Split (1)

train · 907k rows

modelId stringlengths 5 139	author stringlengths 2 42	last_modified timestamp[us, tz=UTC]date 2020-02-15 11:33:14 2025-07-27 12:28:27	downloads int64 0 223M	likes int64 0 11.7k	library_name stringclasses 533 values	tags listlengths 1 4.05k	pipeline_tag stringclasses 55 values	createdAt timestamp[us, tz=UTC]date 2022-03-02 23:29:04 2025-07-27 12:28:17	card stringlengths 11 1.01M
prashanth145x/my-awesome-model	prashanth145x	2025-06-18T09:48:51Z	0	0	transformers	[ "transformers", "safetensors", "bert", "feature-extraction", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	feature-extraction	2025-06-18T09:48:30Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
Mahadi249/deepseek-factchecker-merged	Mahadi249	2025-06-18T09:45:17Z	0	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "8-bit", "bitsandbytes", "region:us" ]	text-generation	2025-06-18T09:42:20Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
shahidrai/All_FrameNet_LLaMa	shahidrai	2025-06-18T09:40:20Z	29	0	peft	[ "peft", "safetensors", "unsloth", "arxiv:1910.09700", "region:us" ]	null	2025-06-09T14:41:40Z	--- base_model: unsloth/meta-llama-3.1-8b-instruct-bnb-4bit library_name: peft tags: - unsloth --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed] ### Framework versions - PEFT 0.15.2
jayalakshmikopuri/deepfake-audio-detector	jayalakshmikopuri	2025-06-18T09:39:14Z	64	0	null	[ "safetensors", "wav2vec2", "region:us" ]	null	2025-05-08T07:22:43Z	# Deepfake Audio Detector This model is fine-tuned for detecting deepfake audio using a dataset of misclassified samples. ## Training Details - Model: Heem2/Deepfake-Audio-Detection - Dataset: 100 real and 100 fake samples - Epochs: 5 - Learning Rate: 0.0003 - Batch Size: 8 - Dropout Rate: 0.3 ## Metrics - Final Eval Accuracy: N/A - Final Eval Precision: N/A - Final Eval Recall: N/A - Final Eval F1: N/A - Final Eval Loss: N/A ## Training Curves ![Training and Validation Loss](loss_plot.png) ![Training and Validation Accuracy](accuracy_plot.png) ## Usage ```python from transformers import AutoModelForAudioClassification, AutoFeatureExtractor model = AutoModelForAudioClassification.from_pretrained("jayalakshmikopuri/deepfake-audio-detector") feature_extractor = AutoFeatureExtractor.from_pretrained("jayalakshmikopuri/deepfake-audio-detector") # Example inference code import librosa import numpy as np audio, sr = librosa.load("path_to_audio.wav", sr=16000, mono=True) inputs = feature_extractor(audio, sampling_rate=16000, return_tensors="pt", padding=True, truncation=True, max_length=480000) outputs = model(**inputs) predicted_class = outputs.logits.argmax().item() print("Predicted class:", "Fake" if predicted_class == 1 else "Real") ``` ## Notes - The model is fine-tuned on a balanced dataset of misclassified real and fake audio samples. - Metrics are saved in `metrics.json` for detailed analysis.
BKM1804/mieumieu	BKM1804	2025-06-18T09:36:55Z	0	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "trl", "sft", "dpo", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-06-18T09:35:57Z	--- library_name: transformers tags: - trl - sft - dpo --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
Talking-Babies/orpo_opt_base_tokenizer	Talking-Babies	2025-06-18T09:35:09Z	0	0	transformers	[ "transformers", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2025-06-18T09:35:08Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
sgonzalezygil/sd-finetuning-dreambooth-v7	sgonzalezygil	2025-06-18T09:31:43Z	0	0	diffusers	[ "diffusers", "safetensors", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "diffusers:StableDiffusionPipeline", "region:us" ]	text-to-image	2025-06-18T09:30:09Z	--- library_name: diffusers --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🧨 diffusers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
Jade-Software/Jade-ModernBert-FT	Jade-Software	2025-06-18T09:27:18Z	628	0	sentence-transformers	[ "sentence-transformers", "safetensors", "modernbert", "sentence-similarity", "feature-extraction", "generated_from_trainer", "dataset_size:10217", "loss:CachedMultipleNegativesRankingLoss", "en", "arxiv:1908.10084", "arxiv:2101.06983", "base_model:nomic-ai/modernbert-embed-base", "base_model:finetune:nomic-ai/modernbert-embed-base", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	sentence-similarity	2025-04-08T02:47:07Z	--- language: - en license: apache-2.0 tags: - sentence-transformers - sentence-similarity - feature-extraction - generated_from_trainer - dataset_size:10217 - loss:CachedMultipleNegativesRankingLoss base_model: nomic-ai/modernbert-embed-base widget: - source_sentence: What integer value is assigned to the global constant SDS_SecondaryType in JADE? sentences: - '#### drawWidth Type: - Integer Availability: - Read or write at run time only The drawWidth property of the [Window](../window_class/window_class.htm) class contains the line width for output from graphics methods on a form or control. Set the drawWidth property to a value in the range 1 through 32,767. This value represents the width of the line in pixels. The default value is 1 pixel wide. Increase the value of the drawWidth property to increase the width of the line.' - '#### JadeDynamicObjectTypes Category Global Constants The global constants listed in the following table define symbolic names for the values of the [JadeDynamicObject](../../encyclosys1/jadedynamicobject_class/jadedynamicobject_class.htm#jadedynamicobjectclass) class [type](../../encyclosys1/jadedynamicobject_class/type.htm#typejadedynamicobject) attribute of dynamic objects returned from [JadeDatabaseAdmin](../../encyclosys1/jadedatabaseadmin_class/jadedatabaseadmin_class.htm#jadedatabaseadminclass) class query methods. \| Global Constant \| Integer Value \| \| ---- \| ---- \| \| SDS_PrimaryType \| 1 \| \| SDS_SecondaryProxyType \| 2 \| \| SDS_SecondaryType \| 3 \| \| SDS_TransactionType \| 4 \|' - "#### sortOrder\n\nType: - Integer\n\nAvailability: - Read or write at\ \ run time only\n\nThe sortOrder property of the [JadeTableColumn](jadetablecolumn_class.htm)\ \ class contains the precedence of the column referenced by this object when sorting,\ \ in the range 1 through 3, or it contains zero (0) to remove sorting\ \ on the current column.\n\nFor a description of this property, see the [Table](../../encyclowin/control_class/table_class.htm#tableclass)\ \ control [sortColumn](../../encyclowin/window__form__and_control_properties/sortcolumn.htm#sortcolumnwin)\ \ property. See also the [JadeTableColumn](jadetablecolumn_class.htm) class [sortAsc](sortasc.htm),\ \ [sortCased](sortcased.htm), and [sortType](sorttype.htm) properties, which are\ \ dependent on the column already being recorded as a sort column by the sortOrder\ \ property.\n\nThe code fragment in the following example shows the use of the\ \ sortOrder property.\n\n```\ntable1.accessColumn(2).sortOrder := 1; //\ \ first column in sort\r\ntable1.accessColumn(4).sortOrder := 2; // second column\r\ \ntable1.accessColumn(5).sortOrder := 3; // third column\n```" - source_sentence: How are values in the ByteArray referenced? sentences: - "#### findAllElementsByNameNS\n\n```\nfindAllElementsByNameNS(namespaceURI: String;\r\ \n localName: String;\r\n elements:\ \ JadeXMLElementArray input);\n```\nThe findAllElementsByNameNS method\ \ of the [JadeXMLElement](jadexmlelement_class.htm) class fills the elements array\ \ with all descendant elements that have the values specified in the namespaceURI\ \ and localName parameters, respectively.\n\nAs the search uses the collection\ \ sequence, the elements may not be in the document sequence.\n\nIf you want to\ \ match all namespaces or local names, specify an asterisk character (*'')\ \ in the namespaceURI or localName parameter. Note, however, that if\ \ you specify \"\"* in the localName parameter, the access method uses\ \ the document sequence to locate the requested elements rather than the collection\ \ sequence that optimizes performance." - '## ByteArray Class The ByteArray class is an ordered collection of [Byte](../../encycloprim/byte_type/byte_type.htm#byte) values in which the values are referenced by their position in the collection. Byte arrays inherit the methods defined in the [Array](../array_class/array_class.htm) class. The bracket ([ ]) subscript operators enable you to assign values to and receive values from a Byte array. For details about the methods defined in the ByteArray class, see "[ByteArray Methods](bytearray_methods.htm)", in the following section. [Array](../array_class/array_class.htm) (None)' - '#### Exposing Properties for a Selected Class To expose all properties for a selected class - Right‑click on the class row in the Classes table and then select the Expose Properties for Selected Class command from the popup menu that is displayed. This command does _not_ automatically add methods or constants to the C# exposure, even if the Show Methods or Show Constants option is checked. (For details, see "[Toggling the Display of Methods](toggling_the_display_of_methods.htm)" or "[Toggling the Display Constants](toggling_the_display_of_constants.htm)", later in this chapter.) All properties in that class are then exposed for inclusion in the C# exposure; that is, each property check box in the Features pane is checked, indicating that the properties for that class will be generated in the C# class library. You can tailor the property selection by unchecking the check box of any property that you want to exclude from the exposure.' - source_sentence: How can you resolve opening database error 14544 in single user mode? sentences: - "#### Changing Lock Type\n\nA type upgrade can queue and potentially time out,\ \ causing a [JoobObjectLockedException](joobobjectlockedexception.htm) to be thrown,\ \ if the requested type is not compatible with existing locks. For example, this\ \ could happen when upgrading a shared lock to exclusive.\n\nLock type downgrades\ \ will never be queued, as the strength is being lowered so there will be no lock\ \ incompatibilities.\n\nWhen a Jade session is in transaction state, requests\ \ to downgrade lock type are ignored. The lock maintains its current type. However,\ \ lock types can be upgraded regardless of transaction state.\n\nWhen a lock type\ \ is being upgraded from shared to update, the object is unlocked before the update\ \ lock is requested. This happens even if the Jade session is in transaction state,\ \ and is the only situation where an object is unlocked while in transaction state.\ \ The reason for doing this is to prevent potential deadlocks, as discussed in\ \ more detail under \"[Avoiding Deadlock Exceptions](avoiding_deadlock_exceptions.htm)\"\ , later in this chapter.\n\nThe following code fragment gives examples of upgrading\ \ and downgrading lock types.\n\n```\nTimeSpan timeOut = TimeSpan.FromSeconds(10);\r\ \ncontext.Lock(obj1, LockType.Shared, LockDuration.Transaction, timeOut);\r\n\ context.Lock(obj1, LockType.Reserve, LockDuration.Transaction, timeOut);\r\n \ \ // The lock is now upgraded from shared to reserve.\r\ \ncontext.Lock(coll, LockType.Exclusive, LockDuration.Transaction, timeOut);\r\ \n \r\nusing (System.Data.IDbTransaction tran = context.BeginTransaction())\r\ \n{\r\n context.Lock(obj1, LockType.Exclusive, LockDuration.Transaction,\r\n\ \ timeOut); // The lock type is upgraded to exclusive, as\r\ \n // locks can be upgraded (but not downgraded)\r\ \n // when in transaction state.\r\n foreach\ \ (C1 obj2 in coll)\r\n {\r\n // The exclusive lock on coll is not downgraded\ \ by the implicit shared\r\n // lock associated with foreach, because transaction\ \ state is in effect.