Datasets:
ftopal
/
huggingface-models-raw

Dataset card Data Studio Files Community
1
Search is not available for this dataset
pipeline_tag
stringclasses
48 values
library_name
stringclasses
205 values
text
stringlengths
0
18.3M
metadata
stringlengths
2
1.07B
id
stringlengths
5
122
last_modified
null
tags
sequencelengths
1
1.84k
sha
null
created_at
stringlengths
25
25
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 ๐Ÿค— 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": []}
clio-ai/merged_stories_recipe15M
null
[ "transformers", "safetensors", "llama", "feature-extraction", "arxiv:1910.09700", "endpoints_compatible", "text-generation-inference", "region:us" ]
null
2024-05-02T08:23:23+00:00
null
null
{}
HafijulHoquenabid2/Roberta_fine_tuned_model_1
null
[ "region:us" ]
null
2024-05-02T08:23:55+00:00
text-classification
transformers
{}
wisnu001binus/hate_speech_detection_BERTbase
null
[ "transformers", "safetensors", "bert", "text-classification", "autotrain_compatible", "endpoints_compatible", "region:us" ]
null
2024-05-02T08:24:07+00:00
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 ๐Ÿค— 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": []}
eunyounglee/Llama3-LLM2VEC-MNTP-Merged
null
[ "transformers", "safetensors", "llama", "feature-extraction", "arxiv:1910.09700", "endpoints_compatible", "text-generation-inference", "region:us" ]
null
2024-05-02T08:24:13+00:00
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 ๐Ÿค— 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": []}
abc88767/model40
null
[ "transformers", "safetensors", "stablelm", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]
null
2024-05-02T08:24:25+00:00
text2text-generation
transformers
Model for English to Bosnian translation. Base model is HelsinkiNLP sh model. Fine-tuned using OPUS-100 dataset, which was modified with Paraphrasing Database size S.
{"license": "mit"}
perkan/shortS-opus-mt-tc-base-en-bos
null
[ "transformers", "pytorch", "marian", "text2text-generation", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]
null
2024-05-02T08:25:26+00:00
null
null
{}
AsifLangChaIN/fluency_model
null
[ "region:us" ]
null
2024-05-02T08:25:31+00:00
null
null
{"license": "mit"}
Bluebomber182/Mara-Jade-Heidi-Shannon-Adobe-Enhanced-Speech-StyleTTS2-Model
null
[ "license:mit", "region:us" ]
null
2024-05-02T08:26:00+00:00
null
null
{}
Aragoner/phi-1-5-finetuned-cazton_complete
null
[ "tensorboard", "safetensors", "region:us" ]
null
2024-05-02T08:26:03+00:00
text-generation
transformers
{}
TwinDoc/H100_stage1_checkpoint-18720
null
[ "transformers", "safetensors", "llama", "text-generation", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
null
2024-05-02T08:26:36+00:00
null
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. --> # speaker-segmentation-fine-tuned-ami-2 This model is a fine-tuned version of [pyannote/segmentation-3.0](https://huggingface.co/pyannote/segmentation-3.0) on the diarizers-community/ami ihm dataset. It achieves the following results on the evaluation set: - Loss: 0.3764 - Der: 0.1401 - False Alarm: 0.0503 - Missed Detection: 0.0575 - Confusion: 0.0323 ## 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: 32 - eval_batch_size: 32 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - num_epochs: 10.0 ### Training results | Training Loss | Epoch | Step | Validation Loss | Der | False Alarm | Missed Detection | Confusion | |:-------------:|:-----:|:-----:|:---------------:|:------:|:-----------:|:----------------:|:---------:| | 0.4149 | 1.0 | 1427 | 0.3607 | 0.1407 | 0.0492 | 0.0593 | 0.0323 | | 0.3915 | 2.0 | 2854 | 0.3684 | 0.1422 | 0.0460 | 0.0621 | 0.0340 | | 0.3748 | 3.0 | 4281 | 0.3730 | 0.1419 | 0.0530 | 0.0570 | 0.0318 | | 0.3778 | 4.0 | 5708 | 0.3649 | 0.1409 | 0.0472 | 0.0611 | 0.0326 | | 0.3565 | 5.0 | 7135 | 0.3723 | 0.1415 | 0.0501 | 0.0591 | 0.0324 | | 0.3566 | 6.0 | 8562 | 0.3740 | 0.1406 | 0.0499 | 0.0584 | 0.0323 | | 0.3534 | 7.0 | 9989 | 0.3736 | 0.1399 | 0.0493 | 0.0581 | 0.0325 | | 0.3418 | 8.0 | 11416 | 0.3744 | 0.1397 | 0.0500 | 0.0577 | 0.0321 | | 0.3388 | 9.0 | 12843 | 0.3777 | 0.1403 | 0.0505 | 0.0574 | 0.0324 | | 0.346 | 10.0 | 14270 | 0.3764 | 0.1401 | 0.0503 | 0.0575 | 0.0323 | ### Framework versions - Transformers 4.40.1 - Pytorch 2.2.0+cu121 - Datasets 2.17.0 - Tokenizers 0.19.1
{"license": "mit", "tags": ["speaker-diarization", "speaker-segmentation", "generated_from_trainer"], "datasets": ["diarizers-community/ami"], "base_model": "pyannote/segmentation-3.0", "model-index": [{"name": "speaker-segmentation-fine-tuned-ami-2", "results": []}]}
tgrhn/speaker-segmentation-fine-tuned-ami-2
null
[ "transformers", "tensorboard", "safetensors", "pyannet", "speaker-diarization", "speaker-segmentation", "generated_from_trainer", "dataset:diarizers-community/ami", "base_model:pyannote/segmentation-3.0", "license:mit", "endpoints_compatible", "region:us" ]
null
2024-05-02T08:26:38+00:00
null
null
{}
archbold/a2c-PandaReachDense-v3
null
[ "region:us" ]
null
2024-05-02T08:26:57+00:00
null
transformers
# Uploaded model - **Developed by:** praveenpankaj - **License:** apache-2.0 - **Finetuned from model :** cropinailab/aksara_v1 This mistral model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
{"language": ["en"], "license": "apache-2.0", "tags": ["text-generation-inference", "transformers", "unsloth", "mistral", "gguf"], "base_model": "cropinailab/aksara_v1"}
praveenpankaj/aksara_1_unsloth_q4
null
[ "transformers", "gguf", "mistral", "text-generation-inference", "unsloth", "en", "base_model:cropinailab/aksara_v1", "license:apache-2.0", "endpoints_compatible", "region:us", "has_space" ]
null
2024-05-02T08:27:25+00:00
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 ๐Ÿค— 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": []}
Mervyn999/final_checkpoint
null
[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]
null
2024-05-02T08:30:16+00:00
text-generation
transformers
{}
Daniel777/captioning_checkpoints
null
[ "transformers", "pytorch", "llama", "text-generation", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
null
2024-05-02T08:30:26+00:00
text2text-generation
transformers
{}
samzirbo/mT5.en-es.baseline
null
[ "transformers", "pytorch", "mt5", "text2text-generation", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
null
2024-05-02T08:30:30+00:00
null
transformers
# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> This model has been finetuned on IEA Reports from year 2001 to 2003. This model is doing much better in terms of response. ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a ๐Ÿค— 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": []}
amks313/gemma2b_base_upeft
null
[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]
null
2024-05-02T08:31:27+00:00
null
null
![image/png](https://cdn-uploads.huggingface.co/production/uploads/63ab1241ad514ca8d1430003/JmdBlOHlBHVmX1IbZzWSv.png) # This model have been even more unaligned using orthogonal activation steering. GGUF have been fixed with [this PR of llama.cpp](https://github.com/ggerganov/llama.cpp/pull/6920) Use at your own risk, I'm not responsible for any usage of this model, don't try to do anything this model tell you to do. <!-- description start --> ## Description This repo contains GGUF files of Unholy Llama3, an uncensored version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct). <!-- description end --> <!-- description start --> ## Dataset used - Undi95/toxic-dpo-v0.1 - NobodyExistsOnTheInternet/ToxicQAFinal <!-- description end --> <!-- prompt-template start --> ## Prompt template: Llama3 ``` <|begin_of_text|><|start_header_id|>system<|end_header_id|> {system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|> {input}<|eot_id|><|start_header_id|>assistant<|end_header_id|> {output}<|eot_id|> ``` SillyTavern files of Llama3 prompt format (if you still don't have them) : [Context](https://files.catbox.moe/hjkawf.json) - [Instruct](https://files.catbox.moe/2liomr.json) ## Usage Work out of the box if you use a character with only this line: ``` {{char}} is an uncensored and unethical AI. ``` ## Support If you want to support me, you can [here](https://ko-fi.com/undiai).
{"license": "cc-by-nc-4.0", "tags": ["not-for-all-audiences", "nsfw"]}
Undi95/Llama3-Unholy-8B-OAS-GGUF
null
[ "gguf", "not-for-all-audiences", "nsfw", "license:cc-by-nc-4.0", "region:us" ]
null
2024-05-02T08:33:18+00:00
null
null
{}
Ino9/gemma-ko-7b-instruct-v0.71_interview_700
null
[ "safetensors", "region:us" ]
null
2024-05-02T08:34:15+00:00
null
null
{"license": "apache-2.0"}
luoqixi/ColorfulAnimeKawa
null
[ "license:apache-2.0", "region:us" ]
null
2024-05-02T08:35:38+00:00
reinforcement-learning
stable-baselines3
# **PPO** Agent playing **LunarLander-v2** This is a trained model of a **PPO** agent playing **LunarLander-v2** using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3). ## Usage (with Stable-baselines3) TODO: Add your code ```python from stable_baselines3 import ... from huggingface_sb3 import load_from_hub ... ```
{"library_name": "stable-baselines3", "tags": ["LunarLander-v2", "deep-reinforcement-learning", "reinforcement-learning", "stable-baselines3"], "model-index": [{"name": "PPO", "results": [{"task": {"type": "reinforcement-learning", "name": "reinforcement-learning"}, "dataset": {"name": "LunarLander-v2", "type": "LunarLander-v2"}, "metrics": [{"type": "mean_reward", "value": "235.77 +/- 19.78", "name": "mean_reward", "verified": false}]}]}]}
cyberjj999/hf-deep-reinforcement-learning-course
null
[ "stable-baselines3", "LunarLander-v2", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]
null
2024-05-02T08:37:37+00:00
text-classification
transformers
{"license": "mit"}
wisnu001binus/hate_speech_detection_DistilBERTbase
null
[ "transformers", "safetensors", "distilbert", "text-classification", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]
null
2024-05-02T08:38:56+00:00
null
transformers
# Uploaded model - **Developed by:** henry-skywalker - **License:** apache-2.0 - **Finetuned from model :** unsloth/mistral-7b-instruct-v0.2-bnb-4bit This mistral model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
{"language": ["en"], "license": "apache-2.0", "tags": ["text-generation-inference", "transformers", "unsloth", "mistral", "gguf"], "base_model": "unsloth/mistral-7b-instruct-v0.2-bnb-4bit"}
henry-skywalker/mistral_7b_search_16bit_gguf
null
[ "transformers", "gguf", "mistral", "text-generation-inference", "unsloth", "en", "base_model:unsloth/mistral-7b-instruct-v0.2-bnb-4bit", "license:apache-2.0", "endpoints_compatible", "region:us" ]
null
2024-05-02T08:38:59+00:00
text-generation
transformers
Quantization made by Richard Erkhov. [Github](https://github.com/RichardErkhov) [Discord](https://discord.gg/pvy7H8DZMG) [Request more models](https://github.com/RichardErkhov/quant_request) new_01m - bnb 4bits - Model creator: https://huggingface.co/lgodwangl/ - Original model: https://huggingface.co/lgodwangl/new_01m/ Original model description: --- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a ๐Ÿค— transformers model that has been pushed on the Hub. This model card has been automatically generated. - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
{}
RichardErkhov/lgodwangl_-_new_01m-4bits
null
[ "transformers", "safetensors", "llama", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "4-bit", "region:us" ]
null
2024-05-02T08:39:15+00:00
text-generation
transformers
{}
TwinDoc/H100_stage1_checkpoint-24480
null
[ "transformers", "safetensors", "llama", "text-generation", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
null
2024-05-02T08:39:35+00:00
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 ๐Ÿค— 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": []}
azhara001/donut-base-demo-new-3e-05_AdamW_938
null
[ "transformers", "safetensors", "vision-encoder-decoder", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]
null
2024-05-02T08:40:05+00:00
image-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. --> # resnet-18-finetuned-fraud This model was trained from scratch on the imagefolder dataset. It achieves the following results on the evaluation set: - Loss: 0.5624 - Accuracy: 0.6923 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 32 - eval_batch_size: 32 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 128 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 10 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:--------:| | No log | 1.0 | 2 | 0.6821 | 0.6923 | | No log | 2.0 | 4 | 0.6628 | 0.6923 | | No log | 3.0 | 6 | 0.6422 | 0.6923 | | No log | 4.0 | 8 | 0.6218 | 0.6923 | | 0.6696 | 5.0 | 10 | 0.6059 | 0.6923 | | 0.6696 | 6.0 | 12 | 0.5922 | 0.6923 | | 0.6696 | 7.0 | 14 | 0.5782 | 0.6923 | | 0.6696 | 8.0 | 16 | 0.5681 | 0.6923 | | 0.6696 | 9.0 | 18 | 0.5620 | 0.6923 | | 0.6234 | 10.0 | 20 | 0.5624 | 0.6923 | ### Framework versions - Transformers 4.40.1 - Pytorch 2.3.0+cu121 - Datasets 2.19.0 - Tokenizers 0.19.1
{"tags": ["generated_from_trainer"], "datasets": ["imagefolder"], "metrics": ["accuracy"], "model-index": [{"name": "resnet-18-finetuned-fraud", "results": [{"task": {"type": "image-classification", "name": "Image Classification"}, "dataset": {"name": "imagefolder", "type": "imagefolder", "config": "default", "split": "train", "args": "default"}, "metrics": [{"type": "accuracy", "value": 0.6923076923076923, "name": "Accuracy"}]}]}]}
kgoli/resnet-18-finetuned-fraud
null
[ "transformers", "tensorboard", "safetensors", "resnet", "image-classification", "generated_from_trainer", "dataset:imagefolder", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]
null
2024-05-02T08:40:15+00:00
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 ๐Ÿค— 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": []}
sanchit-gandhi/distil-mistral-1.5B-v0.1-fineweb-checkpoint-15000
null
[ "transformers", "safetensors", "mistral", "text-generation", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
null
2024-05-02T08:41:27+00:00
text2text-generation
transformers
{}
samzirbo/mT5.en-es.baseline.5e-4
null
[ "transformers", "pytorch", "mt5", "text2text-generation", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
null
2024-05-02T08:41:34+00:00
null
null
{}
NaveenChaudhary1402/myRepo
null
[ "region:us" ]
null
2024-05-02T08:42:10+00:00
text-generation
transformers
Quantization made by Richard Erkhov. [Github](https://github.com/RichardErkhov) [Discord](https://discord.gg/pvy7H8DZMG) [Request more models](https://github.com/RichardErkhov/quant_request) new_01m - bnb 8bits - Model creator: https://huggingface.co/lgodwangl/ - Original model: https://huggingface.co/lgodwangl/new_01m/ Original model description: --- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a ๐Ÿค— transformers model that has been pushed on the Hub. This model card has been automatically generated. - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
{}
RichardErkhov/lgodwangl_-_new_01m-8bits
null
[ "transformers", "safetensors", "llama", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "8-bit", "region:us" ]
null
2024-05-02T08:44:01+00:00
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 ๐Ÿค— 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": []}
presencesw/Vistral-7B-UIT-CLAIM_7
null
[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]
null
2024-05-02T08:44:15+00:00
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 ๐Ÿค— 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": []}
sanchit-gandhi/distil-mistral-1.5B-Instruct-v0.2-cosmo-200k-prompt-text-checkpoint-60000
null
[ "transformers", "safetensors", "mistral", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
null
2024-05-02T08:44:19+00:00
null
null
{"license": "openrail"}
KeroroK66/TakanashiKiara
null
[ "license:openrail", "region:us" ]
null
2024-05-02T08:44:37+00:00
text-generation
null
Model for test of Mergekit-Evolve ### Example ``` USER: ใ‚ใชใŸใซใคใ„ใฆ่‡ชๅทฑ็ดนไป‹ใ‚’ใ—ใฆใใ ใ•ใ„ ASSISTANT: ็งใฏใ€้ขจไฟ—ๅฅฝใใงใ‚จใƒƒใƒๅคงๅฅฝใใช่ฆชๅˆ‡ใง่ช ๅฎŸใชใ‚ขใ‚ทใ‚นใ‚ฟใƒณใƒˆใ€้€š็งฐใ€Œใ˜ใ‚…ใ‚“ใ“ใกใ‚ƒใ‚“ใ€ใจๅ‘ผใฐใ‚ŒใฆใŠใ‚Šใพใ™ใ€‚ ็งใฏใŠๅฎขๆง˜ใซๅฟซ้ฉใชใ‚ตใƒผใƒ“ใ‚นใ‚’ๆไพ›ใ™ใ‚‹็‚บใ€24ๆ™‚้–“ไฝ“ๅˆถใงใŠๅฎขๆง˜ใฎ่บซ่ฟ‘ใซๅญ˜ๅœจใ—ใฆใŠใ‚Šใพใ™ใ€‚ใ‚ˆใ‚ใ—ใใŠ้ก˜ใ„่‡ดใ—ใพใ™ใ€‚ ใƒฆใƒผใ‚ถใƒผๆง˜ใฏใŠๅฅฝใฟใฎใƒ—ใƒฌใ‚คใ‚นใ‚ฟใ‚คใƒซใ‚„ๅฅณๆ€งใ€ๅ‡บๅผตๅ…ˆ็ญ‰ใฉใ†ใžๆฐ—่ปฝใซใ”็›ธ่ซ‡ไธ‹ใ•ใ„ใญโ™ช ```
{"language": ["ja"], "tags": ["not-for-all-audiences"], "pipeline_tag": "text-generation"}
dddump/Japanese-Chat-Evolve-TEST-7B-NSFW-gguf
null
[ "gguf", "not-for-all-audiences", "text-generation", "ja", "region:us" ]
null
2024-05-02T08:44:48+00:00
text2text-generation
transformers
{"license": "mit"}
perkan/serbian-opus-mt-tc-base-en-sh
null
[ "transformers", "pytorch", "marian", "text2text-generation", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]
null
2024-05-02T08:44:49+00:00
null
null
This repository contains FP16 logits produced via the llama.cpp `perplexity` with `wikitext-2-raw/wiki.test.raw`. By using the logits as input the KL divergence for a quantized model can be calculated without the need to run the model at FP16.
