happy, trite endings. Most LLMs do this. It's very hard to get them not to.
## Training Details
Trained on a single M3 Max in roughly 12 hours. | {"language": ["en"], "license": "apache-2.0", "datasets": ["N8Programs/CreativeGPT"], "pipeline_tag": "text-generation"} | N8Programs/Coxcomb | null | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"conversational",
"en",
"dataset:N8Programs/CreativeGPT",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-04-17T19:37:17+00:00 | [] | [
"en"
] | TAGS
#transformers #safetensors #mistral #text-generation #conversational #en #dataset-N8Programs/CreativeGPT #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us
|
!image/png
# Model Card for Coxcomb
A creative writing model, using the superb senseable/WestLake-7B-v2 as a base, finetuned on GPT-4 outputs to a diverse variety of prompts. It in no way competes with GPT-4 - it's quality of writing is below it, and it is primarily meant to be run in offline, local environments.
On creative writing benchmarks, it is consistently ranked higher than most other models - it scores 72.37, beating goliath-120b, yi chat, and mistral-large.
It is designed for single-shot interactions. You ask it to write a story, and it does. It is NOT designed for chat purposes, roleplay, or follow-up questions.
## Model Details
Trained w/ a 40M parameter lora on N8Programs/CreativeGPT for 3 epochs. Overfit slightly (for much better benchmark results).
### Model Description
- Developed by: N8Programs
- Model type: Mistral
- Language(s) (NLP): English
- License: Apache 2.0
- Finetuned from model: senseable/WestLake-7B-v2
## Uses
Bot trained on NSFW (sexual or violent) content but will generate it when asked - it has not been trained with refusals. If you wish to ADD refusal behavior in, further tuning or filtering will be neccessary.
### Direct Use
GGUFs available at Coxcomb-GGUF
Should work with transformers (not officially tested).
## Bias, Risks, and Limitations
Tends to generate stories with happy, trite endings. Most LLMs do this. It's very hard to get them not to.
## Training Details
Trained on a single M3 Max in roughly 12 hours. | [
"# Model Card for Coxcomb\n\nA creative writing model, using the superb senseable/WestLake-7B-v2 as a base, finetuned on GPT-4 outputs to a diverse variety of prompts. It in no way competes with GPT-4 - it's quality of writing is below it, and it is primarily meant to be run in offline, local environments.\nOn creative writing benchmarks, it is consistently ranked higher than most other models - it scores 72.37, beating goliath-120b, yi chat, and mistral-large.\nIt is designed for single-shot interactions. You ask it to write a story, and it does. It is NOT designed for chat purposes, roleplay, or follow-up questions.",
"## Model Details\n\nTrained w/ a 40M parameter lora on N8Programs/CreativeGPT for 3 epochs. Overfit slightly (for much better benchmark results).",
"### Model Description\n\n- Developed by: N8Programs\n- Model type: Mistral\n- Language(s) (NLP): English\n- License: Apache 2.0\n- Finetuned from model: senseable/WestLake-7B-v2",
"## Uses\n\nBot trained on NSFW (sexual or violent) content but will generate it when asked - it has not been trained with refusals. If you wish to ADD refusal behavior in, further tuning or filtering will be neccessary.",
"### Direct Use\n\nGGUFs available at Coxcomb-GGUF\nShould work with transformers (not officially tested).",
"## Bias, Risks, and Limitations\n\nTends to generate stories with happy, trite endings. Most LLMs do this. It's very hard to get them not to.",
"## Training Details\n\nTrained on a single M3 Max in roughly 12 hours."
] | [
"TAGS\n#transformers #safetensors #mistral #text-generation #conversational #en #dataset-N8Programs/CreativeGPT #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n",
"# Model Card for Coxcomb\n\nA creative writing model, using the superb senseable/WestLake-7B-v2 as a base, finetuned on GPT-4 outputs to a diverse variety of prompts. It in no way competes with GPT-4 - it's quality of writing is below it, and it is primarily meant to be run in offline, local environments.\nOn creative writing benchmarks, it is consistently ranked higher than most other models - it scores 72.37, beating goliath-120b, yi chat, and mistral-large.\nIt is designed for single-shot interactions. You ask it to write a story, and it does. It is NOT designed for chat purposes, roleplay, or follow-up questions.",
"## Model Details\n\nTrained w/ a 40M parameter lora on N8Programs/CreativeGPT for 3 epochs. Overfit slightly (for much better benchmark results).",
"### Model Description\n\n- Developed by: N8Programs\n- Model type: Mistral\n- Language(s) (NLP): English\n- License: Apache 2.0\n- Finetuned from model: senseable/WestLake-7B-v2",
"## Uses\n\nBot trained on NSFW (sexual or violent) content but will generate it when asked - it has not been trained with refusals. If you wish to ADD refusal behavior in, further tuning or filtering will be neccessary.",
"### Direct Use\n\nGGUFs available at Coxcomb-GGUF\nShould work with transformers (not officially tested).",
"## Bias, Risks, and Limitations\n\nTends to generate stories with happy, trite endings. Most LLMs do this. It's very hard to get them not to.",
"## Training Details\n\nTrained on a single M3 Max in roughly 12 hours."