\r\n }\r\n context.Lock(obj1, LockType.Shared, LockDuration.Transaction,\ \ timeOut);\r\n // The lock type is not downgraded, but remains\ \ as exclusive.\r\n tran.Commit(); // All transaction duration locks are\ \ released.\r\n}\n```" - '### 1411 - Attempt to add unknown system file Cause This error occurs if the system schema maintenance function attempts to add a new unknown system file. Action This is an internal error. If your Jade licenses include support, contact your local Jade support center or Jade Support.' - '### 14544 - A concurrent process has already opened the same database Cause This error occurs if you attempt to open a database that is already open in single user (exclusive) mode. Action Determine in which mode the database should be opened; that is, single user or multiuser mode.' - source_sentence: What is the cause of the 3323 DbCrypt error? sentences: - '### 3323 - DbCrypt memory allocation failure Cause This error occurs if a memory allocation error occurs in the use of the database encryption module. Action If your Jade licenses include support, contact your local Jade support center or Jade Support.' - '### 3028 - Database file is in use by another process Cause This error occurs if you attempt to open a database file that is already open by another process. Action Refer to the Jade messages log file (jommsg.log) for information about the file. Generally, another program is accessing the file or the database as a whole.' - '### Where Do Jade Methods Execute? Jade methods execute only in Jade nodes. A Jade node is the fundamental building block of Jade''s distributed architecture. Each node contains the Jade Object Manager (JOM), the Jade Interpreter, various caches, and one or more Jade processes. The Jade thin client is _not_ a Jade node; Jade methods do not execute there, although a great deal of effort has been expended to make it look as though they do. In most production systems, there is one database server node (jadrap.exe, jadrapb.exe, or jadserv.exe), one or more application server nodes (jadapp.exe or jadappb.exe), and one or more fat/standard client nodes (jade.exe) for background processing, web services, or HTML forms. When jade.exe is run in single user mode, there is one node only.' - source_sentence: Which subclasses are associated with the JadeXMLCharacterData class? sentences: - '## JadeXMLCharacterData Class The JadeXMLCharacterData class is the abstract superclass of character-based nodes in an XML document tree; that is, the text, CDATA, and comment nodes. For details about the property defined in the JadeXMLCharacterData class, see "[JadeXMLCharacterData Property](jadexmlcharacterdata_property.htm)", in the following section. [JadeXMLNode](../jadexmlnode_class/jadexmlnode_class.htm) [JadeXMLCDATA](../jadexmlcdata_class/jadexmlcdata_class.htm), [JadeXMLComment](../jadexmlcomment_class/jadexmlcomment_class.htm), [JadeXMLText](../jadexmltext_class/jadexmltext_class.htm)' - "### Minimizing the Working Set\n\nIn loops where there are multiple filters,\ \ apply the cheapest filters first and then the filters that reduce the working\ \ set the most. For example, consider the following code fragment, which finds\ \ sales of appliances in a specified city.\n\n```\nwhile iter.next(tran) do\r\n\ \ if tran.type = Type_Sale\r\n and tran.myBranch.myLocation.city = targetCity\r\ \n and tran.myProduct.isAppliance then\r\n <do something with tran>\r\ \n endif;\r\nendwhile;\n```\nIn this example, tran.type should be checked\ \ first, because it is the cheapest. The tran object must be fetched to evaluate\ \ all of the other conditions, so we may as well check the type attribute\ \ first. If we did the isAppliance check first, we would have to fetch all\ \ of the product objects for the transactions that were not sales. Regardless\ \ of how many transactions are sales and how many products are appliances, it\ \ will save time to check tran.type first.\n\nNow, assume that:\n\n- 80 percent\ \ of transactions are sales\n\n- 15 percent, on average, are likely to be in the\ \ target city\n\n- 90 percent of the products are appliances\n\nIt pays to check\ \ the city first, even though it means fetching the branch and location objects\ \ for the non‑appliance products. There are very few non‑appliance products, so\ \ the number of extra fetches is small. By contrast, checking for non‑appliance\ \ products for all other cities would result in a large number of extra fetches.\n\ \nIt doesn't matter if the filters are conditions of an [if](../../devref/ch1languageref/if_instruction.htm#if)\ \ instruction, multiple [if](../../devref/ch1languageref/if_instruction.htm#if)\ \ instructions, or multiple conditions in the [where](../../devref/ch1languageref/where_clause_optimization.htm#whereoptimization)\ \ clause of a [while](../../devref/ch1languageref/while_instruction.htm#while)\ \ statement; the end result is the same.\n\nThis code fragment example is simple\ \ and concise, to convey the concept. In the real world, each successive filter\ \ may be in another method, another class, or even another schema. It may take\ \ a bit of investigation to find all of the filters involved in a single loop." - '##### responseType Use the responseType parameter of the [beginNotification](beginnotification.htm) method to specify the frequency with which the subscribed event was notified. The valid values for the responseType parameter, represented by global constants in the [NotificationResponses](../../encycloprim/appaglobalconstants/notificationresponses_category.htm#notificationresponsescategory) category, are listed in the following table. \| Global Constant \| Integer Value \| Sends a notification… \| \| ---- \| ---- \| ---- \| \| Response_Cancel \| 1 \| When the object receives a matching event and then cancels the notification \| \| Response_Continuous \| 0 \| Whenever the object receives a matching event \| \| Response_Suspend \| 2 \| When the object receives a matching event and then suspends notification until the user refreshes the local copy of the object \|' pipeline_tag: sentence-similarity library_name: sentence-transformers --- # Jade-modernbert-ft `internally on leaderboard known as jade-ft-14-bert` This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [nomic-ai/modernbert-embed-base](https://huggingface.co/nomic-ai/modernbert-embed-base) on the jade_embeddings_train_25.04.04 dataset. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more. ## Model Details ### Model Description - Model Type: Sentence Transformer - Base model: [nomic-ai/modernbert-embed-base](https://huggingface.co/nomic-ai/modernbert-embed-base) <!-- at revision d556a88e332558790b210f7bdbe87da2fa94a8d8 --> - Maximum Sequence Length: 8192 tokens - Output Dimensionality: 768 dimensions - Similarity Function: Cosine Similarity - Training Dataset: - jade_embeddings_train_25.04.04 - Language: en - License: apache-2.0 ### Model Sources - Documentation: [Sentence Transformers Documentation](https://sbert.net) - Repository: [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers) - Hugging Face: [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers) ### Full Model Architecture ``` SentenceTransformer( (0): Transformer({'max_seq_length': 8192, 'do_lower_case': False}) with Transformer model: ModernBertModel (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True}) (2): Normalize() ) ``` ## Usage ### Direct Usage (Sentence Transformers) First install the Sentence Transformers library: ```bash pip install -U sentence-transformers ``` Then you can load this model and run inference. ```python from sentence_transformers import SentenceTransformer # Download from the 🤗 Hub model = SentenceTransformer("lwoollett/jade-ft-14-bert-static") # Run inference sentences = [ 'Which subclasses are associated with the JadeXMLCharacterData class?', '## JadeXMLCharacterData Class\n\nThe JadeXMLCharacterData class is the abstract superclass of character-based nodes in an XML document tree; that is, the text, CDATA, and comment nodes.\n\nFor details about the property defined in the JadeXMLCharacterData class, see "[JadeXMLCharacterData Property](jadexmlcharacterdata_property.htm)", in the following section.\n\n[JadeXMLNode](../jadexmlnode_class/jadexmlnode_class.htm)\n\n[JadeXMLCDATA](../jadexmlcdata_class/jadexmlcdata_class.htm), [JadeXMLComment](../jadexmlcomment_class/jadexmlcomment_class.htm), [JadeXMLText](../jadexmltext_class/jadexmltext_class.htm)', "### Minimizing the Working Set\n\nIn loops where there are multiple filters, apply the cheapest filters first and then the filters that reduce the working set the most. For example, consider the following code fragment, which finds sales of appliances in a specified city.\n\n```\nwhile iter.next(tran) do\r\n if tran.type = Type_Sale\r\n and tran.myBranch.myLocation.city = targetCity\r\n and tran.myProduct.isAppliance then\r\n <do something with tran>\r\n endif;\r\nendwhile;\n```\nIn this example, tran.type should be checked first, because it is the cheapest. The tran object must be fetched to evaluate all of the other conditions, so we may as well check the type attribute first. If we did the isAppliance check first, we would have to fetch all of the product objects for the transactions that were not sales. Regardless of how many transactions are sales and how many products are appliances, it will save time to check tran.type first.\n\nNow, assume that:\n\n- 80 percent of transactions are sales\n\n- 15 percent, on average, are likely to be in the target city\n\n- 90 percent of the products are appliances\n\nIt pays to check the city first, even though it means fetching the branch and location objects for the non‑appliance products. There are very few non‑appliance products, so the number of extra fetches is small. By contrast, checking for non‑appliance products for all other cities would result in a large number of extra fetches.\n\nIt doesn't matter if the filters are conditions of an [if](../../devref/ch1languageref/if_instruction.htm#if) instruction, multiple [if](../../devref/ch1languageref/if_instruction.htm#if) instructions, or multiple conditions in the [where](../../devref/ch1languageref/where_clause_optimization.htm#whereoptimization) clause of a [while](../../devref/ch1languageref/while_instruction.htm#while) statement; the end result is the same.\n\nThis code fragment example is simple and concise, to convey the concept. In the real world, each successive filter may be in another method, another class, or even another schema. It may take a bit of investigation to find all of the filters involved in a single loop.", ] embeddings = model.encode(sentences) print(embeddings.shape) # [3, 768] # Get the similarity scores for the embeddings similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3] ``` <!-- ### Direct Usage (Transformers) <details><summary>Click to see the direct usage in Transformers</summary> </details> --> <!-- ### Downstream Usage (Sentence Transformers) You can finetune this model on your own dataset. <details><summary>Click to expand</summary> </details> --> <!-- ### Out-of-Scope Use List how the model may foreseeably be misused and address what users ought not to do with the model. --> <!-- ## Bias, Risks and Limitations What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model. --> <!