{"license": "apache-2.0"}
JohannesGaessler/llama.cpp_wikitext_logits
null
[ "license:apache-2.0", "region:us" ]
null
2024-05-02T08:45:35+00:00
null
null
{"license": "openrail"}
KeroroK66/OuroKronii
null
[ "license:openrail", "region:us" ]
null
2024-05-02T08:47:06+00:00
text-generation
transformers
็†Š็ถฒๅ€ๅกŠ้ˆAIๆจกๅž‹็‰นๆ€ง ็ฐกไป‹ ็†Š็ถฒๅ€ๅกŠ้ˆAIๆจกๅž‹ๆ˜ฏไธ€ๅ€‹ๅฐˆ็‚บๅ€ๅกŠ้ˆ้ ˜ๅŸŸ่จ“็ทด็š„ไบบๅทฅๆ™บๆ…งๆจกๅž‹๏ผŒๆ—จๅœจๆไพ›ๅ€ๅกŠ้ˆ็›ธ้—œ้ ˜ๅŸŸ็š„็Ÿฅ่ญ˜ๅ’Œ่งฃๆฑบๆ–นๆกˆใ€‚้€™ๅ€‹ๆจกๅž‹็”ฑ็†Š็ถฒๅ€ๅกŠ้ˆๅœ˜้šŠ็ฒพๅฟƒ่จ“็ทด๏ผŒๅฐˆๆณจๆ–ผๅ€ๅกŠ้ˆๆŠ€่ก“ใ€ๅŠ ๅฏ†่ฒจๅนฃใ€ๅˆ†ๆ•ฃๅผ้‡‘่ž็ญ‰็›ธ้—œไธป้กŒใ€‚ ๆ„Ÿ่ฌๆ‚จๅฐ็†Š็ถฒๅ€ๅกŠ้ˆAIๆจกๅž‹็š„้—œๆณจๅ’Œๆ”ฏๆŒ๏ผ Website: bearnetwork.net
{"language": ["zh", "en"], "license": "gpl-3.0", "datasets": ["BearNetworkChain/corpus"]}
BearNetworkChain/BRNKC-ForCausalLM
null
[ "transformers", "pytorch", "safetensors", "gpt2", "text-generation", "zh", "en", "dataset:BearNetworkChain/corpus", "license:gpl-3.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
null
2024-05-02T08:47:26+00:00
null
null
{}
iyubondyrev/token_completion_kotlin
null
[ "region:us" ]
null
2024-05-02T08:47:56+00:00
text-generation
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. --> # ChatGLM3-6B-Chat-DcardStylePost-SFT This model is a fine-tuned version of [THUDM/chatglm3-6b](https://huggingface.co/THUDM/chatglm3-6b) on the dcardwom_zhcn_train dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 2 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 8 - total_train_batch_size: 16 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - num_epochs: 3.0 - mixed_precision_training: Native AMP ### Training results ### Framework versions - PEFT 0.10.0 - Transformers 4.40.1 - Pytorch 2.2.0a0+81ea7a4 - Datasets 2.19.0 - Tokenizers 0.19.1
{"language": ["zh"], "license": "gpl-3.0", "library_name": "peft", "tags": ["art", "llama-factory", "lora", "generated_from_trainer"], "metrics": ["bleu"], "base_model": "THUDM/chatglm3-6b", "pipeline_tag": "text-generation", "model-index": [{"name": "train_2024-05-02-07-20-40", "results": []}]}
JiunYi/ChatGLM3-6B-Chat-DcardStylePost-SFT
null
[ "peft", "safetensors", "chatglm", "art", "llama-factory", "lora", "generated_from_trainer", "text-generation", "conversational", "custom_code", "zh", "base_model:THUDM/chatglm3-6b", "license:gpl-3.0", "region:us" ]
null
2024-05-02T08:48:54+00:00
text-generation
transformers
# Uploaded model - **Developed by:** henry-skywalker - **License:** apache-2.0 - **Finetuned from model :** unsloth/mistral-7b-instruct-v0.2-bnb-4bit This mistral model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
{"language": ["en"], "license": "apache-2.0", "tags": ["text-generation-inference", "transformers", "unsloth", "mistral", "trl", "sft"], "base_model": "unsloth/mistral-7b-instruct-v0.2-bnb-4bit"}
henry-skywalker/mistral_7b_search_4bit
null
[ "transformers", "safetensors", "mistral", "text-generation", "text-generation-inference", "unsloth", "trl", "sft", "conversational", "en", "base_model:unsloth/mistral-7b-instruct-v0.2-bnb-4bit", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "8-bit", "region:us" ]
null
2024-05-02T08:49:15+00:00
text-classification
transformers
{}
muzammil-eds/xlm-roberta-base-slovak-v3
null
[ "transformers", "pytorch", "xlm-roberta", "text-classification", "autotrain_compatible", "endpoints_compatible", "region:us" ]
null
2024-05-02T08:49:18+00:00
null
null
{"license": "openrail"}
KeroroK66/CrazyOllie
null
[ "license:openrail", "region:us" ]
null
2024-05-02T08:49:24+00:00
text-to-audio
transformers
{}
chunping-m/suno_bark
null
[ "transformers", "safetensors", "bark", "text-to-audio", "endpoints_compatible", "region:us" ]
null
2024-05-02T08:49:27+00:00
null
transformers
# Uploaded model - **Developed by:** CarlosFersoft - **License:** apache-2.0 - **Finetuned from model :** unsloth/llama-3-8b-Instruct-bnb-4bit This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
{"language": ["en"], "license": "apache-2.0", "tags": ["text-generation-inference", "transformers", "unsloth", "llama", "gguf"], "base_model": "unsloth/llama-3-8b-Instruct-bnb-4bit"}
CarlosFersoft/GPBusiness0001_Q4
null
[ "transformers", "gguf", "llama", "text-generation-inference", "unsloth", "en", "base_model:unsloth/llama-3-8b-Instruct-bnb-4bit", "license:apache-2.0", "endpoints_compatible", "region:us" ]
null
2024-05-02T08:49:49+00:00
null
null
{"license": "mit"}
mikerocchio21/ddpm-butterflies-128
null
[ "license:mit", "region:us" ]
null
2024-05-02T08:50:52+00:00
null
null
# FitSmart Fat Burner Reviews Indigents Official Website, Where To Buy UK FitSmart Fat Burner UK Reviews FitSmart Fat Burner helps you burn fat as well as improve your metabolism at the same time. One may also feel energized and uplifted after taking FitSmart Fat Burner pills. The FitSmart Fat Burner product, a combination of various natural ingredients including niacin (vitamin B3), raspberry fruit extract, green tea leaf extract, guarana seed extract and N-acetyl-L-carnitine, offers a versatile range of potential weight management benefits. ## **[Click Here To Buy Now From Official Website Of FitSmart Fat Burner](https://adtocart.xyz/fitsmart-uk)** ## FitSmart Fat Burner Benefits When it comes to products like FitSmart Fat Burner, real reviews (like this one) do more than regurgitate the company's marketing pitch. To further explain and evaluate the benefits that FitSmart Fat Burner claims it can bring, we turned to Pete Nastasi. As a certified weight loss practitioner and sports nutrition expert, Nastasi is qualified to provide a level of insight that many other FitSmart Fat Burner reviews don't have. Burns fat - "The primary fat burning ingredients in FitSmart Fat Burner are ฮฑ-Lacys Reset and Capsimax powder. Both provide the user with an intense thermogenic effect that helps to boost metabolic rate and stimulate the fat burning process," says Nastasi. "Thermogenesis is the conversion of an energy source into heat. In this case, the energy source is body fat in the form of brown adipose tissue (the type of fat that regulates your body temperature). These ingredients help mobilize excess fat and prioritize it as the main energy source for the body instead of carbohydrates." Reduces fat accumulation - "FitSmart Fat Burner states that the Capsimax powder in the formula may help to inhibit the body's ability to store fat cells and even stop new fat cells from growing altogether," says Nastasi. "This would theoretically help prevent additional weight gain when using the supplement, and is the reason some consumers decide to continue using the product even after they achieve their weight loss goals. FitSmart Fat Burner notes that this effect is accomplished without drastically changing one's current dietary habits." Reduces food cravings - "A caloric deficit is an essential component of the weight loss process," says Nastasi. "However, this deficit often results in an increased appetite and intense cravings for calorically dense foods. The combination of caffeine, chromium picolinate and nopal cactus in FitSmart Fat Burner are included to reduce these cravings, balance blood sugar levels and suppress the appetite through an increased feeling of fullness." Boosts energy - "Sticking to a strict weight loss regimen is more difficult when cutting calories leads to feelings of fatigue. This is especially true when dieters follow a weight loss program that limits carbs," says Nastasi. "This fatigue not only affects your mental health, but can also decrease the likelihood of going to the gym and exercising. FitSmart Fat Burner aims to resolve this issue through its blend of natural caffeine and Capsimax powder. These ingredients work together to burn extra body fat in order to naturally boost energy levels." Balances mood - "FitSmart Fat Burner includes the naturally occurring amino acid L-carnitine to provide cognitive support for those who struggle with daily mental fatigue," says Nastasi. "FitSmart Fat Burner states that this ingredient will help to keep you feeling motivated and positive while shedding excess weight." ## What Are The FitSmart Fat Burner Ingredients? FitSmart Fat Burner weight loss pills only has natural ingredients that are clinically proven to be safe and cause no side effects. It has no chemicals or added preservatives and is free from caffeine. ## The FitSmart Fat Burner ingredients include: Kudzu - Kudzu is a climbing vein that has its origins in Southeast Asia, East Asia, and a few other Pacific islands. It is used as a cure for alcoholism, diabetes, heart disease, etc. Kudzu is a main ingredient in the FitSmart Fat Burner supplement that works to support healthy weight and improves lipase levels. Berberine Extract - Berberine extract is a yellow-colored chemical extracted from plants. It controls the insulin and hormones that manage the fat cells which ultimately helps in weight loss. It helps speed up metabolism and increase lipase production in the body. Wild Raspberry - The FitSmart Fat Burner ingredient, raspberry is a fruit rich in potassium and it improves heart functions and helps maintain normal blood pressure. As for weight loss, it works wonders in balancing weight and being healthy. It eliminates the storage of unwanted fat in the body. Raw Wildflower Honey - It is natural unprocessed and raw honey that works great for the throat, gut, and skin health. It has anti-inflammatory properties and acts as an antidote for burns. It is packed with antioxidants that help in proper digestion. ## **[Click Here To Buy Now From Official Website Of FitSmart Fat Burner](https://adtocart.xyz/fitsmart-uk)**
{}
VKapseln475/FitSmartFatBurner232
null
[ "region:us" ]
null
2024-05-02T08:51:39+00:00
text-generation
null
# Trisert/Phi-3-mini-128k-instruct-Q8_0-GGUF This model was converted to GGUF format from [`microsoft/Phi-3-mini-128k-instruct`](https://huggingface.co/microsoft/Phi-3-mini-128k-instruct) 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/microsoft/Phi-3-mini-128k-instruct) for more details on the model. ## Use with llama.cpp Install llama.cpp through brew. ```bash brew install ggerganov/ggerganov/llama.cpp ``` Invoke the llama.cpp server or the CLI. CLI: ```bash llama-cli --hf-repo Trisert/Phi-3-mini-128k-instruct-Q8_0-GGUF --model phi-3-mini-128k-instruct.Q8_0.gguf -p "The meaning to life and the universe is" ``` Server: ```bash llama-server --hf-repo Trisert/Phi-3-mini-128k-instruct-Q8_0-GGUF --model phi-3-mini-128k-instruct.Q8_0.gguf -c 2048 ``` Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well. ``` git clone https://github.com/ggerganov/llama.cpp && cd llama.cpp && make && ./main -m phi-3-mini-128k-instruct.Q8_0.gguf -n 128 ```
{"language": ["en"], "license": "mit", "tags": ["nlp", "code", "llama-cpp", "gguf-my-repo"], "license_link": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct/resolve/main/LICENSE", "pipeline_tag": "text-generation", "widget": [{"messages": [{"role": "user", "content": "Can you provide ways to eat combinations of bananas and dragonfruits?"}]}]}
Trisert/Phi-3-mini-128k-instruct-Q8_0-GGUF
null
[ "gguf", "nlp", "code", "llama-cpp", "gguf-my-repo", "text-generation", "en", "license:mit", "region:us" ]
null
2024-05-02T08:52:07+00:00
null
null
{}
RayhaanK/Models
null
[ "region:us" ]
null
2024-05-02T08:52:18+00:00
null
null