] |
text-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": []} | kevin36524/gemma-Code-Instruct-Finetune-yahoo-mail | null | [
"transformers",
"safetensors",
"gemma",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-04-17T19:41:20+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #safetensors #gemma #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
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:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
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.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
| [
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] | [
"TAGS\n#transformers #safetensors #gemma #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
null | null |
# KSI-RPG-128k-7B-GGUF ⭐️⭐️⭐️
KSI-RPG-128k-7B is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
* [AlekseiPravdin/KSI-RP-NSK-128k-7B](https://huggingface.co/AlekseiPravdin/KSI-RP-NSK-128k-7B)
* [flammenai/flammen18X-mistral-7B](https://huggingface.co/flammenai/flammen18X-mistral-7B)
## 🧩 Configuration
```yaml
slices:
- sources:
- model: AlekseiPravdin/KSI-RP-NSK-128k-7B
layer_range: [0, 32]
- model: flammenai/flammen18X-mistral-7B
layer_range: [0, 32]
merge_method: slerp
base_model: AlekseiPravdin/KSI-RP-NSK-128k-7B
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
```
Eval embedding benchmark (with 70 specific quesions):
 | {"language": ["en", "ru", "th"], "license": "apache-2.0", "tags": ["merge", "mergekit", "lazymergekit", "AlekseiPravdin/KSI-RP-NSK-128k-7B", "flammenai/flammen18X-mistral-7B", "gguf", "Q2_K", "Q3_K_L", "Q3_K_M", "Q3_K_S", "Q4_0", "Q4_1", "Q4_K_S", "Q4_k_m", "Q5_0", "Q5_1", "Q6_K", "Q5_K_S", "Q5_k_m", "Q8_0", "128k"]} | AlekseiPravdin/KSI-RPG-128k-7B-gguf | null | [
"gguf",
"merge",
"mergekit",
"lazymergekit",
"AlekseiPravdin/KSI-RP-NSK-128k-7B",
"flammenai/flammen18X-mistral-7B",
"Q2_K",
"Q3_K_L",
"Q3_K_M",
"Q3_K_S",
"Q4_0",
"Q4_1",
"Q4_K_S",
"Q4_k_m",
"Q5_0",
"Q5_1",
"Q6_K",
"Q5_K_S",
"Q5_k_m",
"Q8_0",
"128k",
"en",
"ru",
"th",
"license:apache-2.0",
"region:us"
] | null | 2024-04-17T19:43:48+00:00 | [] | [
"en",
"ru",
"th"
] | TAGS
#gguf #merge #mergekit #lazymergekit #AlekseiPravdin/KSI-RP-NSK-128k-7B #flammenai/flammen18X-mistral-7B #Q2_K #Q3_K_L #Q3_K_M #Q3_K_S #Q4_0 #Q4_1 #Q4_K_S #Q4_k_m #Q5_0 #Q5_1 #Q6_K #Q5_K_S #Q5_k_m #Q8_0 #128k #en #ru #th #license-apache-2.0 #region-us
|
# KSI-RPG-128k-7B-GGUF ⭐️⭐️⭐️
KSI-RPG-128k-7B is a merge of the following models using mergekit:
* AlekseiPravdin/KSI-RP-NSK-128k-7B
* flammenai/flammen18X-mistral-7B
## Configuration
Eval embedding benchmark (with 70 specific quesions):
!URL
!URL
!URL
!URL
!URL
!URL
!URL
!URL
!URL
!URL
!URL
!URL
!URL
!URL | [
"# KSI-RPG-128k-7B-GGUF ⭐️⭐️⭐️\n\nKSI-RPG-128k-7B is a merge of the following models using mergekit:\n* AlekseiPravdin/KSI-RP-NSK-128k-7B\n* flammenai/flammen18X-mistral-7B",
"## Configuration\n\n\n\nEval embedding benchmark (with 70 specific quesions):\n\n!URL\n!URL\n!URL\n!URL\n!URL\n!URL\n!URL\n!URL\n!URL\n!URL\n!URL\n!URL\n!URL\n!URL"
] | [
"TAGS\n#gguf #merge #mergekit #lazymergekit #AlekseiPravdin/KSI-RP-NSK-128k-7B #flammenai/flammen18X-mistral-7B #Q2_K #Q3_K_L #Q3_K_M #Q3_K_S #Q4_0 #Q4_1 #Q4_K_S #Q4_k_m #Q5_0 #Q5_1 #Q6_K #Q5_K_S #Q5_k_m #Q8_0 #128k #en #ru #th #license-apache-2.0 #region-us \n",
"# KSI-RPG-128k-7B-GGUF ⭐️⭐️⭐️\n\nKSI-RPG-128k-7B is a merge of the following models using mergekit:\n* AlekseiPravdin/KSI-RP-NSK-128k-7B\n* flammenai/flammen18X-mistral-7B",
"## Configuration\n\n\n\nEval embedding benchmark (with 70 specific quesions):\n\n!URL\n!URL\n!URL\n!URL\n!URL\n!URL\n!URL\n!URL\n!URL\n!URL\n!URL\n!URL\n!URL\n!URL"
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.