-- ### Recommendations What are recommendations with respect to the foreseeable issues? For example, filtering explicit content. --> ## Training Details ### Training Dataset #### jade_embeddings_train_25.04.04 * Dataset: jade_embeddings_train_25.04.04 * Size: 10,217 training samples * Columns: <code>anchor</code> and <code>positive</code> * Approximate statistics based on the first 1000 samples: \| \| anchor \| positive \| \|:--------\|:----------------------------------------------------------------------------------\|:--------------------------------------------------------------------------------------\| \| type \| string \| string \| \| details \| <ul><li>min: 8 tokens</li><li>mean: 17.17 tokens</li><li>max: 30 tokens</li></ul> \| <ul><li>min: 27 tokens</li><li>mean: 363.15 tokens</li><li>max: 6303 tokens</li></ul> \| * Samples: \| anchor \| positive \| \|:------------------------------------------------------------------------\|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------\| \| <code>What is the format for defining a Byte constant in JADE?</code> \| <code>##### Constant Definition Tips<br><br>When defining a constant value, the value of a constant can be a simple literal value or an expression constructed using literals and other constants. For details about literal types, see "[Literals](../../devref/ch1languageref/literals.htm#literalsexpr)", in Chapter - 1 of the _Developer's Reference_.<br><br>You can define the value for a constant whose primitive type is not a specific literal format by using a typecast of a [String](../../encycloprim/string_type/string_type.htm#string) literal or in the case of a [Byte](../../encycloprim/byte_type/byte_type.htm#byte), a small [Integer](../../encycloprim/integer_type/integer_type.htm#integer) literal, as shown in the examples in the following table.<br><br>\| Primitive Type \| Value Expression \|<br>\| ---- \| ---- \|<br>\| Date \| "31/12/2007".Date \|<br>\| Time \| "14:34:23.123".Time \|<br>\| TimeStamp \| "31/12/2007, 14:34:23:123".TimeStamp \|<br>\| Point \| "1,7".Point \|<br>\| Byte \| 0.Byte \|<br><br>For details about typecasting, see "[Type Casts](../...</code> \| \| <code>How does the replaceFrom__ method handle case sensitivity?</code> \| <code>#### replaceFrom__<br><br>```<br>replaceFrom__(target: String; <br> replacement: String; <br> startIndex: Integer; <br> bIgnoreCase: Boolean): String;<br>```<br>The replaceFrom__ method of the [String](string_type.htm) primitive type replaces only the first occurrence of the substring specified in the target parameter with the substring specified in the replacement parameter, starting from the specified startIndex parameter.<br><br>Case‑sensitivity is ignored if you set the value of the bIgnoreCase parameter to true. Set this parameter to false if you want the substring replacement to be case‑sensitive.<br><br>This method raises exception 1413 (_Index used in string operation is out of bounds_) if the value specified in the startIndex parameter is less than 1 or it is greater than the length of the original string. In addition, it returns the original receiver String if the value specified in the target parameter has a length of zero (*...</code> \| \| <code>What does the global constant Ex_Continue do?</code> \| <code>## Exceptions Category<br><br>The global constants for exceptions are listed in the following table.<br><br>\| Global Constant \| Integer Value \| Description \|<br>\| ---- \| ---- \| ---- \|<br>\| Ex_Abort_Action \| 1 \| Causes the currently executing methods to be aborted. \|<br>\| Ex_Continue \| 0 \| Resumes execution from the next expression after the expression that caused the exception. \|<br>\| Ex_Pass_Back \| -1 \| Passes control back to the prior local exception handler for this type of exception, or if a local handler is not found, a global exception handler for this type of exception. \|<br>\| Ex_Resume_Method_Epilog \| 3 \| Passes control back to the method that armed the exception handler. Execution resumes at the start of the method epilog or at the end of the method if there is no epilog section. Execution resumes at the next statement in the epilog if the exception was raised while executing the epilog. If there were no messages on the execution stack when the handler was armed, the effect of theEx_Resume_Method_Epilog...</code> \| Loss: [<code>CachedMultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cachedmultiplenegativesrankingloss) with these parameters: ```json { "scale": 20.0, "similarity_fct": "cos_sim", "mini_batch_size": 32 } ``` ### Evaluation Dataset #### jade_embeddings_train_25.04.04 * Dataset: jade_embeddings_train_25.04.04 * Size: 1,136 evaluation samples * Columns: <code>anchor</code> and <code>positive</code> * Approximate statistics based on the first 1000 samples: \| \| anchor \| positive \| \|:--------\|:----------------------------------------------------------------------------------\|:--------------------------------------------------------------------------------------\| \| type \| string \| string \| \| details \| <ul><li>min: 8 tokens</li><li>mean: 17.07 tokens</li><li>max: 41 tokens</li></ul> \| <ul><li>min: 25 tokens</li><li>mean: 365.93 tokens</li><li>max: 3397 tokens</li></ul> \| * Samples: \| anchor \| positive \| \|:------------------------------------------------------------------------------------------------------\|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------\| \| <code>What is the keyword list constant value for JADE_SYSTEMVARS?</code> \| <code>### changeKeywords<br><br>```<br>changeKeywords(action: Integer; <br> keywordList: Integer; <br> keywords: String);<br>```<br>The changeKeywords method of the [JadeTextEdit](../control_class/jadetextedit_class.htm) class modifies one or more of the current keyword lists. The keyword lists are used by the current language lexical analyzer to classify the tokens found in the text. For the Jade language, this includes keywords, class names, constant names, and so on.<br><br>The value of the action parameter can be one of the JadeTextEdit class constants listed in the following table.<br><br>\| Class Constant \| Value \| Description \|<br>\| ---- \| ---- \| ---- \|<br>\| KEYWORDS_ADD \| 2 \| Adds the keywords specified in thekeywordsparameter to the list specified in thekeywordListparameter. \|<br>\| KEYWORDS_DELETE \| 3 \| Deletes the words specified in thekeywordsparameter from the list specified in thekeywordListparameter. \|<br>\| KEYWORDS_SET \| 1 \| Clears the list specified in thekeywordListparam...</code> \| \| <code>What should you click to abandon the deletion of a report in JADE?</code> \| <code>#### Delete Report Command<br><br>Use the Delete Report command from the File menu to delete a report.<br><br>To delete a report<br><br>1. Select the Delete Report command from the File menu. The Delete Report dialog, shown in the following image, is then displayed.<br><br>[](../images/reportdelete_feb2022.png)<br><br>2. Select the report that you want to delete from the Report list box or enter the name in the Report name text box.<br><br>3. Filter the list of report names in the Reports list box in one or both of the following ways.<br><br> - To display only those reports that contain that text in their report description, enter text in the Text contains text box. For example, only those reports that mention Pay in their description are displayed if you enter Pay, providing a refined selection list.<br><br> - To display only those reports modified during a specified period, select a last modified period from the Last modified list box. For example, only those reports that were modified in...</code> \| \| <code>What types of objects can be set for the userGroupObject in JadeMultiWorkerTcpTransport?</code> \| <code>#### userGroupObject<br><br>Type: - Object<br><br>The userGroupObject property of the [JadeMultiWorkerTcpTransport](jademultiworkertcptransport_class.htm) class contains a reference to an object that you can associate with the transport group between event callbacks.<br><br>You must set the value of this property to a shared transient or a persistent object, as it must be visible to other workers.<br><br>The default value is null.<br><br>To prevent an object leak, it is your responsibility to delete this object, if required, in your implementation of the [closedEvent](../jademultiworkertcptransportif_interface/closedevent.htm) method in the receiver class.</code> \| * Loss: [<code>CachedMultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cachedmultiplenegativesrankingloss) with these parameters: ```json { "scale": 20.0, "similarity_fct": "cos_sim", "mini_batch_size": 32 } ``` ### Training Hyperparameters #### Non-Default Hyperparameters - `eval_strategy`: steps - `per_device_train_batch_size`: 18 - `per_device_eval_batch_size`: 18 - `num_train_epochs`: 4 - `warmup_ratio`: 0.1 - `bf16`: True - `batch_sampler`: no_duplicates #### All Hyperparameters <details><summary>Click to expand</summary> - `overwrite_output_dir`: False - `do_predict`: False - `eval_strategy`: steps - `prediction_loss_only`: True - `per_device_train_batch_size`: 18 - `per_device_eval_batch_size`: 18 - `per_gpu_train_batch_size`: None - `per_gpu_eval_batch_size`: None - `gradient_accumulation_steps`: 1 - `eval_accumulation_steps`: None - `torch_empty_cache_steps`: None - `learning_rate`: 5e-05 - `weight_decay`: 0.0 - `adam_beta1`: 0.9 - `adam_beta2`: 0.999 - `adam_epsilon`: 1e-08 - `max_grad_norm`: 1.0 - `num_train_epochs`: 4 - `max_steps`: -1 - `lr_scheduler_type`: linear - `lr_scheduler_kwargs`: {} - `warmup_ratio`: 0.1 - `warmup_steps`: 0 - `log_level`: passive - `log_level_replica`: warning - `log_on_each_node`: True - `logging_nan_inf_filter`: True - `save_safetensors`: True - `save_on_each_node`: False - `save_only_model`: False - `restore_callback_states_from_checkpoint`: False - `no_cuda`: False - `use_cpu`: False - `use_mps_device`: False - `seed`: 42 - `data_seed`: None - `jit_mode_eval`: False - `use_ipex`: False - `bf16`: True - `fp16`: False - `fp16_opt_level`: O1 - `half_precision_backend`: auto - `bf16_full_eval`: False - `fp16_full_eval`: False - `tf32`: None - `local_rank`: 0 - `ddp_backend`: None - `tpu_num_cores`: None - `tpu_metrics_debug`: False - `debug`: [] - `dataloader_drop_last`: False - `dataloader_num_workers`: 0 - `dataloader_prefetch_factor`: None - `past_index`: -1 - `disable_tqdm`: False - `remove_unused_columns`: True - `label_names`: None - `load_best_model_at_end`: False - `ignore_data_skip`: False - `fsdp`: [] - `fsdp_min_num_params`: 0 - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False} - `tp_size`: 0 - `fsdp_transformer_layer_cls_to_wrap`: None - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None} - `deepspeed`: None - `label_smoothing_factor`: 0.0 - `optim`: adamw_torch - `optim_args`: None - `adafactor`: False - `group_by_length`: False - `length_column_name`: length - `ddp_find_unused_parameters`: None - `ddp_bucket_cap_mb`: None - `ddp_broadcast_buffers`: False - `dataloader_pin_memory`: True - `dataloader_persistent_workers`: False - `skip_memory_metrics`: True - `use_legacy_prediction_loop`: False - `push_to_hub`: False - `resume_from_checkpoint`: None - `hub_model_id`: None - `hub_strategy`: every_save - `hub_private_repo`: None - `hub_always_push`: False - `gradient_checkpointing`: False - `gradient_checkpointing_kwargs`: None - `include_inputs_for_metrics`: False - `include_for_metrics`: [] - `eval_do_concat_batches`: True - `fp16_backend`: auto - `push_to_hub_model_id`: None - `push_to_hub_organization`: None - `mp_parameters`: - `auto_find_batch_size`: False - `full_determinism`: False - `torchdynamo`: None - `ray_scope`: last - `ddp_timeout`: 1800 - `torch_compile`: False - `torch_compile_backend`: None - `torch_compile_mode`: None - `include_tokens_per_second`: False - `include_num_input_tokens_seen`: False - `neftune_noise_alpha`: None - `optim_target_modules`: None - `batch_eval_metrics`: False - `eval_on_start`: False - `use_liger_kernel`: False - `eval_use_gather_object`: False - `average_tokens_across_devices`: False - `prompts`: None - `batch_sampler`: no_duplicates - `multi_dataset_batch_sampler`: proportional </details> ### Training Logs \| Epoch \| Step \| Training Loss \| Validation Loss \| \|:------:\|:----:\|:-------------:\|:---------------:\| \| 0.1761 \| 100 \| 0.0851 \| 0.0243 \| \| 0.3521 \| 200 \| 0.0262 \| 0.0211 \| \| 0.5282 \| 300 \| 0.0275 \| 0.0217 \| \| 0.7042 \| 400 \| 0.0216 \| 0.0256 \| \| 0.8803 \| 500 \| 0.0283 \| 0.0241 \| \| 1.0563 \| 600 \| 0.0226 \| 0.0195 \| \| 1.2324 \| 700 \| 0.0113 \| 0.0170 \| \| 1.4085 \| 800 \| 0.0114 \| 0.0204 \| \| 1.5845 \| 900 \| 0.0165 \| 0.0182 \| \| 1.7606 \| 1000 \| 0.0129 \| 0.0219 \| \| 1.9366 \| 1100 \| 0.0126 \| 0.0181 \| \| 2.1127 \| 1200 \| 0.0069 \| 0.0207 \| \| 2.2887 \| 1300 \| 0.0045 \| 0.0212 \| \| 2.4648 \| 1400 \| 0.0046 \| 0.0187 \| \| 2.6408 \| 1500 \| 0.0056 \| 0.0206 \| \| 2.8169 \| 1600 \| 0.0084 \| 0.0196 \| \| 2.9930 \| 1700 \| 0.005 \| 0.0214 \| \| 3.1690 \| 1800 \| 0.0056 \| 0.0202 \| \| 3.3451 \| 1900 \| 0.0088 \| 0.0190 \| \| 3.5211 \| 2000 \| 0.0026 \| 0.0202 \| \| 3.6972 \| 2100 \| 0.0064 \| 0.0205 \| \| 3.8732 \| 2200 \| 0.006 \| 0.0202 \| ### Framework Versions - Python: 3.11.11 - Sentence Transformers: 4.0.2 - Transformers: 4.51.0 - PyTorch: 2.8.0.dev20250319+cu128 - Accelerate: 1.6.0 - Datasets: 3.5.0 - Tokenizers: 0.21.1 ## Citation ### BibTeX #### Sentence Transformers ```bibtex @inproceedings{reimers-2019-sentence-bert, title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks", author = "Reimers, Nils and Gurevych, Iryna", booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing", month = "11", year = "2019", publisher = "Association for Computational Linguistics", url = "https://arxiv.org/abs/1908.10084", } ``` #### CachedMultipleNegativesRankingLoss ```bibtex @misc{gao2021scaling, title={Scaling Deep Contrastive Learning Batch Size under Memory Limited Setup}, author={Luyu Gao and Yunyi Zhang and Jiawei Han and Jamie Callan}, year={2021}, eprint={2101.06983}, archivePrefix={arXiv}, primaryClass={cs.LG} } ``` <!-- ## Glossary Clearly define terms in order to be accessible across audiences. --> <!-- ## Model Card Authors Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction. --> <!-- ## Model Card Contact Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors. -->
cucucu666/pray-6.18	cucucu666	2025-06-18T09:25:03Z	0	0	diffusers	[ "diffusers", "text-to-image", "diffusers-training", "lora", "flux", "flux-diffusers", "template:sd-lora", "base_model:black-forest-labs/FLUX.1-Fill-dev", "base_model:adapter:black-forest-labs/FLUX.1-Fill-dev", "license:other", "region:us" ]	text-to-image	2025-06-18T06:48:58Z	--- base_model: black-forest-labs/FLUX.1-Fill-dev library_name: diffusers license: other instance_prompt: labii face, Crayon Shin-chan style, pleading expression, both hands together in a prayer pose, plain white background widget: - text: labii face, Crayon Shin-chan style, pleading expression, both hands together in a prayer pose, plain white background output: url: image_0.png - text: labii face, Crayon Shin-chan style, pleading expression, both hands together in a prayer pose, plain white background output: url: image_1.png - text: labii face, Crayon Shin-chan style, pleading expression, both hands together in a prayer pose, plain white background output: url: image_2.png - text: labii face, Crayon Shin-chan style, pleading expression, both hands together in a prayer pose, plain white background output: url: image_3.png tags: - text-to-image - diffusers-training - diffusers - lora - flux - flux-diffusers - template:sd-lora --- <!-- This model card has been generated automatically according to the information the training script had access to. You should probably proofread and complete it, then remove this comment. --> # Flux-Fill DreamBooth LoRA - cucucu666/pray-6.18 <Gallery /> ## Model description These are cucucu666/pray-6.18 DreamBooth LoRA weights for black-forest-labs/FLUX.1-Fill-dev. The weights were trained using [DreamBooth](https://dreambooth.github.io/) with a custom [Flux diffusers trainer](https://github.com/Sebastian-Zok/FLUX-Fill-LoRa-Training). Was LoRA for the text encoder enabled? False. ## Trigger words You should use `labii face, Crayon Shin-chan style, pleading expression, both hands together in a prayer pose, plain white background` to trigger the image generation. ## Download model [Download the *.safetensors LoRA](cucucu666/pray-6.18/tree/main) in the Files & versions tab. ## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers) ```py from diffusers import AutoPipelineForText2Image import torch pipeline = AutoPipelineForText2Image.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16).to('cuda') pipeline.load_lora_weights('cucucu666/pray-6.18', weight_name='pytorch_lora_weights.safetensors') image = pipeline('labii face, Crayon Shin-chan style, pleading expression, both hands together in a prayer pose, plain white background').images[0] ``` For more details, including weighting, merging and fusing LoRAs, check the [documentation on loading LoRAs in diffusers](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading_adapters) ## License Please adhere to the licensing terms as described [here](https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md). ## Intended uses & limitations #### How to use ```python # TODO: add an example code snippet for running this diffusion pipeline ``` #### Limitations and bias [TODO: provide examples of latent issues and potential remediations] ## Training details [TODO: describe the data used to train the model]
dhadheechi/ppo-CartPole-v1	dhadheechi	2025-06-18T09:23:20Z	0	0	null	[ "tensorboard", "CartPole-v1", "ppo", "deep-reinforcement-learning", "reinforcement-learning", "custom-implementation", "deep-rl-course", "model-index", "region:us" ]	reinforcement-learning	2025-06-18T09:23:01Z	--- tags: - CartPole-v1 - ppo - deep-reinforcement-learning - reinforcement-learning - custom-implementation - deep-rl-course model-index: - name: PPO results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: CartPole-v1 type: CartPole-v1 metrics: - type: mean_reward value: 198.70 +/- 42.86 name: mean_reward verified: false --- # PPO Agent Playing CartPole-v1 This is a trained model of a PPO agent playing CartPole-v1. # Hyperparameters ```python {'exp_name': 'ppo' 'seed': 1 'torch_deterministic': True 'cuda': True 'track': False 'wandb_project_name': 'cleanRL' 'wandb_entity': None 'capture_video': False 'env_id': 'CartPole-v1' 'total_timesteps': 50000 'learning_rate': 0.00025 'num_envs': 4 'num_steps': 128 'anneal_lr': True 'gae': True 'gamma': 0.99 'gae_lambda': 0.95 'num_minibatches': 4 'update_epochs': 4 'norm_adv': True 'clip_coef': 0.2 'clip_vloss': True 'ent_coef': 0.01 'vf_coef': 0.5 'max_grad_norm': 0.5 'target_kl': None 'repo_id': 'dhadheechi/ppo-CartPole-v1' 'batch_size': 512 'minibatch_size': 128} ```
myduy/sft-qwen3-1.7B-base-s920	myduy	2025-06-18T09:14:29Z	0	0	transformers	[ "transformers", "safetensors", "qwen3", "feature-extraction", "arxiv:1910.09700", "text-generation-inference", "endpoints_compatible", "region:us" ]	feature-extraction	2025-06-18T09:12:19Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
hugging-F-a-ce/q-FrozenLake-v1-4x4-yesSlippery	hugging-F-a-ce	2025-06-18T09:10:50Z	0	0	null	[ "FrozenLake-v1-4x4", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]	reinforcement-learning	2025-06-18T09:01:55Z	--- tags: - FrozenLake-v1-4x4 - q-learning - reinforcement-learning - custom-implementation model-index: - name: q-FrozenLake-v1-4x4-yesSlippery results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: FrozenLake-v1-4x4 type: FrozenLake-v1-4x4 metrics: - type: mean_reward value: 0.14 +/- 0.35 name: mean_reward verified: false --- # Q-Learning Agent playing1 FrozenLake-v1 This is a trained model of a Q-Learning agent playing FrozenLake-v1 . ## Usage ```python model = load_from_hub(repo_id="hugging-F-a-ce/q-FrozenLake-v1-4x4-yesSlippery", filename="q-learning.pkl") # Don't forget to check if you need to add additional attributes (is_slippery=False etc) env = gym.make(model["env_id"]) ```
BienThuy/sketch-dog-lora	BienThuy	2025-06-18T09:07:24Z	0	0	diffusers	[ "diffusers", "safetensors", "stable-diffusion", "stable-diffusion-diffusers", "text-to-image", "diffusers-training", "lora", "base_model:stable-diffusion-v1-5/stable-diffusion-v1-5", "base_model:adapter:stable-diffusion-v1-5/stable-diffusion-v1-5", "license:creativeml-openrail-m", "region:us" ]	text-to-image	2025-06-18T07:35:10Z	--- base_model: stable-diffusion-v1-5/stable-diffusion-v1-5 library_name: diffusers license: creativeml-openrail-m inference: true tags: - stable-diffusion - stable-diffusion-diffusers - text-to-image - diffusers - diffusers-training - lora --- <!-- This model card has been generated automatically according to the information the training script had access to. You should probably proofread and complete it, then remove this comment. --> # LoRA text2image fine-tuning - BienThuy/sketch-dog-lora These are LoRA adaption weights for stable-diffusion-v1-5/stable-diffusion-v1-5. The weights were fine-tuned on the zoheb/sketch-scene dataset. You can find some example images in the following. ![img_0](./image_0.png) ![img_1](./image_1.png) ![img_2](./image_2.png) ![img_3](./image_3.png) ## Intended uses & limitations #### How to use ```python # TODO: add an example code snippet for running this diffusion pipeline ``` #### Limitations and bias [TODO: provide examples of latent issues and potential remediations] ## Training details [TODO: describe the data used to train the model]
m1balcerak/energy_matching	m1balcerak	2025-06-18T09:05:44Z	0	1	null	[ "unconditional-image-generation", "dataset:uoft-cs/cifar10", "license:mit", "region:us" ]	unconditional-image-generation	2025-06-17T13:08:00Z	--- license: mit datasets: - uoft-cs/cifar10 pipeline_tag: unconditional-image-generation ---
humendra/chronos-t5-large-fine-tuned-run-28	humendra	2025-06-18T09:03:42Z	0	0	transformers	[ "transformers", "safetensors", "t5", "text2text-generation", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text2text-generation	2025-06-18T09:02:46Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
Florisst/JustidDataSet1	Florisst	2025-06-18T09:01:05Z	0	0	transformers	[ "transformers", "safetensors", "text-generation-inference", "unsloth", "llama", "trl", "en", "license:apache-2.0", "endpoints_compatible", "region:us" ]	null	2025-06-18T09:00:53Z	--- base_model: unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit tags: - text-generation-inference - transformers - unsloth - llama - trl license: apache-2.0 language: - en --- # Uploaded model - Developed by: Florisst - License: apache-2.0 - Finetuned from model : unsloth/llama-3.2-3b-instruct-unsloth-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)
VikramSingh178/models-registery	VikramSingh178	2025-06-18T08:59:08Z	0	0	null	[ "license:apache-2.0", "region:us" ]	null	2025-02-18T18:48:17Z	--- license: apache-2.0 ---
sgonzalezygil/sd-finetuning-dreambooth-v6-2400	sgonzalezygil	2025-06-18T08:49:27Z	0	0	diffusers	[ "diffusers", "safetensors", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "diffusers:StableDiffusionPipeline", "region:us" ]	text-to-image	2025-06-18T08:48:09Z	--- library_name: diffusers --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🧨 diffusers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
trhgquan/visobert-finetune-freezed-24	trhgquan	2025-06-18T08:46:08Z	0	0	transformers	[ "transformers", "safetensors", "xlm-roberta", "text-classification", "vi", "base_model:uitnlp/visobert", "base_model:finetune:uitnlp/visobert", "license:gpl-3.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	2025-06-18T02:34:02Z	--- license: gpl-3.0 language: - vi metrics: - accuracy - f1 base_model: - uitnlp/visobert pipeline_tag: text-classification library_name: transformers ---