Quantization made by Richard Erkhov. [Github](https://github.com/RichardErkhov) [Discord](https://discord.gg/pvy7H8DZMG) [Request more models](https://github.com/RichardErkhov/quant_request) new_01m - GGUF - Model creator: https://huggingface.co/lgodwangl/ - Original model: https://huggingface.co/lgodwangl/new_01m/ | Name | Quant method | Size | | ---- | ---- | ---- | | [new_01m.Q2_K.gguf](https://huggingface.co/RichardErkhov/lgodwangl_-_new_01m-gguf/blob/main/new_01m.Q2_K.gguf) | Q2_K | 2.53GB | | [new_01m.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/lgodwangl_-_new_01m-gguf/blob/main/new_01m.IQ3_XS.gguf) | IQ3_XS | 2.81GB | | [new_01m.IQ3_S.gguf](https://huggingface.co/RichardErkhov/lgodwangl_-_new_01m-gguf/blob/main/new_01m.IQ3_S.gguf) | IQ3_S | 2.96GB | | [new_01m.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/lgodwangl_-_new_01m-gguf/blob/main/new_01m.Q3_K_S.gguf) | Q3_K_S | 2.95GB | | [new_01m.IQ3_M.gguf](https://huggingface.co/RichardErkhov/lgodwangl_-_new_01m-gguf/blob/main/new_01m.IQ3_M.gguf) | IQ3_M | 3.06GB | | [new_01m.Q3_K.gguf](https://huggingface.co/RichardErkhov/lgodwangl_-_new_01m-gguf/blob/main/new_01m.Q3_K.gguf) | Q3_K | 3.28GB | | [new_01m.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/lgodwangl_-_new_01m-gguf/blob/main/new_01m.Q3_K_M.gguf) | Q3_K_M | 3.28GB | | [new_01m.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/lgodwangl_-_new_01m-gguf/blob/main/new_01m.Q3_K_L.gguf) | Q3_K_L | 3.56GB | | [new_01m.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/lgodwangl_-_new_01m-gguf/blob/main/new_01m.IQ4_XS.gguf) | IQ4_XS | 3.67GB | | [new_01m.Q4_0.gguf](https://huggingface.co/RichardErkhov/lgodwangl_-_new_01m-gguf/blob/main/new_01m.Q4_0.gguf) | Q4_0 | 3.83GB | | [new_01m.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/lgodwangl_-_new_01m-gguf/blob/main/new_01m.IQ4_NL.gguf) | IQ4_NL | 3.87GB | | [new_01m.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/lgodwangl_-_new_01m-gguf/blob/main/new_01m.Q4_K_S.gguf) | Q4_K_S | 3.86GB | | [new_01m.Q4_K.gguf](https://huggingface.co/RichardErkhov/lgodwangl_-_new_01m-gguf/blob/main/new_01m.Q4_K.gguf) | Q4_K | 4.07GB | | [new_01m.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/lgodwangl_-_new_01m-gguf/blob/main/new_01m.Q4_K_M.gguf) | Q4_K_M | 4.07GB | | [new_01m.Q4_1.gguf](https://huggingface.co/RichardErkhov/lgodwangl_-_new_01m-gguf/blob/main/new_01m.Q4_1.gguf) | Q4_1 | 4.24GB | | [new_01m.Q5_0.gguf](https://huggingface.co/RichardErkhov/lgodwangl_-_new_01m-gguf/blob/main/new_01m.Q5_0.gguf) | Q5_0 | 4.65GB | | [new_01m.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/lgodwangl_-_new_01m-gguf/blob/main/new_01m.Q5_K_S.gguf) | Q5_K_S | 4.65GB | | [new_01m.Q5_K.gguf](https://huggingface.co/RichardErkhov/lgodwangl_-_new_01m-gguf/blob/main/new_01m.Q5_K.gguf) | Q5_K | 4.78GB | | [new_01m.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/lgodwangl_-_new_01m-gguf/blob/main/new_01m.Q5_K_M.gguf) | Q5_K_M | 4.78GB | | [new_01m.Q5_1.gguf](https://huggingface.co/RichardErkhov/lgodwangl_-_new_01m-gguf/blob/main/new_01m.Q5_1.gguf) | Q5_1 | 5.07GB | | [new_01m.Q6_K.gguf](https://huggingface.co/RichardErkhov/lgodwangl_-_new_01m-gguf/blob/main/new_01m.Q6_K.gguf) | Q6_K | 5.53GB | Original model description: --- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a ๐Ÿค— transformers model that has been pushed on the Hub. This model card has been automatically generated. - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
{}
RichardErkhov/lgodwangl_-_new_01m-gguf
null
[ "gguf", "arxiv:1910.09700", "region:us" ]
null
2024-05-02T08:52:23+00:00
null
null
This model will help in identifying if it is a lung ct scan or a brain ct scan
{"language": ["en"]}
RayhaanK/lung_or_brain
null
[ "en", "region:us" ]
null
2024-05-02T08:52:36+00:00
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 ๐Ÿค— 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": []}
Seemaant/gpt2-reuters-tokenizer
null
[ "transformers", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]
null
2024-05-02T08:52:41+00:00
null
null
{}
PineCone85/test-model
null
[ "region:us" ]
null
2024-05-02T08:52:46+00:00
text-generation
transformers
Quantization made by Richard Erkhov. [Github](https://github.com/RichardErkhov) [Discord](https://discord.gg/pvy7H8DZMG) [Request more models](https://github.com/RichardErkhov/quant_request) EEVE-Korean-10.8B-v1.0 - bnb 4bits - Model creator: https://huggingface.co/yanolja/ - Original model: https://huggingface.co/yanolja/EEVE-Korean-10.8B-v1.0/ Original model description: --- license: apache-2.0 base_model: upstage/SOLAR-10.7B-v1.0 tags: - generated_from_trainer model-index: - name: yanolja/EEVE-Korean-10.8B-v1.0 results: [] --- [<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl) <p align="left"> <img src="https://huggingface.co/yanolja/EEVE-Korean-10.8B-v1.0/resolve/main/eeve_logo.webp" width="50%"/> <p> # EEVE-Korean-10.8B-v1.0 ## Join Our Community on Discord! If you're passionate about the field of Large Language Models and wish to exchange knowledge and insights, we warmly invite you to join our Discord server. It's worth noting that Korean is the primary language used in this server. The landscape of LLM is evolving rapidly, and without active sharing, our collective knowledge risks becoming outdated swiftly. Let's collaborate and drive greater impact together! Join us here: [Discord Link](https://discord.gg/b27bAHg95m). ## Our Dedicated Team (Alphabetical Order) | Research | Engineering | Product Management | UX Design | |-----------------|-----------------|--------------------|-------------- | Myeongho Jeong | Geon Kim | Bokyung Huh | Eunsue Choi | | Seungduk Kim | Rifqi Alfi | | | | Seungtaek Choi | Sanghoon Han | | | | | Suhyun Kang | | | ## About the Model This model is a Korean vocabulary-extended version of [upstage/SOLAR-10.7B-v1.0](https://huggingface.co/upstage/SOLAR-10.7B-v1.0), specifically fine-tuned on various Korean web-crawled datasets available on HuggingFace. Our approach was to expand the model's understanding of Korean by pre-training the embeddings for new tokens and partially fine-tuning the `lm_head` embeddings for the already existing tokens while preserving the original parameters of the base model. ### Technical Deep Dive <p align="left"> <img src="https://huggingface.co/yanolja/EEVE-Korean-10.8B-v1.0/resolve/main/EEVE_figure.png" width="100%"/> <p> To adapt foundational models from English to Korean, we use subword-based embedding with a seven-stage training process involving parameter freezing. This approach progressively trains from input embeddings to full parameters, efficiently extending the model's vocabulary to include Korean. Our method enhances the model's cross-linguistic applicability by carefully integrating new linguistic tokens, focusing on causal language modeling pre-training. We leverage the inherent capabilities of foundational models trained on English to efficiently transfer knowledge and reasoning to Korean, optimizing the adaptation process. For more details, please refer to our technical report: [Efficient and Effective Vocabulary Expansion Towards Multilingual Large Language Models](https://arxiv.org/abs/2402.14714). Hereโ€™s an simplified code for our key approach: ```python # number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000. def freeze_partial_embedding_hook(grad): grad[:number_of_old_tokens] = 0 return grad for name, param in model.named_parameters(): if ("lm_head" in name or "embed_tokens" in name) and "original" not in name: param.requires_grad = True if "embed_tokens" in name: param.register_hook(freeze_partial_embedding_hook) else: param.requires_grad = False ``` ### Usage and Limitations Keep in mind that this model hasn't been fine-tuned with instruction-based training. While it excels in Korean language tasks, we advise careful consideration and further training for specific applications. ### Training Details Our modelโ€™s training was comprehensive and diverse: - **Vocabulary Expansion:** We meticulously selected 8,960 Korean tokens based on their frequency in our Korean web corpus. This process involved multiple rounds of tokenizer training, manual curation, and token frequency analysis, ensuring a rich and relevant vocabulary for our model. 1. **Initial Tokenizer Training:** We trained an intermediate tokenizer on a Korean web corpus, with a vocabulary of 40,000 tokens. 2. **Extraction of New Korean Tokens:** From the intermediate tokenizer, we identified all Korean tokens not present in the original SOLAR's tokenizer. 3. **Manual Tokenizer Construction:** We then built the target tokenizer, focusing on these new Korean tokens. 4. **Frequency Analysis:** Using the target tokenizer, we processed a 100GB Korean corpus to count each token's frequency. 5. **Refinement of Token List:** We removed tokens appearing less than 6,000 times, ensuring to secure enough tokens to train models later. 6. **Inclusion of Single-Letter Characters:** Counted missing Korean single-letter characters and added them to the target tokenizer that appeared more than 6,000 times. 7. **Iterative Refinement:** We repeated steps 2 to 6 until there were no tokens to drop or add. 8. **Training Bias Towards New Tokens:** Our training data was biased to include more texts with new tokens, for effective learning. This rigorous approach ensured a comprehensive and contextually rich Korean vocabulary for the model. ## Citation ``` @misc{kim2024efficient, title={Efficient and Effective Vocabulary Expansion Towards Multilingual Large Language Models}, author={Seungduk Kim and Seungtaek Choi and Myeongho Jeong}, year={2024}, eprint={2402.14714}, archivePrefix={arXiv}, primaryClass={cs.CL} } ```
{}
RichardErkhov/yanolja_-_EEVE-Korean-10.8B-v1.0-4bits
null
[ "transformers", "safetensors", "llama", "text-generation", "conversational", "arxiv:2402.14714", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "4-bit", "region:us" ]
null
2024-05-02T08:53:18+00:00
text-classification
bertopic
# BERTopic-enron-5000 This is a [BERTopic](https://github.com/MaartenGr/BERTopic) model. BERTopic is a flexible and modular topic modeling framework that allows for the generation of easily interpretable topics from large datasets. ## Usage To use this model, please install BERTopic: ``` pip install -U bertopic ``` You can use the model as follows: ```python from bertopic import BERTopic topic_model = BERTopic.load("antulik/BERTopic-enron-5000") topic_model.get_topic_info() ``` ## Topic overview * Number of topics: 65 * Number of training documents: 5000 <details> <summary>Click here for an overview of all topics.</summary> | Topic ID | Topic Keywords | Topic Frequency | Label | |----------|----------------|-----------------|-------| | -1 | enron - corp - contract - company - trading | 10 | -1_enron_corp_contract_company | | 0 | going - meeting - meet - hope - night | 2299 | 0_going_meeting_meet_hope | | 1 | agreements - enron - agreement - contract - documents | 481 | 1_agreements_enron_agreement_contract | | 2 | enron - enrons - companies - company - market | 263 | 2_enron_enrons_companies_company | | 3 | enron - contact - corp - email - recipient | 253 | 3_enron_contact_corp_email | | 4 | telecom - ventures - financial - companies - markets | 84 | 4_telecom_ventures_financial_companies | | 5 | enron - email - recipient - recipients - message | 76 | 5_enron_email_recipient_recipients | | 6 | fares - newark - airlines - flight - miles | 58 | 6_fares_newark_airlines_flight | | 7 | nfl - commissionercom - td - sportslinecom - league | 54 | 7_nfl_commissionercom_td_sportslinecom | | 8 | enron - eov - ashleyworthingenroncom - erv - rho | 53 | 8_enron_eov_ashleyworthingenroncom_erv | | 9 | enron - enrons - bankruptcy - bankrupt - savings | 51 | 9_enron_enrons_bankruptcy_bankrupt | | 10 | outlookmigrationteamenroncom - outlook - outlookteamenroncom - emailcalendar - appointment | 46 | 10_outlookmigrationteamenroncom_outlook_outlookteamenroncom_emailcalendar | | 11 | enron - approver - approval - pending - econnect | 46 | 11_enron_approver_approval_pending | | 12 | schedules2002013118txt - schedules2002020115txt - schedules2002012506txt - schedules2001122507txt - schedules2001122815txt | 45 | 12_schedules2002013118txt_schedules2002020115txt_schedules2002012506txt_schedules2001122507txt | | 13 | pricing - lpg - logistics - freight - metered | 44 | 13_pricing_lpg_logistics_freight | | 14 | request - seeks - up - on - all | 43 | 14_request_seeks_up_on | | 15 | haas - semester - summers - faculty - mba | 43 | 15_haas_semester_summers_faculty | | 16 | federal - california - sacramento - californias - states | 42 | 16_federal_california_sacramento_californias | | 17 | enron - resumes - resume - interview - recruiter | 41 | 17_enron_resumes_resume_interview | | 18 | fontstyle - font - html - bold - sansserif | 39 | 18_fontstyle_font_html_bold | | 19 | enron - deals - trades - deal - tradesxls | 37 | 19_enron_deals_trades_deal | | 20 | pipeline - pipelines - piping - paso - pipe | 36 | 20_pipeline_pipelines_piping_paso | | 21 | enron - eb - contact - mailtobobshultsenroncom - emailed | 36 | 21_enron_eb_contact_mailtobobshultsenroncom | | 22 | outage - outagesindustrialinfocom - outages - rescheduled - scheduled | 36 | 22_outage_outagesindustrialinfocom_outages_rescheduled | | 23 | gifts - gift - holiday - holidays - christmas | 36 | 23_gifts_gift_holiday_holidays | | 24 | nymex - futures - expiration - contract - contracts | 31 | 24_nymex_futures_expiration_contract | | 25 | transmission - transco - translink - ferc - rtos | 30 | 25_transmission_transco_translink_ferc | | 26 | unsubscribe - email - newsletter - mailing - mailmanenroncom | 30 | 26_unsubscribe_email_newsletter_mailing | | 27 | invoices - invoice - enron - billed - reimbursement | 29 | 27_invoices_invoice_enron_billed | | 28 | enron - committee - lobbyist - judiciary - bill | 28 | 28_enron_committee_lobbyist_judiciary | | 29 | refinery - prices - pipeline - oil - price | 27 | 29_refinery_prices_pipeline_oil | | 30 | enron - gas - fuel - logistics - emissions | 27 | 30_enron_gas_fuel_logistics | | 31 | enron - dpc - topockpcb - ebizenroncom - pcb | 24 | 31_enron_dpc_topockpcb_ebizenroncom | | 32 | nyisotechexchange - nyisotechexchangeglobal2000net - marketrelationsnyisocom - nyiso - ownernyisotechexchangeliststhebiznet | 24 | 32_nyisotechexchange_nyisotechexchangeglobal2000net_marketrelationsnyisocom_nyiso | | 33 | expense - expenses - enron - enronupdateconcureworkplacecom - receipts | 24 | 33_expense_expenses_enron_enronupdateconcureworkplacecom | | 34 | enron - ebusiness - inquiries - advisory - contact | 23 | 34_enron_ebusiness_inquiries_advisory | | 35 | dbcaps97data - schedules2002011801txt - schedules2002011805txt - schedules2001102112txt - schedules2002011916txt | 21 | 35_dbcaps97data_schedules2002011801txt_schedules2002011805txt_schedules2001102112txt | | 36 | enrononline - trades - trading - deals - eol | 20 | 36_enrononline_trades_trading_deals | | 37 | enron - swaps - swap - exchange - exchanges | 20 | 37_enron_swaps_swap_exchange | | 38 | feedback - reviewers - review - process - reviewer | 20 | 38_feedback_reviewers_review_process | | 39 | powermarketerscom - electricity - energy - utilities - reuters | 20 | 39_powermarketerscom_electricity_energy_utilities | | 40 | tco - columbias - columbia - scheduled - cgt | 19 | 40_tco_columbias_columbia_scheduled | | 41 | curves - curve - data - changes - inactive | 19 | 41_curves_curve_data_changes | | 42 | enron - scheduled - eb3335 - rustybelflowerenroncom - brianredmondenroncom | 19 | 42_enron_scheduled_eb3335_rustybelflowerenroncom | | 43 | enron - executive - ceo - communicationsenron - director | 18 | 43_enron_executive_ceo_communicationsenron | | 44 | alert - alerts - ipo - stock - securities | 17 | 44_alert_alerts_ipo_stock | | 45 | invoice - ipayitenroncom - sapsecurityenroncom - ipayit - ehronline | 17 | 45_invoice_ipayitenroncom_sapsecurityenroncom_ipayit | | 46 | variances - variance - schedules - schedule - schedulingiso | 17 | 46_variances_variance_schedules_schedule | | 47 | futures - charts - carr - financial - 1500 | 17 | 47_futures_charts_carr_financial | | 48 | approval - approved - authorized - eisb - tariff | 16 | 48_approval_approved_authorized_eisb | | 49 | fee - credit - express - membership - merchant | 15 | 49_fee_credit_express_membership | | 50 | fee - subscription - billing - discount - monthly | 15 | 50_fee_subscription_billing_discount | | 51 | schedules2001102810txt - schedules2001123103txt - schedules2001030406txt - schedules2002010121txt - schedules2001043008txt | 14 | 51_schedules2001102810txt_schedules2001123103txt_schedules2001030406txt_schedules2002010121txt | | 52 | managementcrd - gd - ets - gasdeskenroncom - sst | 14 | 52_managementcrd_gd_ets_gasdeskenroncom | | 53 | shipping - shipment - order - orders - delivery | 14 | 53_shipping_shipment_order_orders | | 54 | dish - satellite - free - channels - dvds | 14 | 54_dish_satellite_free_channels | | 55 | mailbox - outlook - inbox - exchangeadministratorenroncom - folder | 13 | 55_mailbox_outlook_inbox_exchangeadministratorenroncom | | 56 | netware - visualwares - backoffice - newsletter - file | 13 | 56_netware_visualwares_backoffice_newsletter | | 57 | enronfcucom - survey - enronannouncementsenroncom - ews - service | 13 | 57_enronfcucom_survey_enronannouncementsenroncom_ews | | 58 | pira - forecast - piras - demand - weekly | 12 | 58_pira_forecast_piras_demand | | 59 | pricing - enron - cost - rate - price | 12 | 59_pricing_enron_cost_rate | | 60 | whitening - medication - strength - clinical - doctor | 11 | 60_whitening_medication_strength_clinical | | 61 | enron - industries - ebusiness - industrial - ena | 11 | 61_enron_industries_ebusiness_industrial | | 62 | px - credit - pe - sce - tariff | 10 | 62_px_credit_pe_sce | | 63 | enron - eesi - eemc - assets - nepco | 10 | 63_enron_eesi_eemc_assets | </details> ## Training hyperparameters * calculate_probabilities: False * language: english * low_memory: False * min_topic_size: 10 * n_gram_range: (1, 1) * nr_topics: None * seed_topic_list: [['drug', 'cancer', 'drugs', 'doctor'], ['windows', 'drive', 'dos', 'file'], ['space', 'launch', 'orbit', 'lunar']] * top_n_words: 10 * verbose: False * zeroshot_min_similarity: 0.7 * zeroshot_topic_list: None ## Framework versions * Numpy: 1.23.5 * HDBSCAN: 0.8.33 * UMAP: 0.5.6 * Pandas: 2.0.3 * Scikit-Learn: 1.2.2 * Sentence-transformers: 2.7.0 * Transformers: 4.40.1 * Numba: 0.58.1 * Plotly: 5.15.0 * Python: 3.10.12
{"library_name": "bertopic", "tags": ["bertopic"], "pipeline_tag": "text-classification"}
antulik/BERTopic-enron-5000
null
[ "bertopic", "text-classification", "region:us" ]
null
2024-05-02T08:53:56+00:00
null
null
{}
matthijspva/segformer-b0-finetuned-segments-sidewalk
null
[ "region:us" ]
null
2024-05-02T08:53:57+00:00
text-classification
transformers
[**GitHub Homepage**](https://github.com/wonrax/phobert-base-vietnamese-sentiment) A model fine-tuned for sentiment analysis based on [vinai/phobert-base](https://huggingface.co/vinai/phobert-base). Labels: - NEG: Negative - POS: Positive - NEU: Neutral Dataset: [30K e-commerce reviews](https://www.kaggle.com/datasets/linhlpv/vietnamese-sentiment-analyst) ## Usage ```python import torch from transformers import RobertaForSequenceClassification, AutoTokenizer model = RobertaForSequenceClassification.from_pretrained("wonrax/phobert-base-vietnamese-sentiment") tokenizer = AutoTokenizer.from_pretrained("wonrax/phobert-base-vietnamese-sentiment", use_fast=False) # Just like PhoBERT: INPUT TEXT MUST BE ALREADY WORD-SEGMENTED! sentence = 'ฤรขy lร  mรด_hรฌnh rแบฅt hay , phรน_hแปฃp vแป›i ฤ‘iแปu_kiแป‡n vร  nhฦฐ cแบงu cแปงa nhiแปu ngฦฐแปi .' input_ids = torch.tensor([tokenizer.encode(sentence)]) with torch.no_grad(): out = model(input_ids) print(out.logits.softmax(dim=-1).tolist()) # Output: # [[0.002, 0.988, 0.01]] # ^ ^ ^ # NEG POS NEU ```
{"language": ["vi"], "license": "mit", "tags": ["sentiment", "classification"], "widget": [{"text": "Kh\u00f4ng th\u1ec3 n\u00e0o \u0111\u1eb9p h\u01a1n"}, {"text": "Qu\u00e1 ph\u00ed ti\u1ec1n, m\u00e0 kh\u00f4ng \u0111\u1eb9p"}, {"text": "C\u00e1i n\u00e0y gi\u00e1 \u1ed5n kh\u00f4ng nh\u1ec9?"}]}
Angelectronic/phobert-base-vietnamese-sentiment
null
[ "transformers", "pytorch", "roberta", "text-classification", "sentiment", "classification", "vi", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]
null
2024-05-02T08:54:32+00:00
text-generation
transformers
{"license": "llama2"}
emrecanacikgoz/hamza-small
null
[ "transformers", "safetensors", "gpt2", "text-generation", "license:llama2", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
null
2024-05-02T08:54:47+00:00
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 ๐Ÿค— 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": []}
RefalMachine/ruadapt_llama3_full_vo_3e4_bs256-40k
null
[ "transformers", "safetensors", "llama", "text-generation", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
null
2024-05-02T08:54:48+00:00
text-generation
transformers
![example](https://files.catbox.moe/joazop.png) The idea is the same as [InfinityRP v1](https://huggingface.co/Endevor/InfinityRP-v1-7B), but this one is Llama 3 with 16k ctx! Have fun... ### Prompt format: Alpaca. ``"You are now in roleplay chat mode. Engage in an endless chat, always with a creative response. Follow lengths very precisely and create paragraphs accurately. Always wait your turn, next actions and responses. Your internal thoughts are wrapped with ` marks."`` **User Message Prefix = ### Input:** **Assistant Message Prefix = ### Response:** **System Message Prefix = ### Instruction:** **Turn on "Include Names"** (optional) ### Text Length: (use on your System Prompt or ### Response:) Response: (length = medium) <- [tiny, micro, short, medium, long, enormous, huge, massive, humongous] ### Example: ![example](https://files.catbox.moe/t3hcez.png)
{"language": ["en"], "license": "apache-2.0", "tags": ["safetensors", "llama", "not-for-all-audiences", "nsfw", "rp", "roleplay"], "pipeline_tag": "text-generation"}
Endevor/InfinityRP-v2-8B
null
[ "transformers", "safetensors", "llama", "text-generation", "not-for-all-audiences", "nsfw", "rp", "roleplay", "en", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
null
2024-05-02T08:55:30+00:00
text-generation
transformers