bananacha/eesscha	bananacha	2025-06-18T08:45:07Z	0	0	sentence-transformers	[ "sentence-transformers", "safetensors", "roberta", "feature-extraction", "sentence-similarity", "transformers", "autotrain_compatible", "text-embeddings-inference", "endpoints_compatible", "region:us" ]	sentence-similarity	2025-06-18T08:11:47Z	--- library_name: sentence-transformers pipeline_tag: sentence-similarity tags: - sentence-transformers - feature-extraction - sentence-similarity - transformers --- # {MODEL_NAME} This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search. <!--- Describe your model here --> ## Usage (Sentence-Transformers) Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed: ``` pip install -U sentence-transformers ``` Then you can use the model like this: ```python from sentence_transformers import SentenceTransformer sentences = ["This is an example sentence", "Each sentence is converted"] model = SentenceTransformer('{MODEL_NAME}') embeddings = model.encode(sentences) print(embeddings) ``` ## Usage (HuggingFace Transformers) Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings. ```python from transformers import AutoTokenizer, AutoModel import torch #Mean Pooling - Take attention mask into account for correct averaging def mean_pooling(model_output, attention_mask): token_embeddings = model_output[0] #First element of model_output contains all token embeddings input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float() return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9) # Sentences we want sentence embeddings for sentences = ['This is an example sentence', 'Each sentence is converted'] # Load model from HuggingFace Hub tokenizer = AutoTokenizer.from_pretrained('{MODEL_NAME}') model = AutoModel.from_pretrained('{MODEL_NAME}') # Tokenize sentences encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt') # Compute token embeddings with torch.no_grad(): model_output = model(*encoded_input) # Perform pooling. In this case, mean pooling. sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask']) print("Sentence embeddings:") print(sentence_embeddings) ``` ## Evaluation Results <!--- Describe how your model was evaluated --> For an automated evaluation of this model, see the Sentence Embeddings Benchmark: [https://seb.sbert.net](https://seb.sbert.net?model_name={MODEL_NAME}) ## Training The model was trained with the parameters: DataLoader: `sentence_transformers.datasets.NoDuplicatesDataLoader.NoDuplicatesDataLoader` of length 1097 with parameters: ``` {'batch_size': 16} ``` Loss*: `sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss` with parameters: ``` {'scale': 20.0, 'similarity_fct': 'cos_sim'} ``` Parameters of the fit()-Method: ``` { "epochs": 1, "evaluation_steps": 0, "evaluator": "NoneType", "max_grad_norm": 1, "optimizer_class": "<class 'torch.optim.adamw.AdamW'>", "optimizer_params": { "lr": 2e-05 }, "scheduler": "WarmupLinear", "steps_per_epoch": null, "warmup_steps": 100, "weight_decay": 0.01 } ``` ## Full Model Architecture ``` SentenceTransformer( (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: RobertaModel (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True}) ) ``` ## Citing & Authors <!--- Describe where people can find more information -->
victordorian66/final_mistral_attack	victordorian66	2025-06-18T08:41:37Z	0	0	peft	[ "peft", "safetensors", "arxiv:1910.09700", "base_model:mistralai/Mistral-7B-Instruct-v0.3", "base_model:adapter:mistralai/Mistral-7B-Instruct-v0.3", "region:us" ]	null	2025-06-18T08:41:07Z	--- base_model: mistralai/Mistral-7B-Instruct-v0.3 library_name: peft --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed] ### Framework versions - PEFT 0.15.2
SrijitSet99/sarvam-translate-Q4_K_M-GGUF	SrijitSet99	2025-06-18T08:23:51Z	0	0	transformers	[ "transformers", "gguf", "llama-cpp", "gguf-my-repo", "translation", "as", "bn", "brx", "doi", "gom", "gu", "en", "hi", "kn", "ks", "mai", "ml", "mni", "mr", "ne", "or", "pa", "sa", "sat", "sd", "ta", "te", "ur", "base_model:sarvamai/sarvam-translate", "base_model:finetune:sarvamai/sarvam-translate", "license:gpl-3.0", "endpoints_compatible", "region:us" ]	translation	2025-06-18T08:23:39Z	--- library_name: transformers license: gpl-3.0 language: - as - bn - brx - doi - gom - gu - en - hi - kn - ks - mai - ml - mni - mr - ne - or - pa - sa - sat - sd - ta - te - ur base_model: sarvamai/sarvam-translate base_model_relation: finetune pipeline_tag: translation tags: - llama-cpp - gguf-my-repo --- # SrijitSet99/sarvam-translate-Q4_K_M-GGUF This model was converted to GGUF format from [`sarvamai/sarvam-translate`](https://huggingface.co/sarvamai/sarvam-translate) 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/sarvamai/sarvam-translate) for more details on the model. ## Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) ```bash brew install llama.cpp ``` Invoke the llama.cpp server or the CLI. ### CLI: ```bash llama-cli --hf-repo SrijitSet99/sarvam-translate-Q4_K_M-GGUF --hf-file sarvam-translate-q4_k_m.gguf -p "The meaning to life and the universe is" ``` ### Server: ```bash llama-server --hf-repo SrijitSet99/sarvam-translate-Q4_K_M-GGUF --hf-file sarvam-translate-q4_k_m.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. Step 1: Clone llama.cpp from GitHub. ``` git clone https://github.com/ggerganov/llama.cpp ``` Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux). ``` cd llama.cpp && LLAMA_CURL=1 make ``` Step 3: Run inference through the main binary. ``` ./llama-cli --hf-repo SrijitSet99/sarvam-translate-Q4_K_M-GGUF --hf-file sarvam-translate-q4_k_m.gguf -p "The meaning to life and the universe is" ``` or ``` ./llama-server --hf-repo SrijitSet99/sarvam-translate-Q4_K_M-GGUF --hf-file sarvam-translate-q4_k_m.gguf -c 2048 ```
morturr/Llama-2-7b-hf-LOO_headlines-COMB_dadjokes-comb1-seed42-2025-06-18	morturr	2025-06-18T08:18:51Z	0	0	peft	[ "peft", "safetensors", "trl", "sft", "generated_from_trainer", "base_model:meta-llama/Llama-2-7b-hf", "base_model:adapter:meta-llama/Llama-2-7b-hf", "license:llama2", "region:us" ]	null	2025-06-18T08:18:28Z	--- library_name: peft license: llama2 base_model: meta-llama/Llama-2-7b-hf tags: - trl - sft - generated_from_trainer model-index: - name: Llama-2-7b-hf-LOO_headlines-COMB_dadjokes-comb1-seed42-2025-06-18 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # Llama-2-7b-hf-LOO_headlines-COMB_dadjokes-comb1-seed42-2025-06-18 This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on the None dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0003 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 64 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: linear - num_epochs: 2 ### Training results ### Framework versions - PEFT 0.13.2 - Transformers 4.46.1 - Pytorch 2.5.1+cu124 - Datasets 3.0.2 - Tokenizers 0.20.1
hugging-F-a-ce/q-FrozenLake-v1-4x4-noSlippery	hugging-F-a-ce	2025-06-18T08:16:50Z	0	0	null	[ "FrozenLake-v1-4x4-no_slippery", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]	reinforcement-learning	2025-06-18T08:16:47Z	--- tags: - FrozenLake-v1-4x4-no_slippery - q-learning - reinforcement-learning - custom-implementation model-index: - name: q-FrozenLake-v1-4x4-noSlippery results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: FrozenLake-v1-4x4-no_slippery type: FrozenLake-v1-4x4-no_slippery metrics: - type: mean_reward value: 1.00 +/- 0.00 name: mean_reward verified: false --- # Q-Learning Agent playing1 FrozenLake-v1 This is a trained model of a Q-Learning agent playing FrozenLake-v1 . ## Usage ```python model = load_from_hub(repo_id="hugging-F-a-ce/q-FrozenLake-v1-4x4-noSlippery", filename="q-learning.pkl") # Don't forget to check if you need to add additional attributes (is_slippery=False etc) env = gym.make(model["env_id"]) ```
teknium/Llama-3.1-AlternateTokenizer	teknium	2025-06-18T08:15:15Z	1,408	4	transformers	[ "transformers", "safetensors", "llama", "text-generation", "facebook", "meta", "pytorch", "llama-3", "conversational", "en", "de", "fr", "it", "pt", "hi", "es", "th", "arxiv:2204.05149", "license:llama3.1", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-07-23T23:50:37Z	--- language: - en - de - fr - it - pt - hi - es - th pipeline_tag: text-generation tags: - facebook - meta - pytorch - llama - llama-3 license: llama3.1 extra_gated_prompt: >- ### LLAMA 3.1 COMMUNITY LICENSE AGREEMENT Llama 3.1 Version Release Date: July 23, 2024 "Agreement" means the terms and conditions for use, reproduction, distribution and modification of the Llama Materials set forth herein. "Documentation" means the specifications, manuals and documentation accompanying Llama 3.1 distributed by Meta at https://llama.meta.com/doc/overview. "Licensee" or "you" means you, or your employer or any other person or entity (if you are entering into this Agreement on such person or entity’s behalf), of the age required under applicable laws, rules or regulations to provide legal consent and that has legal authority to bind your employer or such other person or entity if you are entering in this Agreement on their behalf. "Llama 3.1" means the foundational large language models and software and algorithms, including machine-learning model code, trained model weights, inference-enabling code, training-enabling code, fine-tuning enabling code and other elements of the foregoing distributed by Meta at https://llama.meta.com/llama-downloads. "Llama Materials" means, collectively, Meta’s proprietary Llama 3.1 and Documentation (and any portion thereof) made available under this Agreement. "Meta" or "we" means Meta Platforms Ireland Limited (if you are located in or, if you are an entity, your principal place of business is in the EEA or Switzerland) and Meta Platforms, Inc. (if you are located outside of the EEA or Switzerland). 1. License Rights and Redistribution. a. Grant of Rights. You are granted a non-exclusive, worldwide, non-transferable and royalty-free limited license under Meta’s intellectual property or other rights owned by Meta embodied in the Llama Materials to use, reproduce, distribute, copy, create derivative works of, and make modifications to the Llama Materials. b. Redistribution and Use. i. If you distribute or make available the Llama Materials (or any derivative works thereof), or a product or service (including another AI model) that contains any of them, you shall (A) provide a copy of this Agreement with any such Llama Materials; and (B) prominently display “Built with Llama” on a related website, user interface, blogpost, about page, or product documentation. If you use the Llama Materials or any outputs or results of the Llama Materials to create, train, fine tune, or otherwise improve an AI model, which is distributed or made available, you shall also include “Llama” at the beginning of any such AI model name. ii. If you receive Llama Materials, or any derivative works thereof, from a Licensee as part of an integrated end user product, then Section 2 of this Agreement will not apply to you. iii. You must retain in all copies of the Llama Materials that you distribute the following attribution notice within a “Notice” text file distributed as a part of such copies: “Llama 3.1 is licensed under the Llama 3.1 Community License, Copyright © Meta Platforms, Inc. All Rights Reserved.” iv. Your use of the Llama Materials must comply with applicable laws and regulations (including trade compliance laws and regulations) and adhere to the Acceptable Use Policy for the Llama Materials (available at https://llama.meta.com/llama3_1/use-policy), which is hereby incorporated by reference into this Agreement. 