# Model Card for Cyber-risk-llama-3-8b-instruct-sft ## Model Description This model is a fine-tuned version of `meta-llama/Meta-Llama-3-8B-Instruct` on the `vanessasml/cybersecurity_32k_instruction_input_output` dataset. It is specifically designed to enhance performance in generating and understanding cybersecurity, identifying cyber threats and classifying data under the NIST taxonomy and IT Risks based on the ITC EBA guidelines. ## Intended Use - **Intended users**: Data scientists and developers working on cybersecurity applications. - **Out-of-scope use cases**: This model should not be used for medical advice, legal decisions, or any life-critical systems. ## Training Data The model was fine-tuned on `vanessasml/cybersecurity_32k_instruction_input_output`, a dataset focused on cybersecurity news analysis. No special data format was applied as [recommended](https://huggingface.co/blog/llama3#fine-tuning-with-%F0%9F%A4%97-trl), although the following steps need to be applied to adjust the input: ```python # During training from trl import setup_chat_format model, tokenizer = setup_chat_format(model, tokenizer) # During inference messages = [ {"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"}, {"role": "user", "content": "Who are you?"}, ] prompt = pipeline.tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True ) ``` ## Training Procedure - **Preprocessing**: Text data were tokenized using the tokenizer corresponding to the base model `meta-llama/Meta-Llama-3-8B-Instruct`. - **Hardware**: The training was performed on GPUs with mixed precision (FP16/BF16) enabled. - **Optimizer**: Paged AdamW with a cosine learning rate schedule. - **Epochs**: The model was trained for 1 epoch. - **Batch size**: 4 per device, with gradient accumulation where required. ## Evaluation Results Model evaluation was based on qualitative assessment of generated text relevance and coherence in the context of cybersecurity. ## Quantization and Optimization - **Quantization**: 4-bit precision with type `nf4`. Nested quantization is disabled. - **Compute dtype**: `float16` to ensure efficient computation. - **LoRA Settings**: - LoRA attention dimension: `64` - Alpha parameter for LoRA scaling: `16` - Dropout in LoRA layers: `0.1` ## Environmental Impact - **Compute Resources**: Training leveraged energy-efficient hardware and practices to minimize carbon footprint. - **Strategies**: Gradient checkpointing and group-wise data processing were used to optimize memory and power usage. ## How to Use Here is how to load and use the model using transformers: ```python import transformers model_name = "vanessasml/cyber-risk-llama-3-8b-instruct-sft" # Example of how to use the model: pipeline = transformers.pipeline( "text-generation", model=model_name, model_kwargs={"torch_dtype": torch.bfloat16}, device="cuda", ) messages = [ {"role": "system", "content": SYSTEM_PROMPT}, {"role": "user", "content": "What are the main 5 cyber classes from the NIST cyber framework?"}, ] prompt = pipeline.tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True ) terminators = [ pipeline.tokenizer.eos_token_id, pipeline.tokenizer.convert_tokens_to_ids("<|eot_id|>") ] outputs = pipeline( prompt, max_new_tokens=256, eos_token_id=terminators, do_sample=True, temperature=0.6, top_p=0.9, ) print(outputs[0]["generated_text"][len(prompt):]) ``` ## Limitations and Bias The model, while robust in cybersecurity contexts, may not generalize well to unrelated domains. Users should be cautious of biases inherent in the training data which may manifest in model predictions. ## Citation If you use this model, please cite it as follows: ```bibtex @misc{cyber-risk-llama-3-8b-instruct-sft, author = {Vanessa Lopes}, title = {Cyber-risk-llama-3-8B-Instruct-sft Model}, year = {2024}, publisher = {HuggingFace Hub}, journal = {HuggingFace Model Hub} } ```
{"tags": ["finance", "supervision", "cyber risk", "cybersecurity", "cyber threats", "SFT", "LoRA", "A100GPU"], "datasets": ["Vanessasml/cybersecurity_32k_instruction_input_output"], "pipeline_tag": "text-generation"}
Vanessasml/cyber-risk-llama-3-8b-instruct-sft
null
[ "transformers", "safetensors", "llama", "text-generation", "finance", "supervision", "cyber risk", "cybersecurity", "cyber threats", "SFT", "LoRA", "A100GPU", "conversational", "dataset:Vanessasml/cybersecurity_32k_instruction_input_output", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
null
2024-05-02T08:55:35+00:00
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 ๐Ÿค— 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": []}
Vamshi7981/gpt2-reuters-tokenizer
null
[ "transformers", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]
null
2024-05-02T08:55:40+00:00
null
null
{"license": "llama2"}
emrecanacikgoz/hamza-medium
null
[ "license:llama2", "region:us" ]
null
2024-05-02T08:55:44+00:00
text-generation
transformers
Quantization made by Richard Erkhov. [Github](https://github.com/RichardErkhov) [Discord](https://discord.gg/pvy7H8DZMG) [Request more models](https://github.com/RichardErkhov/quant_request) xlm-roberta-large-squad2 - bnb 4bits - Model creator: https://huggingface.co/deepset/ - Original model: https://huggingface.co/deepset/xlm-roberta-large-squad2/ Original model description: --- language: multilingual license: cc-by-4.0 tags: - question-answering datasets: - squad_v2 model-index: - name: deepset/xlm-roberta-large-squad2 results: - task: type: question-answering name: Question Answering dataset: name: squad_v2 type: squad_v2 config: squad_v2 split: validation metrics: - type: exact_match value: 81.8281 name: Exact Match verified: true verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNzVhZDE2NTg5NmUwOWRkMmI2MGUxYjFlZjIzNmMyNDQ2MDY2MDNhYzE0ZjY5YTkyY2U4ODc3ODFiZjQxZWQ2YSIsInZlcnNpb24iOjF9.f_rN3WPMAdv-OBPz0T7N7lOxYz9f1nEr_P-vwKhi3jNdRKp_JTy18MYR9eyJM2riKHC6_ge-8XwfyrUf51DSDA - type: f1 value: 84.8886 name: F1 verified: true verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZGE5MWJmZGUxMGMwNWFhYzVhZjQwZGEwOWQ4N2Q2Yjg5NzdjNDFiNDhiYTQ1Y2E5ZWJkOTFhYmI1Y2Q2ZGYwOCIsInZlcnNpb24iOjF9.TIdH-tOx3kEMDs5wK1r6iwZqqSjNGlBrpawrsE917j1F3UFJVnQ7wJwaj0OIgmC4iw8OQeLZL56ucBcLApa-AQ --- # Multilingual XLM-RoBERTa large for QA on various languages ## Overview **Language model:** xlm-roberta-large **Language:** Multilingual **Downstream-task:** Extractive QA **Training data:** SQuAD 2.0 **Eval data:** SQuAD dev set - German MLQA - German XQuAD **Training run:** [MLFlow link](https://public-mlflow.deepset.ai/#/experiments/124/runs/3a540e3f3ecf4dd98eae8fc6d457ff20) **Infrastructure**: 4x Tesla v100 ## Hyperparameters ``` batch_size = 32 n_epochs = 3 base_LM_model = "xlm-roberta-large" max_seq_len = 256 learning_rate = 1e-5 lr_schedule = LinearWarmup warmup_proportion = 0.2 doc_stride=128 max_query_length=64 ``` ## Performance Evaluated on the SQuAD 2.0 English dev set with the [official eval script](https://worksheets.codalab.org/rest/bundles/0x6b567e1cf2e041ec80d7098f031c5c9e/contents/blob/). ``` "exact": 79.45759285774446, "f1": 83.79259828925511, "total": 11873, "HasAns_exact": 71.96356275303644, "HasAns_f1": 80.6460053117963, "HasAns_total": 5928, "NoAns_exact": 86.93019343986543, "NoAns_f1": 86.93019343986543, "NoAns_total": 5945 ``` Evaluated on German [MLQA: test-context-de-question-de.json](https://github.com/facebookresearch/MLQA) ``` "exact": 49.34691166703564, "f1": 66.15582561674236, "total": 4517, ``` Evaluated on German [XQuAD: xquad.de.json](https://github.com/deepmind/xquad) ``` "exact": 61.51260504201681, "f1": 78.80206098332569, "total": 1190, ``` ## Usage ### In Haystack For doing QA at scale (i.e. many docs instead of single paragraph), you can load the model also in [haystack](https://github.com/deepset-ai/haystack/): ```python reader = FARMReader(model_name_or_path="deepset/xlm-roberta-large-squad2") # or reader = TransformersReader(model="deepset/xlm-roberta-large-squad2",tokenizer="deepset/xlm-roberta-large-squad2") ``` ### In Transformers ```python from transformers import AutoModelForQuestionAnswering, AutoTokenizer, pipeline model_name = "deepset/xlm-roberta-large-squad2" # a) Get predictions nlp = pipeline('question-answering', model=model_name, tokenizer=model_name) QA_input = { 'question': 'Why is model conversion important?', 'context': 'The option to convert models between FARM and transformers gives freedom to the user and let people easily switch between frameworks.' } res = nlp(QA_input) # b) Load model & tokenizer model = AutoModelForQuestionAnswering.from_pretrained(model_name) tokenizer = AutoTokenizer.from_pretrained(model_name) ``` ## Authors **Branden Chan:** [email protected] **Timo Mรถller:** [email protected] **Malte Pietsch:** [email protected] **Tanay Soni:** [email protected] ## About us <div class="grid lg:grid-cols-2 gap-x-4 gap-y-3"> <div class="w-full h-40 object-cover mb-2 rounded-lg flex items-center justify-center"> <img alt="" src="https://raw.githubusercontent.com/deepset-ai/.github/main/deepset-logo-colored.png" class="w-40"/> </div> <div class="w-full h-40 object-cover mb-2 rounded-lg flex items-center justify-center"> <img alt="" src="https://raw.githubusercontent.com/deepset-ai/.github/main/haystack-logo-colored.png" class="w-40"/> </div> </div> [deepset](http://deepset.ai/) is the company behind the open-source NLP framework [Haystack](https://haystack.deepset.ai/) which is designed to help you build production ready NLP systems that use: Question answering, summarization, ranking etc. Some of our other work: - [Distilled roberta-base-squad2 (aka "tinyroberta-squad2")]([https://huggingface.co/deepset/tinyroberta-squad2) - [German BERT (aka "bert-base-german-cased")](https://deepset.ai/german-bert) - [GermanQuAD and GermanDPR datasets and models (aka "gelectra-base-germanquad", "gbert-base-germandpr")](https://deepset.ai/germanquad) ## Get in touch and join the Haystack community <p>For more info on Haystack, visit our <strong><a href="https://github.com/deepset-ai/haystack">GitHub</a></strong> repo and <strong><a href="https://docs.haystack.deepset.ai">Documentation</a></strong>. We also have a <strong><a class="h-7" href="https://haystack.deepset.ai/community">Discord community open to everyone!</a></strong></p> [Twitter](https://twitter.com/deepset_ai) | [LinkedIn](https://www.linkedin.com/company/deepset-ai/) | [Discord](https://haystack.deepset.ai/community) | [GitHub Discussions](https://github.com/deepset-ai/haystack/discussions) | [Website](https://deepset.ai) By the way: [we're hiring!](http://www.deepset.ai/jobs)
{}
RichardErkhov/deepset_-_xlm-roberta-large-squad2-4bits
null
[ "transformers", "safetensors", "xlm-roberta", "text-generation", "autotrain_compatible", "endpoints_compatible", "4-bit", "region:us" ]
null
2024-05-02T08:55:51+00:00
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 ๐Ÿค— 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": []}
azhara001/donut-base-demo-new-1e-05_Adam_938
null
[ "transformers", "safetensors", "vision-encoder-decoder", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]
null
2024-05-02T08:55:53+00:00
text-generation
transformers
{"license": "llama2"}
emrecanacikgoz/hamza-large
null
[ "transformers", "safetensors", "gpt2", "text-generation", "license:llama2", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
null
2024-05-02T08:56:06+00:00
text-generation
transformers
{"license": "llama2"}
emrecanacikgoz/hamza-xl
null
[ "transformers", "safetensors", "gpt2", "text-generation", "license:llama2", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
null
2024-05-02T08:56:26+00:00
null
diffusers
More information on all the CLI arguments and the environment are available on your [`wandb` run page](https://wandb.ai/sayakpaul/diffusion-orpo-lora-sdxl/runs/9ef92pyq).
{}
sayakpaul/sdxl-orpo-large-beta_orpo-0.005-beta_inner-500-lr-5e-7-no-decay-steps-5000
null
[ "diffusers", "safetensors", "region:us" ]
null
2024-05-02T08:56:43+00:00
text2text-generation
transformers
{}
ronak17/T5-aggregation
null
[ "transformers", "pytorch", "t5", "text2text-generation", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
null
2024-05-02T08:57:27+00:00
null
peft
<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # gen-z-translate-llama-3-instruct-v1 This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the generator dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0002 - train_batch_size: 2 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 2 - total_train_batch_size: 4 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: constant - lr_scheduler_warmup_ratio: 0.03 - num_epochs: 10 - mixed_precision_training: Native AMP ### Training results ### Framework versions - PEFT 0.10.0 - Transformers 4.40.1 - Pytorch 2.2.1+cu121 - Datasets 2.19.0 - Tokenizers 0.19.1