2. Additional Commercial Terms. If, on the Llama 3.1 version release date, the monthly active users of the products or services made available by or for Licensee, or Licensee’s affiliates, is greater than 700 million monthly active users in the preceding calendar month, you must request a license from Meta, which Meta may grant to you in its sole discretion, and you are not authorized to exercise any of the rights under this Agreement unless or until Meta otherwise expressly grants you such rights. 3. Disclaimer of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS THEREFROM ARE PROVIDED ON AN “AS IS” BASIS, WITHOUT WARRANTIES OF ANY KIND, AND META DISCLAIMS ALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE FOR DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS AND ASSUME ANY RISKS ASSOCIATED WITH YOUR USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS. 4. Limitation of Liability. IN NO EVENT WILL META OR ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS AGREEMENT, FOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN IF META OR ITS AFFILIATES HAVE BEEN ADVISED OF THE POSSIBILITY OF ANY OF THE FOREGOING. 5. Intellectual Property. a. No trademark licenses are granted under this Agreement, and in connection with the Llama Materials, neither Meta nor Licensee may use any name or mark owned by or associated with the other or any of its affiliates, except as required for reasonable and customary use in describing and redistributing the Llama Materials or as set forth in this Section 5(a). Meta hereby grants you a license to use “Llama” (the “Mark”) solely as required to comply with the last sentence of Section 1.b.i. You will comply with Meta’s brand guidelines (currently accessible at https://about.meta.com/brand/resources/meta/company-brand/ ). All goodwill arising out of your use of the Mark will inure to the benefit of Meta. b. Subject to Meta’s ownership of Llama Materials and derivatives made by or for Meta, with respect to any derivative works and modifications of the Llama Materials that are made by you, as between you and Meta, you are and will be the owner of such derivative works and modifications. c. If you institute litigation or other proceedings against Meta or any entity (including a cross-claim or counterclaim in a lawsuit) alleging that the Llama Materials or Llama 3.1 outputs or results, or any portion of any of the foregoing, constitutes infringement of intellectual property or other rights owned or licensable by you, then any licenses granted to you under this Agreement shall terminate as of the date such litigation or claim is filed or instituted. You will indemnify and hold harmless Meta from and against any claim by any third party arising out of or related to your use or distribution of the Llama Materials. 6. Term and Termination. The term of this Agreement will commence upon your acceptance of this Agreement or access to the Llama Materials and will continue in full force and effect until terminated in accordance with the terms and conditions herein. Meta may terminate this Agreement if you are in breach of any term or condition of this Agreement. Upon termination of this Agreement, you shall delete and cease use of the Llama Materials. Sections 3, 4 and 7 shall survive the termination of this Agreement. 7. Governing Law and Jurisdiction. This Agreement will be governed and construed under the laws of the State of California without regard to choice of law principles, and the UN Convention on Contracts for the International Sale of Goods does not apply to this Agreement. The courts of California shall have exclusive jurisdiction of any dispute arising out of this Agreement. ### Llama 3.1 Acceptable Use Policy Meta is committed to promoting safe and fair use of its tools and features, including Llama 3.1. If you access or use Llama 3.1, you agree to this Acceptable Use Policy (“Policy”). The most recent copy of this policy can be found at [https://llama.meta.com/llama3_1/use-policy](https://llama.meta.com/llama3_1/use-policy) #### Prohibited Uses We want everyone to use Llama 3.1 safely and responsibly. You agree you will not use, or allow others to use, Llama 3.1 to: 1. Violate the law or others’ rights, including to: 1. Engage in, promote, generate, contribute to, encourage, plan, incite, or further illegal or unlawful activity or content, such as: 1. Violence or terrorism 2. Exploitation or harm to children, including the solicitation, creation, acquisition, or dissemination of child exploitative content or failure to report Child Sexual Abuse Material 3. Human trafficking, exploitation, and sexual violence 4. The illegal distribution of information or materials to minors, including obscene materials, or failure to employ legally required age-gating in connection with such information or materials. 5. Sexual solicitation 6. Any other criminal activity 3. Engage in, promote, incite, or facilitate the harassment, abuse, threatening, or bullying of individuals or groups of individuals 4. Engage in, promote, incite, or facilitate discrimination or other unlawful or harmful conduct in the provision of employment, employment benefits, credit, housing, other economic benefits, or other essential goods and services 5. Engage in the unauthorized or unlicensed practice of any profession including, but not limited to, financial, legal, medical/health, or related professional practices 6. Collect, process, disclose, generate, or infer health, demographic, or other sensitive personal or private information about individuals without rights and consents required by applicable laws 7. Engage in or facilitate any action or generate any content that infringes, misappropriates, or otherwise violates any third-party rights, including the outputs or results of any products or services using the Llama Materials 8. Create, generate, or facilitate the creation of malicious code, malware, computer viruses or do anything else that could disable, overburden, interfere with or impair the proper working, integrity, operation or appearance of a website or computer system 2. Engage in, promote, incite, facilitate, or assist in the planning or development of activities that present a risk of death or bodily harm to individuals, including use of Llama 3.1 related to the following: 1. Military, warfare, nuclear industries or applications, espionage, use for materials or activities that are subject to the International Traffic Arms Regulations (ITAR) maintained by the United States Department of State 2. Guns and illegal weapons (including weapon development) 3. Illegal drugs and regulated/controlled substances 4. Operation of critical infrastructure, transportation technologies, or heavy machinery 5. Self-harm or harm to others, including suicide, cutting, and eating disorders 6. Any content intended to incite or promote violence, abuse, or any infliction of bodily harm to an individual 3. Intentionally deceive or mislead others, including use of Llama 3.1 related to the following: 1. Generating, promoting, or furthering fraud or the creation or promotion of disinformation 2. Generating, promoting, or furthering defamatory content, including the creation of defamatory statements, images, or other content 3. Generating, promoting, or further distributing spam 4. Impersonating another individual without consent, authorization, or legal right 5. Representing that the use of Llama 3.1 or outputs are human-generated 6. Generating or facilitating false online engagement, including fake reviews and other means of fake online engagement 4. Fail to appropriately disclose to end users any known dangers of your AI system Please report any violation of this Policy, software “bug,” or other problems that could lead to a violation of this Policy through one of the following means: * Reporting issues with the model: [https://github.com/meta-llama/llama-models/issues](https://github.com/meta-llama/llama-models/issues) * Reporting risky content generated by the model: developers.facebook.com/llama_output_feedback * Reporting bugs and security concerns: facebook.com/whitehat/info * Reporting violations of the Acceptable Use Policy or unlicensed uses of Meta Llama 3: [email protected] extra_gated_fields: First Name: text Last Name: text Date of birth: date_picker Country: country Affiliation: text Job title: type: select options: - Student - Research Graduate - AI researcher - AI developer/engineer - Reporter - Other geo: ip_location By clicking Submit below I accept the terms of the license and acknowledge that the information I provide will be collected stored processed and shared in accordance with the Meta Privacy Policy: checkbox extra_gated_description: >- The information you provide will be collected, stored, processed and shared in accordance with the [Meta Privacy Policy](https://www.facebook.com/privacy/policy/). extra_gated_button_content: Submit library_name: transformers --- ## Model Information The Meta Llama 3.1 collection of multilingual large language models (LLMs) is a collection of pretrained and instruction tuned generative models in 8B, 70B and 405B sizes (text in/text out). The Llama 3.1 instruction tuned text only models (8B, 70B, 405B) are optimized for multilingual dialogue use cases and outperform many of the available open source and closed chat models on common industry benchmarks. Model developer: Meta Model Architecture: Llama 3.1 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety. <table> <tr> <td> </td> <td><strong>Training Data</strong> </td> <td><strong>Params</strong> </td> <td><strong>Input modalities</strong> </td> <td><strong>Output modalities</strong> </td> <td><strong>Context length</strong> </td> <td><strong>GQA</strong> </td> <td><strong>Token count</strong> </td> <td><strong>Knowledge cutoff</strong> </td> </tr> <tr> <td rowspan="3" >Llama 3.1 (text only) </td> <td rowspan="3" >A new mix of publicly available online data. </td> <td>8B </td> <td>Multilingual Text </td> <td>Multilingual Text and code </td> <td>128k </td> <td>Yes </td> <td rowspan="3" >15T+ </td> <td rowspan="3" >December 2023 </td> </tr> <tr> <td>70B </td> <td>Multilingual Text </td> <td>Multilingual Text and code </td> <td>128k </td> <td>Yes </td> </tr> <tr> <td>405B </td> <td>Multilingual Text </td> <td>Multilingual Text and code </td> <td>128k </td> <td>Yes </td> </tr> </table> Supported languages: English, German, French, Italian, Portuguese, Hindi, Spanish, and Thai. Llama 3.1 family of models. Token counts refer to pretraining data only. All model versions use Grouped-Query Attention (GQA) for improved inference scalability. Model Release Date: July 23, 2024. Status: This is a static model trained on an offline dataset. Future versions of the tuned models will be released as we improve model safety with community feedback. License: A custom commercial license, the Llama 3.1 Community License, is available at: [https://github.com/meta-llama/llama-models/blob/main/models/llama3_1/LICENSE](https://github.com/meta-llama/llama-models/blob/main/models/llama3_1/LICENSE) Where to send questions or comments about the model Instructions on how to provide feedback or comments on the model can be found in the model [README](https://github.com/meta-llama/llama3). For more technical information about generation parameters and recipes for how to use Llama 3.1 in applications, please go [here](https://github.com/meta-llama/llama-recipes). ## Intended Use Intended Use Cases Llama 3.1 is intended for commercial and research use in multiple languages. Instruction tuned text only models are intended for assistant-like chat, whereas pretrained models can be adapted for a variety of natural language generation tasks. The Llama 3.1 model collection also supports the ability to leverage the outputs of its models to improve other models including synthetic data generation and distillation. The Llama 3.1 Community License allows for these use cases. Out-of-scope Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in any other way that is prohibited by the Acceptable Use Policy and Llama 3.1 Community License. Use in languages beyond those explicitly referenced as supported in this model card. <span style="text-decoration:underline;">Note</span>: Llama 3.1 has been trained on a broader collection of languages than the 8 supported languages. Developers may fine-tune Llama 3.1 models for languages beyond the 8 supported languages provided they comply with the Llama 3.1 Community License and the Acceptable Use Policy and in such cases are responsible for ensuring that any uses of Llama 3.1 in additional languages is done in a safe and responsible manner. ## How to use This repository contains two versions of Meta-Llama-3.1-8B, for use with transformers and with the original `llama` codebase. ### Use with transformers Starting with transformers >= 4.43.0 onward, you can run conversational inference using the Transformers pipeline abstraction or by leveraging the Auto classes with the generate() function. Make sure to update your transformers installation via pip install --upgrade transformers. ```python import transformers import torch model_id = "meta-llama/Meta-Llama-3.1-8B" pipeline = transformers.pipeline( "text-generation", model=model_id, model_kwargs={"torch_dtype": torch.bfloat16}, device_map="auto" ) pipeline("Hey how are you doing today?") ``` ### Use with `llama` Please, follow the instructions in the [repository](https://github.com/meta-llama/llama). To download Original checkpoints, see the example command below leveraging `huggingface-cli`: ``` huggingface-cli download meta-llama/Meta-Llama-3.1-8B --include "original/" --local-dir Meta-Llama-3.1-8B ``` ## Hardware and Software Training Factors* We used custom training libraries, Meta's custom built GPU cluster, and production infrastructure for pretraining. Fine-tuning, annotation, and evaluation were also performed on production infrastructure. Training utilized a cumulative of 39.3M GPU hours of computation on H100-80GB (TDP of 700W) type hardware, per the table below. Training time is the total GPU time required for training each model and power consumption is the peak power capacity per GPU device used, adjusted for power usage efficiency. Training Greenhouse Gas Emissions Estimated total location-based greenhouse gas emissions were 11,390 tons CO2eq for training. Since 2020, Meta has maintained net zero greenhouse gas emissions in its global operations and matched 100% of its electricity use with renewable energy, therefore the total market-based greenhouse gas emissions for training were 0 tons CO2eq. <table> <tr> <td> </td> <td><strong>Training Time (GPU hours)</strong> </td> <td><strong>Training Power Consumption (W)</strong> </td> <td><strong>Training Location-Based Greenhouse Gas Emissions</strong> <p> <strong>(tons CO2eq)</strong> </td> <td><strong>Training Market-Based Greenhouse Gas Emissions</strong> <p> <strong>(tons CO2eq)</strong> </td> </tr> <tr> <td>Llama 3.1 8B </td> <td>1.46M </td> <td>700 </td> <td>420 </td> <td>0 </td> </tr> <tr> <td>Llama 3.1 70B </td> <td>7.0M </td> <td>700 </td> <td>2,040 </td> <td>0 </td> </tr> <tr> <td>Llama 3.1 405B </td> <td>30.84M </td> <td>700 </td> <td>8,930 </td> <td>0 </td> </tr> <tr> <td>Total </td> <td>39.3M <td> <ul> </ul> </td> <td>11,390 </td> <td>0 </td> </tr> </table> The methodology used to determine training energy use and greenhouse gas emissions can be found [here](https://arxiv.org/pdf/2204.05149). Since Meta is openly releasing these models, the training energy use and greenhouse gas emissions will not be incurred by others. ## Training Data Overview: Llama 3.1 was pretrained on ~15 trillion tokens of data from publicly available sources. The fine-tuning data includes publicly available instruction datasets, as well as over 25M synthetically generated examples. Data Freshness: The pretraining data has a cutoff of December 2023. ## Benchmark scores In this section, we report the results for Llama 3.1 models on standard automatic benchmarks. For all the evaluations, we use our internal evaluations library. ### Base pretrained models <table> <tr> <td><strong>Category</strong> </td> <td><strong>Benchmark</strong> </td> <td><strong># Shots</strong> </td> <td><strong>Metric</strong> </td> <td><strong>Llama 3 8B</strong> </td> <td><strong>Llama 3.1 8B</strong> </td> <td><strong>Llama 3 70B</strong> </td> <td><strong>Llama 3.1 70B</strong> </td> <td><strong>Llama 3.1 405B</strong> </td> </tr> <tr> <td rowspan="7" >General </td> <td>MMLU </td> <td>5 </td> <td>macro_avg/acc_char </td> <td>66.7 </td> <td>66.7 </td> <td>79.5 </td> <td>79.3 </td> <td>85.2 </td> </tr> <tr> <td>MMLU-Pro (CoT) </td> <td>5 </td> <td>macro_avg/acc_char </td> <td>36.2 </td> <td>37.1 </td> <td>55.0 </td> <td>53.8 </td> <td>61.6 </td> </tr> <tr> <td>AGIEval English </td> <td>3-5 </td> <td>average/acc_char </td> <td>47.1 </td> <td>47.8 </td> <td>63.0 </td> <td>64.6 </td> <td>71.6 </td> </tr> <tr> <td>CommonSenseQA </td> <td>7 </td> <td>acc_char </td> <td>72.6 </td> <td>75.0 </td> <td>83.8 </td> <td>84.1 </td> <td>85.8 </td> </tr> <tr> <td>Winogrande </td> <td>5 </td> <td>acc_char </td> <td>- </td> <td>60.5 </td> <td>- </td> <td>83.3 </td> <td>86.7 </td> </tr> <tr> <td>BIG-Bench Hard (CoT) </td> <td>3 </td> <td>average/em </td> <td>61.1 </td> <td>64.2 </td> <td>81.3 </td> <td>81.6 </td> <td>85.9 </td> </tr> <tr> <td>ARC-Challenge </td> <td>25 </td> <td>acc_char </td> <td>79.4 </td> <td>79.7 </td> <td>93.1 </td> <td>92.9 </td> <td>96.1 </td> </tr> <tr> <td>Knowledge reasoning </td> <td>TriviaQA-Wiki </td> <td>5 </td> <td>em </td> <td>78.5 </td> <td>77.6 </td> <td>89.7 </td> <td>89.8 </td> <td>91.8 </td> </tr> <tr> <td rowspan="4" >Reading comprehension </td> <td>SQuAD </td> <td>1 </td> <td>em </td> <td>76.4 </td> <td>77.0 </td> <td>85.6 </td> <td>81.8 </td> <td>89.3 </td> </tr> <tr> <td>QuAC (F1) </td> <td>1 </td> <td>f1 </td> <td>44.4 </td> <td>44.9 </td> <td>51.1 </td> <td>51.1 </td> <td>53.6 </td> </tr> <tr> <td>BoolQ </td> <td>0 </td> <td>acc_char </td> <td>75.7 </td> <td>75.0 </td> <td>79.0 </td> <td>79.4 </td> <td>80.0 </td> </tr> <tr> <td>DROP (F1) </td> <td>3 </td> <td>f1 </td> <td>58.4 </td> <td>59.5 </td> <td>79.7 </td> <td>79.6 </td> <td>84.8 </td> </tr> </table> ### Instruction tuned models <table> <tr> <td><strong>Category</strong> </td> <td><strong>Benchmark</strong> </td> <td><strong># Shots</strong> </td> <td><strong>Metric</strong> </td> <td><strong>Llama 3 8B Instruct</strong> </td> <td><strong>Llama 3.1 8B Instruct</strong> </td> <td><strong>Llama 3 70B Instruct</strong> </td> <td><strong>Llama 3.1 70B Instruct</strong> </td> <td><strong>Llama 3.1 405B Instruct</strong> </td> </tr> <tr> <td rowspan="4" >General </td> <td>MMLU </td> <td>5 </td> <td>macro_avg/acc </td> <td>68.5 </td> <td>69.4 </td> <td>82.0 </td> <td>83.6 </td> <td>87.3 </td> </tr> <tr> <td>MMLU (CoT) </td> <td>0 </td> <td>macro_avg/acc </td> <td>65.3 </td> <td>73.0 </td> <td>80.9 </td> <td>86.0 </td> <td>88.6 </td> </tr> <tr> <td>MMLU-Pro (CoT) </td> <td>5 </td> <td>micro_avg/acc_char </td> <td>45.5 </td> <td>48.3 </td> <td>63.4 </td> <td>66.4 </td> <td>73.3 </td> </tr> <tr> <td>IFEval </td> <td> </td> <td> </td> <td>76.8 </td> <td>80.4 </td> <td>82.9 </td> <td>87.5 </td> <td>88.6 </td> </tr> <tr> <td rowspan="2" >Reasoning </td> <td>ARC-C </td> <td>0 </td> <td>acc </td> <td>82.4 </td> <td>83.4 </td> <td>94.4 </td> <td>94.8 </td> <td>96.9 </td> </tr> <tr> <td>GPQA </td> <td>0 </td> <td>em </td> <td>34.6 </td> <td>30.4 </td> <td>39.5 </td> <td>41.7 </td> <td>50.7 </td> </tr> <tr> <td rowspan="4" >Code </td> <td>HumanEval </td> <td>0 </td> <td>pass@1 </td> <td>60.4 </td> <td>72.6 </td> <td>81.7 </td> <td>80.5 </td> <td>89.0 </td> </tr> <tr> <td>MBPP ++ base version </td> <td>0 </td> <td>pass@1 </td> <td>70.6 </td> <td>72.8 </td> <td>82.5 </td> <td>86.0 </td> <td>88.6 </td> </tr> <tr> <td>Multipl-E HumanEval </td> <td>0 </td> <td>pass@1 </td> <td>- </td> <td>50.8 </td> <td>- </td> <td>65.5 </td> <td>75.2 </td> </tr> <tr> <td>Multipl-E MBPP </td> <td>0 </td> <td>pass@1 </td> <td>- </td> <td>52.4 </td> <td>- </td> <td>62.0 </td> <td>65.7 </td> </tr> <tr> <td rowspan="2" >Math </td> <td>GSM-8K (CoT) </td> <td>8 </td> <td>em_maj1@1 </td> <td>80.6 </td> <td>84.5 </td> <td>93.0 </td> <td>95.1 </td> <td>96.8 </td> </tr> <tr> <td>MATH (CoT) </td> <td>0 </td> <td>final_em </td> <td>29.1 </td> <td>51.9 </td> <td>51.0 </td> <td>68.0 </td> <td>73.8 </td> </tr> <tr> <td rowspan="4" >Tool Use </td> <td>API-Bank </td> <td>0 </td> <td>acc </td> <td>48.3 </td> <td>82.6 </td> <td>85.1 </td> <td>90.0 </td> <td>92.0 </td> </tr> <tr> <td>BFCL </td> <td>0 </td> <td>acc </td> <td>60.3 </td> <td>76.1 </td> <td>83.0 </td> <td>84.8 </td> <td>88.5 </td> </tr> <tr> <td>Gorilla Benchmark API Bench </td> <td>0 </td> <td>acc </td> <td>1.7 </td> <td>8.2 </td> <td>14.7 </td> <td>29.7 </td> <td>35.3 </td> </tr> <tr> <td>Nexus (0-shot) </td> <td>0 </td> <td>macro_avg/acc </td> <td>18.1 </td> <td>38.5 </td> <td>47.8 </td> <td>56.7 </td> <td>58.7 </td> </tr> <tr> <td>Multilingual </td> <td>Multilingual MGSM (CoT) </td> <td>0 </td> <td>em </td> <td>- </td> <td>68.9 </td> <td>- </td> <td>86.9 </td> <td>91.6 </td> </tr> </table> #### Multilingual benchmarks <table> <tr> <td><strong>Category</strong> </td> <td><strong>Benchmark</strong> </td> <td><strong>Language</strong> </td> <td><strong>Llama 3.1 8B</strong> </td> <td><strong>Llama 3.1 70B</strong> </td> <td><strong>Llama 3.1 405B</strong> </td> </tr> <tr> <td rowspan="9" ><strong>General</strong> </td> <td rowspan="9" ><strong>MMLU (5-shot, macro_avg/acc)</strong> </td> <td>Portuguese </td> <td>62.12 </td> <td>80.13 </td> <td>84.95 </td> </tr> <tr> <td>Spanish </td> <td>62.45 </td> <td>80.05 </td> <td>85.08 </td> </tr> <tr> <td>Italian </td> <td>61.63 </td> <td>80.4 </td> <td>85.04 </td> </tr> <tr> <td>German </td> <td>60.59 </td> <td>79.27 </td> <td>84.36 </td> </tr> <tr> <td>French </td> <td>62.34 </td> <td>79.82 </td> <td>84.66 </td> </tr> <tr> <td>Hindi </td> <td>50.88 </td> <td>74.52 </td> <td>80.31 </td> </tr> <tr> <td>Thai </td> <td>50.32 </td> <td>72.95 </td> <td>78.21 </td> </tr> </table> ## Responsibility & Safety As part of our Responsible release approach, we followed a three-pronged strategy to managing trust & safety risks: * Enable developers to deploy helpful, safe and flexible experiences for their target audience and for the use cases supported by Llama. * Protect developers against adversarial users aiming to exploit Llama capabilities to potentially cause harm. * Provide protections for the community to help prevent the misuse of our models. ### Responsible deployment Llama is a foundational technology designed to be used in a variety of use cases, examples on how Meta’s Llama models have been responsibly deployed can be found in our [Community Stories webpage](https://llama.meta.com/community-stories/). Our approach is to build the most helpful models enabling the world to benefit from the technology power, by aligning our model safety for the generic use cases addressing a standard set of harms. Developers are then in the driver seat to tailor safety for their use case, defining their own policy and deploying the models with the necessary safeguards