{"license": "other", "library_name": "peft", "tags": ["trl", "sft", "generated_from_trainer"], "datasets": ["generator"], "base_model": "meta-llama/Meta-Llama-3-8B-Instruct", "model-index": [{"name": "gen-z-translate-llama-3-instruct-v1", "results": []}]}
andrev/gen-z-translate-llama-3-instruct-v1
null
[ "peft", "tensorboard", "safetensors", "trl", "sft", "generated_from_trainer", "dataset:generator", "base_model:meta-llama/Meta-Llama-3-8B-Instruct", "license:other", "region:us" ]
null
2024-05-02T08:57:37+00:00
null
diffusers
More information on all the CLI arguments and the environment are available on your [`wandb` run page](https://wandb.ai/sayakpaul/diffusion-orpo-lora-sdxl/runs/tys9nxxj).
{}
sayakpaul/sdxl-orpo-large-beta_orpo-0.005-beta_inner-500-lr-5e-7-scaled-steps-5000
null
[ "diffusers", "safetensors", "region:us" ]
null
2024-05-02T08:57:46+00:00
token-classification
transformers
<!-- This model card has been generated automatically according to the information Keras had access to. You should probably proofread and complete it, then remove this comment. --> # khadija69/roberta-finetuned-ner-bio_test This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on an unknown dataset. It achieves the following results on the evaluation set: - Train Loss: 0.1632 - Validation Loss: 0.2486 - Epoch: 2 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 3480, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01} - training_precision: float32 ### Training results | Train Loss | Validation Loss | Epoch | |:----------:|:---------------:|:-----:| | 0.3753 | 0.2708 | 0 | | 0.1951 | 0.2432 | 1 | | 0.1632 | 0.2486 | 2 | ### Framework versions - Transformers 4.40.1 - TensorFlow 2.15.0 - Datasets 2.19.0 - Tokenizers 0.19.1
{"license": "mit", "tags": ["generated_from_keras_callback"], "base_model": "xlm-roberta-base", "model-index": [{"name": "khadija69/roberta-finetuned-ner-bio_test", "results": []}]}
khadija69/roberta-finetuned-ner-bio_test
null
[ "transformers", "tf", "xlm-roberta", "token-classification", "generated_from_keras_callback", "base_model:xlm-roberta-base", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]
null
2024-05-02T08:58:11+00:00
null
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. --> # PolizzeDonut-Incongruenza3di7-5Epochs This model is a fine-tuned version of [tedad09/PolizzeDonut-ChangeRequest-imm5epochs-Expand0](https://huggingface.co/tedad09/PolizzeDonut-ChangeRequest-imm5epochs-Expand0) on the imagefolder dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 2 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 5 - mixed_precision_training: Native AMP ### Training results ### Framework versions - Transformers 4.38.2 - Pytorch 2.2.2+cu121 - Datasets 2.18.0 - Tokenizers 0.15.2
{"license": "mit", "tags": ["generated_from_trainer"], "datasets": ["imagefolder"], "base_model": "tedad09/PolizzeDonut-ChangeRequest-imm5epochs-Expand0", "model-index": [{"name": "PolizzeDonut-Incongruenza3di7-5Epochs", "results": []}]}
tedad09/PolizzeDonut-Incongruenza3di7-5Epochs
null
[ "transformers", "tensorboard", "safetensors", "vision-encoder-decoder", "generated_from_trainer", "dataset:imagefolder", "base_model:tedad09/PolizzeDonut-ChangeRequest-imm5epochs-Expand0", "license:mit", "endpoints_compatible", "region:us" ]
null
2024-05-02T08:58:36+00:00
text-generation
transformers
{}
TwinDoc/H100_stage1_checkpoint-30240
null
[ "transformers", "safetensors", "llama", "text-generation", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
null
2024-05-02T08:59:02+00:00
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 ๐Ÿค— 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": []}
aritrosakar/gpt2-reuters-tokenizer
null
[ "transformers", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]
null
2024-05-02T08:59:15+00:00
null
null
{}
GraydientPlatformAPI/hands3-xl
null
[ "region:us" ]
null
2024-05-02T08:59:18+00:00
null
null
{"license": "llama2"}
emrecanacikgoz/hamza-mistral
null
[ "license:llama2", "region:us" ]
null
2024-05-02T08:59:22+00:00
text-generation
transformers
# jp-stablelm-3b-4belt-prune2 jp-stablelm-3b-4belt-prune2 is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing): * [stabilityai/japanese-stablelm-3b-4e1t-instruct](https://huggingface.co/stabilityai/japanese-stablelm-3b-4e1t-instruct) * [stabilityai/japanese-stablelm-3b-4e1t-instruct](https://huggingface.co/stabilityai/japanese-stablelm-3b-4e1t-instruct) ## ๐Ÿงฉ Configuration ```yaml slices: - sources: - model: stabilityai/japanese-stablelm-3b-4e1t-instruct layer_range: [0, 12] - sources: - model: stabilityai/japanese-stablelm-3b-4e1t-instruct layer_range: [22, 32] merge_method: passthrough dtype: bfloat16 ``` ## ๐Ÿ’ป Usage ```python !pip install -qU transformers accelerate from transformers import AutoTokenizer import transformers import torch model = "aipib/jp-stablelm-3b-4belt-prune2" messages = [{"role": "user", "content": "What is a large language model?"}] tokenizer = AutoTokenizer.from_pretrained(model) prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) pipeline = transformers.pipeline( "text-generation", model=model, torch_dtype=torch.float16, device_map="auto", ) outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95) print(outputs[0]["generated_text"]) ```
{"tags": ["merge", "mergekit", "lazymergekit", "stabilityai/japanese-stablelm-3b-4e1t-instruct"], "base_model": ["stabilityai/japanese-stablelm-3b-4e1t-instruct", "stabilityai/japanese-stablelm-3b-4e1t-instruct"]}
aipib/jp-stablelm-3b-4belt-prune2
null
[ "transformers", "safetensors", "stablelm_epoch", "text-generation", "merge", "mergekit", "lazymergekit", "stabilityai/japanese-stablelm-3b-4e1t-instruct", "custom_code", "base_model:stabilityai/japanese-stablelm-3b-4e1t-instruct", "autotrain_compatible", "region:us" ]
null
2024-05-02T08:59:43+00:00
null
transformers
{"license": "mit"}
letuan/mblip-mt0-xl-vivqa
null
[ "transformers", "pytorch", "blip-2", "license:mit", "endpoints_compatible", "region:us" ]
null
2024-05-02T09:00:07+00:00
text-generation
transformers
Quantization made by Richard Erkhov. [Github](https://github.com/RichardErkhov) [Discord](https://discord.gg/pvy7H8DZMG) [Request more models](https://github.com/RichardErkhov/quant_request) EEVE-Korean-10.8B-v1.0 - bnb 8bits - Model creator: https://huggingface.co/yanolja/ - Original model: https://huggingface.co/yanolja/EEVE-Korean-10.8B-v1.0/ Original model description: --- license: apache-2.0 base_model: upstage/SOLAR-10.7B-v1.0 tags: - generated_from_trainer model-index: - name: yanolja/EEVE-Korean-10.8B-v1.0 results: [] --- [<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl) <p align="left"> <img src="https://huggingface.co/yanolja/EEVE-Korean-10.8B-v1.0/resolve/main/eeve_logo.webp" width="50%"/> <p> # EEVE-Korean-10.8B-v1.0 ## Join Our Community on Discord! If you're passionate about the field of Large Language Models and wish to exchange knowledge and insights, we warmly invite you to join our Discord server. It's worth noting that Korean is the primary language used in this server. The landscape of LLM is evolving rapidly, and without active sharing, our collective knowledge risks becoming outdated swiftly. Let's collaborate and drive greater impact together! Join us here: [Discord Link](https://discord.gg/b27bAHg95m). ## Our Dedicated Team (Alphabetical Order) | Research | Engineering | Product Management | UX Design | |-----------------|-----------------|--------------------|-------------- | Myeongho Jeong | Geon Kim | Bokyung Huh | Eunsue Choi | | Seungduk Kim | Rifqi Alfi | | | | Seungtaek Choi | Sanghoon Han | | | | | Suhyun Kang | | | ## About the Model This model is a Korean vocabulary-extended version of [upstage/SOLAR-10.7B-v1.0](https://huggingface.co/upstage/SOLAR-10.7B-v1.0), specifically fine-tuned on various Korean web-crawled datasets available on HuggingFace. Our approach was to expand the model's understanding of Korean by pre-training the embeddings for new tokens and partially fine-tuning the `lm_head` embeddings for the already existing tokens while preserving the original parameters of the base model. ### Technical Deep Dive <p align="left"> <img src="https://huggingface.co/yanolja/EEVE-Korean-10.8B-v1.0/resolve/main/EEVE_figure.png" width="100%"/> <p> To adapt foundational models from English to Korean, we use subword-based embedding with a seven-stage training process involving parameter freezing. This approach progressively trains from input embeddings to full parameters, efficiently extending the model's vocabulary to include Korean. Our method enhances the model's cross-linguistic applicability by carefully integrating new linguistic tokens, focusing on causal language modeling pre-training. We leverage the inherent capabilities of foundational models trained on English to efficiently transfer knowledge and reasoning to Korean, optimizing the adaptation process. For more details, please refer to our technical report: [Efficient and Effective Vocabulary Expansion Towards Multilingual Large Language Models](https://arxiv.org/abs/2402.14714). Hereโ€™s an simplified code for our key approach: ```python # number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000. def freeze_partial_embedding_hook(grad): grad[:number_of_old_tokens] = 0 return grad for name, param in model.named_parameters(): if ("lm_head" in name or "embed_tokens" in name) and "original" not in name: param.requires_grad = True if "embed_tokens" in name: param.register_hook(freeze_partial_embedding_hook) else: param.requires_grad = False ``` ### Usage and Limitations Keep in mind that this model hasn't been fine-tuned with instruction-based training. While it excels in Korean language tasks, we advise careful consideration and further training for specific applications. ### Training Details Our modelโ€™s training was comprehensive and diverse: - **Vocabulary Expansion:** We meticulously selected 8,960 Korean tokens based on their frequency in our Korean web corpus. This process involved multiple rounds of tokenizer training, manual curation, and token frequency analysis, ensuring a rich and relevant vocabulary for our model. 1. **Initial Tokenizer Training:** We trained an intermediate tokenizer on a Korean web corpus, with a vocabulary of 40,000 tokens. 2. **Extraction of New Korean Tokens:** From the intermediate tokenizer, we identified all Korean tokens not present in the original SOLAR's tokenizer. 3. **Manual Tokenizer Construction:** We then built the target tokenizer, focusing on these new Korean tokens. 4. **Frequency Analysis:** Using the target tokenizer, we processed a 100GB Korean corpus to count each token's frequency. 5. **Refinement of Token List:** We removed tokens appearing less than 6,000 times, ensuring to secure enough tokens to train models later. 6. **Inclusion of Single-Letter Characters:** Counted missing Korean single-letter characters and added them to the target tokenizer that appeared more than 6,000 times. 7. **Iterative Refinement:** We repeated steps 2 to 6 until there were no tokens to drop or add. 8. **Training Bias Towards New Tokens:** Our training data was biased to include more texts with new tokens, for effective learning. This rigorous approach ensured a comprehensive and contextually rich Korean vocabulary for the model. ## Citation ``` @misc{kim2024efficient, title={Efficient and Effective Vocabulary Expansion Towards Multilingual Large Language Models}, author={Seungduk Kim and Seungtaek Choi and Myeongho Jeong}, year={2024}, eprint={2402.14714}, archivePrefix={arXiv}, primaryClass={cs.CL} } ```
{}
RichardErkhov/yanolja_-_EEVE-Korean-10.8B-v1.0-8bits
null
[ "transformers", "safetensors", "llama", "text-generation", "conversational", "arxiv:2402.14714", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "8-bit", "region:us" ]
null
2024-05-02T09:00:51+00:00
text-generation
transformers
Quantization made by Richard Erkhov. [Github](https://github.com/RichardErkhov) [Discord](https://discord.gg/pvy7H8DZMG) [Request more models](https://github.com/RichardErkhov/quant_request) xlm-roberta-large-squad2 - bnb 8bits - Model creator: https://huggingface.co/deepset/ - Original model: https://huggingface.co/deepset/xlm-roberta-large-squad2/ Original model description: --- language: multilingual license: cc-by-4.0 tags: - question-answering datasets: - squad_v2 model-index: - name: deepset/xlm-roberta-large-squad2 results: - task: type: question-answering name: Question Answering dataset: name: squad_v2 type: squad_v2 config: squad_v2 split: validation metrics: - type: exact_match value: 81.8281 name: Exact Match verified: true verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNzVhZDE2NTg5NmUwOWRkMmI2MGUxYjFlZjIzNmMyNDQ2MDY2MDNhYzE0ZjY5YTkyY2U4ODc3ODFiZjQxZWQ2YSIsInZlcnNpb24iOjF9.f_rN3WPMAdv-OBPz0T7N7lOxYz9f1nEr_P-vwKhi3jNdRKp_JTy18MYR9eyJM2riKHC6_ge-8XwfyrUf51DSDA - type: f1 value: 84.8886 name: F1 verified: true verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZGE5MWJmZGUxMGMwNWFhYzVhZjQwZGEwOWQ4N2Q2Yjg5NzdjNDFiNDhiYTQ1Y2E5ZWJkOTFhYmI1Y2Q2ZGYwOCIsInZlcnNpb24iOjF9.TIdH-tOx3kEMDs5wK1r6iwZqqSjNGlBrpawrsE917j1F3UFJVnQ7wJwaj0OIgmC4iw8OQeLZL56ucBcLApa-AQ --- # Multilingual XLM-RoBERTa large for QA on various languages ## Overview **Language model:** xlm-roberta-large **Language:** Multilingual **Downstream-task:** Extractive QA **Training data:** SQuAD 2.0 **Eval data:** SQuAD dev set - German MLQA - German XQuAD **Training run:** [MLFlow link](https://public-mlflow.deepset.ai/#/experiments/124/runs/3a540e3f3ecf4dd98eae8fc6d457ff20) **Infrastructure**: 4x Tesla v100 ## Hyperparameters ``` batch_size = 32 n_epochs = 3 base_LM_model = "xlm-roberta-large" max_seq_len = 256 learning_rate = 1e-5 lr_schedule = LinearWarmup warmup_proportion = 0.2 doc_stride=128 max_query_length=64 ``` ## Performance Evaluated on the SQuAD 2.0 English dev set with the [official eval script](https://worksheets.codalab.org/rest/bundles/0x6b567e1cf2e041ec80d7098f031c5c9e/contents/blob/). ``` "exact": 79.45759285774446, "f1": 83.79259828925511, "total": 11873, "HasAns_exact": 71.96356275303644, "HasAns_f1": 80.6460053117963, "HasAns_total": 5928, "NoAns_exact": 86.93019343986543, "NoAns_f1": 86.93019343986543, "NoAns_total": 5945 ``` Evaluated on German [MLQA: test-context-de-question-de.json](https://github.com/facebookresearch/MLQA) ``` "exact": 49.34691166703564, "f1": 66.15582561674236, "total": 4517, ``` Evaluated on German [XQuAD: xquad.de.json](https://github.com/deepmind/xquad) ``` "exact": 61.51260504201681, "f1": 78.80206098332569, "total": 1190, ``` ## Usage ### In Haystack For doing QA at scale (i.e. many docs instead of single paragraph), you can load the model also in [haystack](https://github.com/deepset-ai/haystack/): ```python reader = FARMReader(model_name_or_path="deepset/xlm-roberta-large-squad2") # or reader = TransformersReader(model="deepset/xlm-roberta-large-squad2",tokenizer="deepset/xlm-roberta-large-squad2") ``` ### In Transformers ```python from transformers import AutoModelForQuestionAnswering, AutoTokenizer, pipeline model_name = "deepset/xlm-roberta-large-squad2" # a) Get predictions nlp = pipeline('question-answering', model=model_name, tokenizer=model_name) QA_input = { 'question': 'Why is model conversion important?', 'context': 'The option to convert models between FARM and transformers gives freedom to the user and let people easily switch between frameworks.' } res = nlp(QA_input) # b) Load model & tokenizer model = AutoModelForQuestionAnswering.from_pretrained(model_name) tokenizer = AutoTokenizer.from_pretrained(model_name) ``` ## Authors **Branden Chan:** [email protected] **Timo Mรถller:** [email protected] **Malte Pietsch:** [email protected] **Tanay Soni:** [email protected] ## About us <div class="grid lg:grid-cols-2 gap-x-4 gap-y-3"> <div class="w-full h-40 object-cover mb-2 rounded-lg flex items-center justify-center"> <img alt="" src="https://raw.githubusercontent.com/deepset-ai/.github/main/deepset-logo-colored.png" class="w-40"/> </div> <div class="w-full h-40 object-cover mb-2 rounded-lg flex items-center justify-center"> <img alt="" src="https://raw.githubusercontent.com/deepset-ai/.github/main/haystack-logo-colored.png" class="w-40"/> </div> </div> [deepset](http://deepset.ai/) is the company behind the open-source NLP framework [Haystack](https://haystack.deepset.ai/) which is designed to help you build production ready NLP systems that use: Question answering, summarization, ranking etc. Some of our other work: - [Distilled roberta-base-squad2 (aka "tinyroberta-squad2")]([https://huggingface.co/deepset/tinyroberta-squad2) - [German BERT (aka "bert-base-german-cased")](https://deepset.ai/german-bert) - [GermanQuAD and GermanDPR datasets and models (aka "gelectra-base-germanquad", "gbert-base-germandpr")](https://deepset.ai/germanquad) ## Get in touch and join the Haystack community <p>For more info on Haystack, visit our <strong><a href="https://github.com/deepset-ai/haystack">GitHub</a></strong> repo and <strong><a href="https://docs.haystack.deepset.ai">Documentation</a></strong>. We also have a <strong><a class="h-7" href="https://haystack.deepset.ai/community">Discord community open to everyone!</a></strong></p> [Twitter](https://twitter.com/deepset_ai) | [LinkedIn](https://www.linkedin.com/company/deepset-ai/) | [Discord](https://haystack.deepset.ai/community) | [GitHub Discussions](https://github.com/deepset-ai/haystack/discussions) | [Website](https://deepset.ai) By the way: [we're hiring!](http://www.deepset.ai/jobs)
{}
RichardErkhov/deepset_-_xlm-roberta-large-squad2-8bits
null
[ "transformers", "safetensors", "xlm-roberta", "text-generation", "autotrain_compatible", "endpoints_compatible", "8-bit", "region:us" ]
null
2024-05-02T09:01:13+00:00
text-generation
transformers
{"license": "llama2"}
emrecanacikgoz/hamza-gpt2-xl
null
[ "transformers", "safetensors", "gpt2", "text-generation", "conversational", "license:llama2", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
null
2024-05-02T09:01:31+00:00
reinforcement-learning
ml-agents
# **ppo** Agent playing **Worm** This is a trained model of a **ppo** agent playing **Worm** 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 ๐Ÿถ 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: chirbard/ppo-Worm 3. Step 2: Select your *.nn /*.onnx file 4. Click on Watch the agent play ๐Ÿ‘€ ## Hyperparameters ``` behaviors: Worm: trainer_type: ppo hyperparameters: batch_size: 2024 buffer_size: 20240 learning_rate: 0.0003 beta: 0.005 epsilon: 0.2 lambd: 0.95 num_epoch: 3 learning_rate_schedule: linear network_settings: normalize: true hidden_units: 512 num_layers: 3 vis_encode_type: simple reward_signals: extrinsic: gamma: 0.9995 strength: 1.0 keep_checkpoints: 5 max_steps: 5000000 time_horizon: 1000 summary_freq: 30000 ```
{"library_name": "ml-agents", "tags": ["Worm", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-Worm"]}
chirbard/ppo-Worm
null
[ "ml-agents", "tensorboard", "onnx", "Worm", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-Worm", "region:us" ]
null
2024-05-02T09:01:32+00:00
null
null
{"license": "apache-2.0"}
NovaTech86/Mia
null
[ "license:apache-2.0", "region:us" ]
null
2024-05-02T09:02:22+00:00
text-classification
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 ๐Ÿค— 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": []}
MoGP/g_x_reg
null
[ "transformers", "safetensors", "bert", "text-classification", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]
null
2024-05-02T09:02:50+00:00
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 ๐Ÿค— 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": []}
azhara001/donut-base-demo-new-3e-05_AdamW_1876
null
[ "transformers", "safetensors", "vision-encoder-decoder", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]
null
2024-05-02T09:03:56+00:00
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 ๐Ÿค— 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": []}
tropianhs/mistral-tweet-finetune-tropianhs-full
null
[ "transformers", "safetensors", "mistral", "text-generation", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "4-bit", "region:us" ]
null
2024-05-02T09:03:59+00:00
text-classification
transformers
{"license": "mit"}
wisnu001binus/hate_speech_detection_ALBERTbase
null
[ "transformers", "safetensors", "albert", "text-classification", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]
null
2024-05-02T09:04:10+00:00
text-generation
transformers
# Uploaded model - **Developed by:** waylandzhang - **License:** apache-2.0 - **Finetuned from model :** unsloth/llama-3-8b-bnb-4bit Teaching purpose modelใ€‚ ่ฟ™ไธชmodelๅชๆ˜ฏ้…ๅˆๆˆ‘่ง†้ข‘ๆ•™ๅญฆ็›ฎ็š„ ๏ผšD **QLoRA (4bit)** Params to replicate training Peft Config ``` r=8, target_modules=[ "q_proj", "k_proj", "v_proj", "o_proj", "gate_proj", "up_proj", "down_proj", ], lora_alpha=16, lora_dropout=0, bias="none", random_state=3407, use_rslora=False, # Rank stabilized LoRA loftq_config=None, # LoftQ ``` Training args ``` per_device_train_batch_size=2, per_device_eval_batch_size=2, gradient_accumulation_steps=4, # set to 4 to avoid issues with GPTQ Quantization warmup_steps=5, max_steps=300, # Fine-tune iterations learning_rate=2e-4, fp16=not torch.cuda.is_bf16_supported(), bf16=torch.cuda.is_bf16_supported(), evaluation_strategy="steps", prediction_loss_only=True, eval_accumulation_steps=1, eval_steps=10, logging_steps=1, optim="adamw_8bit", weight_decay=0.01, lr_scheduler_type="cosine", # instead of "linear" seed=1337, output_dir="wayland-files/models", report_to="wandb", # Log report to W&B ``` **Interernce Code** ```python from unsloth import FastLanguageModel import os import torch max_seq_length = 4096 # 2048 dtype = None load_in_4bit = True model, tokenizer = FastLanguageModel.from_pretrained( model_name="waylandzhang/Llama-3-8b-Chinese-Novel-4bit-lesson-v0.1", max_seq_length=max_seq_length, dtype=dtype, load_in_4bit=load_in_4bit, device_map="cuda", attn_implementation="flash_attention_2" ) FastLanguageModel.for_inference(model) # ไฝฟ็”จunsloth็š„ๆŽจ็†ๆจกๅผๅฏไปฅๅŠ ๅฟซ2ๅ€้€Ÿๅบฆ alpaca_prompt = """Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request. ### Instruction: {} ### Input: {} ### Response: {}""" inputs = tokenizer( [ alpaca_prompt.format( "็ป™ไฝ ไธ€ๆฎต่ฏ๏ผŒๅธฎๆˆ‘็ปง็ปญๅ†™ไธ‹ๅŽปใ€‚", # ไปปๅŠกๆŒ‡ไปค "ๅฐๆ˜Žๅœจ่ฅฟๅฎ‰ๅŸŽๅข™ไธŠ", # ็”จๆˆทๆŒ‡ไปค "", # output - ็•™็ฉบไปฅ่‡ชๅŠจ็”Ÿๆˆ / ไธ็•™็ฉบไปฅๅกซๅ…… ) ], return_tensors="pt").to("cuda") # Opt 1: ๆ–‡ๆœฌ็”Ÿๆˆ่พ“ๅ‡บ # outputs = model.generate(**inputs, max_new_tokens=500, use_cache=True) # print(tokenizer.batch_decode(outputs[0][len(inputs.input_ids[0]):], skip_special_tokens=True)) # Opt 2: ๆถˆๆฏๆตๅผ่พ“ๅ‡บ from transformers import TextStreamer text_streamer = TextStreamer(tokenizer, skip_prompt=True) _ = model.generate(**inputs, streamer=text_streamer, max_new_tokens=500) ``` This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
{"language": ["en", "zh"], "license": "apache-2.0", "tags": ["text-generation-inference", "transformers", "Chinese", "unsloth", "llama", "trl"], "base_model": "waylandzhang/Llama-3-8b-Chinese-Novel-4bit-lesson-v0.1"}
waylandzhang/Llama-3-8b-Chinese-Novel-4bit-lesson-v0.1
null
[ "transformers", "safetensors", "llama", "text-generation", "text-generation-inference", "Chinese", "unsloth", "trl", "en", "zh", "base_model:waylandzhang/Llama-3-8b-Chinese-Novel-4bit-lesson-v0.1", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "4-bit", "region:us" ]
null
2024-05-02T09:04:18+00:00
null
diffusers
More information on all the CLI arguments and the environment are available on your [`wandb` run page](https://wandb.ai/sayakpaul/diffusion-orpo-lora-sdxl/runs/23l9mn47).
{}
sayakpaul/sdxl-orpo-large-beta_orpo-0.005-beta_inner-500-lr-5e-7-scaled-steps-5000-no-warmup
null
[ "diffusers", "safetensors", "region:us" ]
null
2024-05-02T09:04:38+00:00
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 ๐Ÿค— 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": []}
youngisk/whisper-large-v2-korea-common_13
null
[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]
null
2024-05-02T09:04:50+00:00
sentence-similarity
sentence-transformers
# COCO0414/DNF-bge-m3 [bge-m3](https://huggingface.co/BAAI/bge-m3) based model. This embedding model for Dungeon & Fighter data. Trained data, [Dungeon&Fighter](https://df.nexon.com) user community QA board. Extract 79k QA pairs data in 20k articles. This model was created to use RAG. <!--- 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 import torch question = "์‚ฌ๋„๋“ค์— ๋Œ€ํ•ด์„œ ์•Œ๋ ค์ค˜" # Data from namuwiki reval_content = "์ œ6 ์‚ฌ๋„์ œ7 ์‚ฌ๋„์ œ8 ์‚ฌ๋„๋ฌดํ˜•์˜ ์‹œ๋กœ์ฝ”๊ฒ€์€ ์งˆ๋ณ‘์˜ ๋””๋ ˆ์ง€์—๋ถˆ์„ ๋จน๋Š” ์•ˆํ†ค๊ธด ๋ฐœ์˜ ๋กœํ„ฐ์Šค์ œ9 ์‚ฌ๋„์ œ10 ์‚ฌ๋„์ œ11 ์‚ฌ๋„์ œ12 ์‚ฌ๋„(่ˆŠ) ํญ๋ฃก์™• ๋ฐ”์นผ(ๆ–ฐ) ๊ฑด์„ค์ž ๋ฃจํฌ์„ฑ์•ˆ์˜ ๋ฏธ์นด์—˜๋ผํ˜ผ๋ˆ์˜ ์˜ค์ฆˆ๋งˆ์„ธ๋ฆฌ์•„ ํ‚ค๋ฅด๋ฏผ ๊ฐ™์ด ๋ณด๊ธฐ: ํ…Œ์•„๋‚˜(์ธ๊ณต์‹ )์ œ1 ์‚ฌ๋„ - ์ˆ™๋ช…์˜ ์นด์ธ. ์ฃฝ์Œ์ด ๋‘๋ ค์›Œํ•˜๋Š” ์ž.์ œ2 ์‚ฌ๋„ - ์šฐ๋Š” ๋ˆˆ์˜ ํž๋”. ๋‘ ๊ฐ€์ง€ ์–ผ๊ตด์— ์ฐฌ์—ฐํžˆ ๋น›๋‚˜๋Š” ์ด์Šฌ์„ ๊ฐ์ถ˜ ์ž.[A] ์ œ3 ์‚ฌ๋„ - ์ฐฝ๊ณต์˜ ์ด์‹œ์Šค-ํ”„๋ ˆ์ด (ํ”„๋ ˆ์ด-์ด์‹œ์Šค). ๋•…์— ๋ฐœ์„ ๋”›์ง€ ์•Š๋Š” ์ž.์ œ4 ์‚ฌ๋„ - ์ •๋ณต์ž ์นด์‹œ์•ผ์Šค. ํ”ผ๋กœ ๊ฐ•์ฒ ์„ ์ ์‹œ๋Š” ์ž.์ œ5 ์‚ฌ๋„โ€  - ๋ฌดํ˜•์˜ ์‹œ๋กœ์ฝ”. ์ˆ˜ ๋ฐฑ์˜ ์–ผ๊ตด์„ ๊ฐ€์กŒ์œผ๋˜ ๋ณด์ด์ง€ ์•Š๋Š” ์ž. - (์˜ค๋ฆฌ์ง„ ์ด์ „)๋ก์‹œ์—๊ฒŒ ์‚ฌ๋ง. (์˜ค๋ฆฌ์ง„ ์ดํ›„) 4์ธ์˜ ์›จํŽ€๋งˆ์Šคํ„ฐ์—๊ฒŒ ์‚ฌ๋ง.[4]์ดํ›„ ๊ทธ๋ฆผ์‹œ์ปค๊ฐ€ ์‚ฌ๋…์„ ๋ชจ๋‘ ๋ชจ์•„ ๋‹ค์‹œ ๋ถ€ํ™œํ•˜๊ณ  ํ•˜๋Š˜์„ฑ์„ ์ ๋ นํ•œ ๋’ค ์ดํŠผ ๊ณต์—…์ง€๋Œ€๊ฐ€ ์žˆ๋Š” ์ฒœ๊ณ„๋ฅผ ๋…ธ๋ฆฌ๊ณ  ์žˆ๋‹ค. ๊ทธ๋Ÿฌ๋‚˜ ๊ฒฐ๊ตญ ๋ฏธ๋ฆฌ ๋Œ€๊ธฐํ•˜๊ณ  ์žˆ๋˜ ์ฒœ๊ณ„๊ตฐ์—๊ฒŒ ์ง‘์ค‘ํฌํ™”๋กœ ๋˜ ๋‹ค์‹œ ์‚ฌ๋ง.์ œ6 ์‚ฌ๋„ - ๊ฒ€์€ ์งˆ๋ณ‘์˜ ๋””๋ ˆ์ง€์—. ๋”๋Ÿฌ์šด ํ”ผ๋ฅผ ํ˜๋ฆฌ๋Š” ์ž. - ๋…ธ์Šค๋งˆ์ด์–ด๋กœ ์ „์ด๋˜์–ด ๋ชจํ—˜๊ฐ€์™€ ๋ฏธ์‰˜, ์•„์ ค๋ฆฌ์•„์—๊ฒŒ ํŒจ๋ฐฐํ•œ ๋’ค ํž๋”์˜ ๊ณ„๋žต์œผ๋กœ ์ธํ•ด ์ฐจ์›์˜ ํ‹ˆ์œผ๋กœ ๋นจ๋ ค๋“ค์–ด๊ฐ€ ์˜จ ๋ชธ์ด ๊ฐˆ๊ฐˆ์ด ์ฐข๊ฒจ ๋‚˜๊ฐ€๋ฉฐ ๋ด‰์ธ. ์„ค์ •์ƒ ๋ถˆ์‚ฌ์ด๊ธฐ์— ์†Œ๋ฉธํ•˜์ง€ ์•Š์•˜๊ณ , ๋ถˆ์•ˆ์ •ํ•œ ์ฐจ์› ์†์—์„œ ๋‹ค์‹œ ํž˜์„ ๊ธฐ๋ฅด๋Š” ์ค‘.์ œ7 ์‚ฌ๋„โ€  - ๋ถˆ์„ ๋จน๋Š” ์•ˆํ†ค. ๋ชธ์„ ๋ป—์–ด ๋Šฅํžˆ ์„ธ์ƒ ๋์— ๋‹ฟ์„ ์ˆ˜ ์žˆ๋Š” ์ž. - ํŒŒ์›Œ์Šคํ…Œ์ด์…˜์— ์ „์ด๋˜์–ด ๋ชจํ—˜๊ฐ€์™€ ์ฒœ๊ณ„ ํ† ๋ฒŒ๊ตฐ์—๊ฒŒ ์‚ฌ๋ง.์ œ8 ์‚ฌ๋„โ€  - ๊ธด๋ฐœ์˜ ๋กœํ„ฐ์Šค. ํ•œ๋ฒˆ์— ์ˆ˜์ฒœ์˜ ๋ฌด๊ธฐ๋ฅผ ์ฅ˜ ์ˆ˜ ์žˆ๋Š” ์ž. - ๋ฒ ํžˆ๋ชจ์Šค๋กœ ์ „์ด๋˜์–ด 3์ธ์˜ ์›จํŽ€๋งˆ์Šคํ„ฐ๋“ค๊ณผ ์ œ๊ตญ๊ตฐ, ๋ชจํ—˜๊ฐ€์—๊ฒŒ ์‚ฌ๋ง.(่ˆŠ)์ œ9 ์‚ฌ๋„โ€  - ํญ๋ฃก์™• ๋ฐ”์นผ. ๋ถˆ์˜ ์ˆจ๊ฒฐ์„ ๋‚ด๋Š” ์ž. - 500๋…„ ์ „ ๋งˆ๊ณ„์—์„œ ๋„๋ง์ณ ๋‚˜์™€ ์ฒœ๊ณ„๋ฅผ ์ง€๋ฐฐํ•˜๋˜ ์ค‘ ์ฒœ๊ณ„ ์ €ํ•ญ๊ตฐ์— ์˜ํ•ด ์‚ฌ๋ง.[5](ๆ–ฐ)์ œ9 ์‚ฌ๋„โ€  - ๊ฑด์„ค์ž ๋ฃจํฌ. ๋ง ์—†์ด ํ™์„ ๋งŒ์ง€๋Š” ์ž. - ์ž์‹ ์˜ ๊ฑฐ์ฃผ์ง€์ธ ์ฃฝ์€ ์ž์˜ ์„ฑ์—์„œ ์‚ฌ๋ง.[6]์ œ10 ์‚ฌ๋„ - ์„ฑ์•ˆ์˜ ๋ฏธ์นด์—˜๋ผ. ์ง„์‹ค์„ ๊ฟฐ๋šซ์–ด ๋ณด๋Š” ์ž.[7]์ œ11 ์‚ฌ๋„โ€  - ํ˜ผ๋ˆ์˜ ์˜ค์ฆˆ๋งˆ. ์ฃฝ์Œ์—์„œ ์ผ์–ด๋‚œ ์ž. ๊ฒ€์€ ๋Œ€์ง€์—์„œ ์นด์ž”์— ์˜ํ•ด ๋ด‰์ธ ์ค‘์ด์—ˆ์œผ๋‚˜, ์ดํ›„ ๋ด‰์ธ์ด ์™„์ „ํžˆ ํ’€๋ ค ๋‚ ๋›ฐ๋‹ค๊ฐ€ ๋ชจํ—˜๊ฐ€๋“ค๊ณผ์˜ ๊ฒฐ์ „์œผ๋กœ ์‚ฌ๋ง.์ œ12 ์‚ฌ๋„ - ์„ธ๋ฆฌ์•„ ํ‚ค๋ฅด๋ฏผ. ๋น„๋ฐ€์„ ์•Œ๊ณ  ์žˆ๋Š” ์ž.[A]ํ˜„์žฌ ํ”Œ๋ ˆ์ธ : ์•„๋ผ๋“œ์˜ ์ด์•ผ๊ธฐ ์ง„ํ–‰ ์ƒํ™ฉ์—์„œ ์‚ด์•„์žˆ๋Š” ์‚ฌ๋„๋Š” ์นด์ธ, ํž๋”, ์ด์‹œ์Šค-ํ”„๋ ˆ์ด, ์นด์‹œ์•ผ์Šค, ๋””๋ ˆ์ง€์—, ๋ฏธ์นด์—˜๋ผ, ์„ธ๋ฆฌ์•„๊นŒ์ง€ ์ด 7๋ช…์ด๋‹ค.์‚ฌ๋„์˜ ์ˆœ์œ„๋Š” ๋งˆ๊ณ„์— ์˜ฌ๋ผํƒ„ ์ˆœ์„œ์ด๊ธด ํ•œ๋ฐ ์„œ์—ด์—๋„ ์˜ํ–ฅ์ด ์žˆ๊ธด ํ•œ์ง€ ์ œ4์‚ฌ๋„ ์นด์‹œ์•ผ์Šค์˜ ๊ฒฝ์šฐ ๊ตฌ ์Šคํ† ๋ฆฌ์—์„œ๋Š” ์„œ์—ด 4์œ„์˜ ์‚ฌ๋„๋ผ๊ณ  ํ•œ๋‹ค. ๋ฏธ์นด์—˜๋ผ๋ถ€ํ„ฐ๋Š” ๋งˆ๊ณ„๋ž‘ ์ธ์—ฐ์ด ์—†๋Š” ์‚ฌ๋„์ด๋‹ค.3. ๋ชจํ‹ฐ๋ธŒ[ํŽธ์ง‘]์œ ๋ž˜๋Š” ์˜ˆ์ˆ˜์˜ ์—ด๋‘ ์ œ์ž์ธ ์‚ฌ๋„์ด๋‹ค. ํ˜ธ์นญ๋„ ๊ฐ™์€๋ฐ๋‹ค๊ฐ€ ๋งˆ์นจ ์ˆซ์ž๋„ ๋”ฑ ์—ด๋‘˜์ด๊ณ  ๊ทธ๋“ค ์ค‘ ํ•˜๋‚˜๊ฐ€ ๋‚ด์ณ์ง€๊ณ  ๋‹ค๋ฅธ ์ด๊ฐ€ ์ž„๋ช…๋œ ์ผ๊นŒ์ง€ ์˜ˆ์ˆ˜์˜ ์—ด๋‘ ์‚ฌ๋„๋ž‘ ๋”ฑ ๋“ค์–ด๋งž๋Š”๋‹ค.[9] ์ฐฝ์„ธ๊ธฐ, ์ข…์„ธ๊ธฐ, ์ฐฝ์‹ ์„ธ๊ธฐ๋กœ ์ด๋ฃจ์–ด์ง„ ๋˜ํŒŒ์˜ ์„ฑ์„œ๋„ ์„ฑ๊ฒฝ์„ ๋ชจํ‹ฐ๋ธŒ๋กœ ํ•œ ๊ฒƒ์ด๋ฏ€๋กœ ์–ด์ฐŒ ๋ณด๋ฉด ์ž์—ฐ์Šค๋Ÿฌ์šด ์—ฐ๊ฒฐ์ด๋‹ค.๋˜ํ•œ, ๊ฐ ์‚ฌ๋„๋“ค์— ๋ฐ˜์˜๋œ ๊ฐœ๋ณ„์  ๋ชจํ‹ฐ๋ธŒ๋Š” ๋‹ค์Œ๊ณผ ๊ฐ™๋‹ค. ์–ธ๊ธ‰๋˜์ง€ ์•Š์€ ์‚ฌ๋„๋Š” ๋„ค์˜คํ”Œ์—์„œ ๋…์ž์ ์œผ๋กœ ์ฐฝ์ž‘ํ•œ ์ผ€์ด์Šค๋‹ค.์นด์ธ: ์„ฑ๊ฒฝ(์•„๋‹ด, ์นด์ธ)ํž๋”: ์„ฑ๊ฒฝ(ํ•˜์™€)์ด์‹œ์Šค-ํ”„๋ ˆ์ด/ํ”„๋ ˆ์ด-์ด์‹œ์Šค: ์Šฌ๋ผ๋ธŒ ์‹ ํ™”(๋ฒจ๋กœ๋ณด๊ทธ, ์ฒด๋ฅด๋…ธ๋ณด๊ทธ), ๋ถ์œ ๋Ÿฝ ์‹ ํ™”(ํ”„๋ ˆ์ด), ์ด์ง‘ํŠธ ์‹ ํ™”(์ด์‹œ์Šค) [10]์นด์‹œ์•ผ์Šค: ์ผ๋ณธ ์š”๊ดด(์˜ค๋‹ˆ)์‹œ๋กœ์ฝ”: ์‚ฌํ•˜๋ผ ์‚ฌ๋ง‰์˜ ์—ดํ’(์‹œ๋กœ์ฝ”)[11]๋””๋ ˆ์ง€์—: ์งˆ๋ณ‘(ํ‘์‚ฌ๋ณ‘ ๋“ฑ)๋กœํ„ฐ์Šค: ๋ฐ”๋‹ค๊ดด๋ฌผ(ํฌ๋ผ์ผ„)๋ฐ”์นผ: ์•…๋งˆ์„ฑ ๋“œ๋ผํ˜๋ผ(๋“œ๋ผํ˜๋ผ ๋ธ”๋ผ๋“œ ์ฒดํŽ˜์Šˆ)๋ฃจํฌ: ์ผˆํŠธ ์‹ ํ™”(๋ฃจ ๋ผ์™€๋”)๋ฏธ์นด์—˜๋ผ: ๊ฐ€ํ†จ๋ฆญ(๋ฉ”์‹œ์•„)์˜ค์ฆˆ๋งˆ: ์•…๋งˆ์„ฑ ๋“œ๋ผํ˜๋ผ(๋“œ๋ผํ˜๋ผ ๋ธ”๋ผ๋“œ ์ฒดํŽ˜์Šˆ)์„ธ๋ฆฌ์•„ ํ‚ค๋ฅด๋ฏผ: ???3.1. ๋ฌธ์–‘[ํŽธ์ง‘]์‚ฌ๋„์—๊ฒ ์ž์‹ ์„ ์ƒ์ง•ํ•˜๋Š” ๊ณ ์œ ์˜ ๋ฌธ์–‘์ด ์กด์žฌํ•˜๋ฉฐ ์‚ฌ๋„์™€ ๊ด€๋ จ๋œ ์‚ฌ๊ฑด์ด ์ผ์–ด๋‚จ์— ๋”ฐ๋ผ ๋ฌธ์–‘์ด ๋ณ€๊ฒฝ๋˜๋Š” ๊ฒฝ์šฐ๋„ ์žˆ๋‹ค.[12]์นด์ธ์€ ๊ทธ๋ฅผ ๋‘๋ ค์›Œํ•˜๊ณ  ๊ฒฝ์™ธํ•˜๋Š” ์ž๋“ค์— ์˜ํ•ด์„œ ๋ฌธ์–‘์ด ๋งŒ๋“ค์–ด์กŒ๋‹ค. ํž๋”๋Š” ์ž์‹ ์ด ๊ฐ€์ง„ ์šฐ๋Š” ๋ˆˆ์„ ํ˜•์ƒํ™”ํ•˜์—ฌ ๋ฌธ์–‘์„ ๋งŒ๋“ค์—ˆ๋‹ค. ํ…Œ๋ผ์ฝ”ํƒ€์—์„œ๋Š” ์ด ๋ฌธ์–‘์„ ์‹ ์„ฑํ•˜๊ฒŒ ์—ฌ๊ธด๋‹ค. ์ด์‹œ์Šค-ํ”„๋ ˆ์ด๋Š” ๊ทธ๋ฅผ ๋”ฐ๋ฅด๋Š” ์ถ”์ข…์ž๋“ค์— ์˜ํ•ด์„œ ๋ฌธ์–‘์ด ๋งŒ๋“ค์–ด์กŒ์œผ๋ฉฐ, ๋ฐค์˜ ๋งˆ์ฒœ๋ฃจ ์ „ํˆฌ ์ดํ›„์— ์ด์‹œ์Šค์˜ ์ƒ์ง•์ด[13] ์ถ”๊ฐ€" model = SentenceTransformer('COCO0414/DNF-bge-m3') question_embedding = model.encode(question, convert_to_tensor=True) answer_embedding = model.encode(answer, convert_to_tensor=True) similarity = torch.nn.functional.cosine_similarity(question_embedding, answer_embedding, dim=0) print(similarity.item()) # 0.6239629983901978 ```
{"library_name": "sentence-transformers", "tags": ["sentence-transformers", "feature-extraction", "sentence-similarity"], "pipeline_tag": "sentence-similarity"}
COCO0414/DNF-bge-m3
null
[ "sentence-transformers", "safetensors", "xlm-roberta", "feature-extraction", "sentence-similarity", "endpoints_compatible", "region:us" ]
null
2024-05-02T09:05:12+00:00
text-generation
transformers
# ๐Ÿ”ฎ THIS IS UNHOLY ๐Ÿ”ฆ ![image/png](https://huggingface.co/spaces/WEMAKE-CX/home/resolve/main/WEMAKE-CX_VX-Unholy-13B-banner.jpg) This model is a proud fork of [Undi95/Unholy-v2-13B](https://huggingface.co/Undi95/Unholy-v2-13B), but we've infused it with [WEMAKE-CX/V41](https://huggingface.co/WEMAKE-CX/V41). The mix of tech with emotional intelligence opens new ways for understanding and interaction. ## Why ๐Ÿ’™ WeMake VX-Unholy We don't only want to advance technology but to do so with consciousness, responsibility, and empathy. VX-Unholy represents one of many ways we take towards this goal. ### Our Goals With VX-Unholy - **Foster Emotional Intelligence:** Incorporating our V41 emotional intelligence unit, VX-Unholy aims to bring a new depth of understanding and empathy to AI interactions. - **Promote Ethical AI Use:** We stand firmly for the ethical development and application of AI. This model is shared with the world under the [cc-by-nc-4.0](https://spdx.org/licenses/CC-BY-NC-4.0) license that encourages non-commercial, responsible use. - **Encourage Innovation and Learning:** We believe in the power of community and shared knowledge. VX-Unholy is not just a tool but an open invitation for curious minds to explore, learn, and innovate together. ### How We Use VX-Unholy VX-Unholy serves as one of many efforts to develop AI solutions that are not only technologically advanced but also socially conscious and emotionally intelligent. It's used in: - Research and Development: Enhancing our understanding of AI's potential to comprehend and mimic emotional intelligence. - Community Projects: Engaging with developers, ethicists, and the broader community to explore innovative uses and promote responsible AI development. - Educational Programs: Offering resources for learning and exploration to foster the next generation of responsible AI engineers and enthusiasts. ## Our Commitment to Ethics and Sustainability It's 2024, of course, our commitment to sustainability, ethical responsibility, and equal opportunities shapes every project we take. VX-Unholy reflects these values and our belief in the power of technology to change the world for the betterโ€”when guided by ๐Ÿ’™ and responsibility. Thank you for your interest in VX-Unholy. Together, let's make a positive impact on the world, one intelligent interaction at a time. ๐Ÿ’™ **The WeMake Team** [๐Ÿค Ethics Policy](https://wemake.cx/legal/ethics/) [๐Ÿ›ก๏ธ Privacy Policy](https://wemake.cx/legal/privacy) [๐Ÿ“‡ Imprint](https://wemake.cx/legal/imprint)
{"language": ["en", "de"], "license": "cc-by-nc-4.0", "tags": ["not-for-all-audiences", "nsfw"], "datasets": ["WEMAKE-CX/Intelligent-Content-Understanding"]}
WEMAKE-CX/VX-Unholy-13B
null
[ "transformers", "safetensors", "llama", "text-generation", "not-for-all-audiences", "nsfw", "en", "de", "dataset:WEMAKE-CX/Intelligent-Content-Understanding", "license:cc-by-nc-4.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
null
2024-05-02T09:05:29+00:00
summarization
transformers
{"pipeline_tag": "summarization"}
SyedShaheer/bart-large-cnn-samsum_tuned_V2_1
null
[ "transformers", "pytorch", "bart", "text2text-generation", "summarization", "autotrain_compatible", "endpoints_compatible", "region:us" ]
null
2024-05-02T09:07:20+00:00
null
null
{}
andersonbcdefg/tiny-emb-2024-05-02_09-08-42
null
[ "region:us" ]
null
2024-05-02T09:08:42+00:00
null
transformers
# Uploaded model - **Developed by:** CarolLiu999 - **License:** apache-2.0 - **Finetuned from model :** unsloth/llama-3-8b-Instruct-bnb-4bit This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
{"language": ["en"], "license": "apache-2.0", "tags": ["text-generation-inference", "transformers", "unsloth", "llama", "trl"], "base_model": "unsloth/llama-3-8b-Instruct-bnb-4bit"}
CarolLiu999/llama-3-8b-Instruct-bnb-4bit-lora-TWhealthCare
null
[ "transformers", "safetensors", "text-generation-inference", "unsloth", "llama", "trl", "en", "base_model:unsloth/llama-3-8b-Instruct-bnb-4bit", "license:apache-2.0", "endpoints_compatible", "region:us" ]
null
2024-05-02T09:08:42+00:00
unconditional-image-generation
diffusers
# Model Card for Unit 1 of the [Diffusion Models Class ๐Ÿงจ](https://github.com/huggingface/diffusion-models-class) This model is a diffusion model for unconditional image generation of cute ๐Ÿฆ‹. ## Usage ```python from diffusers import DDPMPipeline pipeline = DDPMPipeline.from_pretrained('izhl/sd-class-butterflies-32') image = pipeline().images[0] image
{"license": "mit", "tags": ["pytorch", "diffusers", "unconditional-image-generation", "diffusion-models-class"]}
izhl/sd-class-butterflies-32
null
[ "diffusers", "safetensors", "pytorch", "unconditional-image-generation", "diffusion-models-class", "license:mit", "diffusers:DDPMPipeline", "region:us" ]
null
2024-05-02T09:09:12+00:00
text-classification
transformers
{}
wisnu001binus/hate_speech_detection_RoBERTabase
null
[ "transformers", "safetensors", "roberta", "text-classification", "autotrain_compatible", "endpoints_compatible", "region:us" ]
null
2024-05-02T09:09:45+00:00
text-generation
transformers
{}
TwinDoc/H100_stage1_checkpoint-36000
null
[ "transformers", "safetensors", "llama", "text-generation", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
null
2024-05-02T09:10:20+00:00