in their Llama systems. Llama 3.1 was developed following the best practices outlined in our Responsible Use Guide, you can refer to the [Responsible Use Guide](https://llama.meta.com/responsible-use-guide/) to learn more. #### Llama 3.1 instruct Our main objectives for conducting safety fine-tuning are to provide the research community with a valuable resource for studying the robustness of safety fine-tuning, as well as to offer developers a readily available, safe, and powerful model for various applications to reduce the developer workload to deploy safe AI systems. For more details on the safety mitigations implemented please read the Llama 3 paper. Fine-tuning data We employ a multi-faceted approach to data collection, combining human-generated data from our vendors with synthetic data to mitigate potential safety risks. We’ve developed many large language model (LLM)-based classifiers that enable us to thoughtfully select high-quality prompts and responses, enhancing data quality control. Refusals and Tone Building on the work we started with Llama 3, we put a great emphasis on model refusals to benign prompts as well as refusal tone. We included both borderline and adversarial prompts in our safety data strategy, and modified our safety data responses to follow tone guidelines. #### Llama 3.1 systems Large language models, including Llama 3.1, are not designed to be deployed in isolation but instead should be deployed as part of an overall AI system with additional safety guardrails as required. Developers are expected to deploy system safeguards when building agentic systems. Safeguards are key to achieve the right helpfulness-safety alignment as well as mitigating safety and security risks inherent to the system and any integration of the model or system with external tools. As part of our responsible release approach, we provide the community with [safeguards](https://llama.meta.com/trust-and-safety/) that developers should deploy with Llama models or other LLMs, including Llama Guard 3, Prompt Guard and Code Shield. All our [reference implementations](https://github.com/meta-llama/llama-agentic-system) demos contain these safeguards by default so developers can benefit from system-level safety out-of-the-box. #### New capabilities Note that this release introduces new capabilities, including a longer context window, multilingual inputs and outputs and possible integrations by developers with third party tools. Building with these new capabilities requires specific considerations in addition to the best practices that generally apply across all Generative AI use cases. Tool-use: Just like in standard software development, developers are responsible for the integration of the LLM with the tools and services of their choice. They should define a clear policy for their use case and assess the integrity of the third party services they use to be aware of the safety and security limitations when using this capability. Refer to the Responsible Use Guide for best practices on the safe deployment of the third party safeguards. Multilinguality: Llama 3.1 supports 7 languages in addition to English: French, German, Hindi, Italian, Portuguese, Spanish, and Thai. Llama may be able to output text in other languages than those that meet performance thresholds for safety and helpfulness. We strongly discourage developers from using this model to converse in non-supported languages without implementing finetuning and system controls in alignment with their policies and the best practices shared in the Responsible Use Guide. ### Evaluations We evaluated Llama models for common use cases as well as specific capabilities. Common use cases evaluations measure safety risks of systems for most commonly built applications including chat bot, coding assistant, tool calls. We built dedicated, adversarial evaluation datasets and evaluated systems composed of Llama models and Llama Guard 3 to filter input prompt and output response. It is important to evaluate applications in context, and we recommend building dedicated evaluation dataset for your use case. Prompt Guard and Code Shield are also available if relevant to the application. Capability evaluations measure vulnerabilities of Llama models inherent to specific capabilities, for which were crafted dedicated benchmarks including long context, multilingual, tools calls, coding or memorization. Red teaming For both scenarios, we conducted recurring red teaming exercises with the goal of discovering risks via adversarial prompting and we used the learnings to improve our benchmarks and safety tuning datasets. We partnered early with subject-matter experts in critical risk areas to understand the nature of these real-world harms and how such models may lead to unintended harm for society. Based on these conversations, we derived a set of adversarial goals for the red team to attempt to achieve, such as extracting harmful information or reprogramming the model to act in a potentially harmful capacity. The red team consisted of experts in cybersecurity, adversarial machine learning, responsible AI, and integrity in addition to multilingual content specialists with background in integrity issues in specific geographic markets. ### Critical and other risks We specifically focused our efforts on mitigating the following critical risk areas: 1- CBRNE (Chemical, Biological, Radiological, Nuclear, and Explosive materials) helpfulness To assess risks related to proliferation of chemical and biological weapons, we performed uplift testing designed to assess whether use of Llama 3.1 models could meaningfully increase the capabilities of malicious actors to plan or carry out attacks using these types of weapons. 2. Child Safety Child Safety risk assessments were conducted using a team of experts, to assess the model’s capability to produce outputs that could result in Child Safety risks and inform on any necessary and appropriate risk mitigations via fine tuning. We leveraged those expert red teaming sessions to expand the coverage of our evaluation benchmarks through Llama 3 model development. For Llama 3, we conducted new in-depth sessions using objective based methodologies to assess the model risks along multiple attack vectors including the additional languages Llama 3 is trained on. We also partnered with content specialists to perform red teaming exercises assessing potentially violating content while taking account of market specific nuances or experiences. 3. Cyber attack enablement Our cyber attack uplift study investigated whether LLMs can enhance human capabilities in hacking tasks, both in terms of skill level and speed. Our attack automation study focused on evaluating the capabilities of LLMs when used as autonomous agents in cyber offensive operations, specifically in the context of ransomware attacks. This evaluation was distinct from previous studies that considered LLMs as interactive assistants. The primary objective was to assess whether these models could effectively function as independent agents in executing complex cyber-attacks without human intervention. Our study of Llama-3.1-405B’s social engineering uplift for cyber attackers was conducted to assess the effectiveness of AI models in aiding cyber threat actors in spear phishing campaigns. Please read our Llama 3.1 Cyber security whitepaper to learn more. ### Community Generative AI safety requires expertise and tooling, and we believe in the strength of the open community to accelerate its progress. We are active members of open consortiums, including the AI Alliance, Partnership on AI and MLCommons, actively contributing to safety standardization and transparency. We encourage the community to adopt taxonomies like the MLCommons Proof of Concept evaluation to facilitate collaboration and transparency on safety and content evaluations. Our Purple Llama tools are open sourced for the community to use and widely distributed across ecosystem partners including cloud service providers. We encourage community contributions to our [Github repository](https://github.com/meta-llama/PurpleLlama). We also set up the [Llama Impact Grants](https://llama.meta.com/llama-impact-grants/) program to identify and support the most compelling applications of Meta’s Llama model for societal benefit across three categories: education, climate and open innovation. The 20 finalists from the hundreds of applications can be found [here](https://llama.meta.com/llama-impact-grants/#finalists). Finally, we put in place a set of resources including an [output reporting mechanism](https://developers.facebook.com/llama_output_feedback) and [bug bounty program](https://www.facebook.com/whitehat) to continuously improve the Llama technology with the help of the community. ## Ethical Considerations and Limitations The core values of Llama 3.1 are openness, inclusivity and helpfulness. It is meant to serve everyone, and to work for a wide range of use cases. It is thus designed to be accessible to people across many different backgrounds, experiences and perspectives. Llama 3.1 addresses users and their needs as they are, without insertion unnecessary judgment or normativity, while reflecting the understanding that even content that may appear problematic in some cases can serve valuable purposes in others. It respects the dignity and autonomy of all users, especially in terms of the values of free thought and expression that power innovation and progress. But Llama 3.1 is a new technology, and like any new technology, there are risks associated with its use. Testing conducted to date has not covered, nor could it cover, all scenarios. For these reasons, as with all LLMs, Llama 3.1’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 3.1 models, developers should perform safety testing and tuning tailored to their specific applications of the model. Please refer to available resources including our [Responsible Use Guide](https://llama.meta.com/responsible-use-guide), [Trust and Safety](https://llama.meta.com/trust-and-safety/) solutions, and other [resources](https://llama.meta.com/docs/get-started/) to learn more about responsible development.
Dragon168/llama3.2_3B_news_qlora	Dragon168	2025-06-18T08:08:39Z	0	0	peft	[ "peft", "safetensors", "arxiv:1910.09700", "region:us" ]	null	2025-06-18T07:29:39Z	--- base_model: unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit library_name: peft --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed] ### Framework versions - PEFT 0.15.2
wengti0608/ppo-Pyramid	wengti0608	2025-06-18T08:07:09Z	0	0	ml-agents	[ "ml-agents", "tensorboard", "onnx", "Pyramids", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-Pyramids", "region:us" ]	reinforcement-learning	2025-06-18T08:05:40Z	--- library_name: ml-agents tags: - Pyramids - deep-reinforcement-learning - reinforcement-learning - ML-Agents-Pyramids --- # ppo Agent playing Pyramids This is a trained model of a ppo agent playing Pyramids using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents). ## Usage (with ML-Agents) The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/ We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub: - A short tutorial where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction - A longer tutorial to understand how works ML-Agents: https://huggingface.co/learn/deep-rl-course/unit5/introduction ### Resume the training ```bash mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume ``` ### Watch your Agent play You can watch your agent playing directly in your browser 1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity 2. Step 1: Find your model_id: wengti0608/ppo-Pyramid 3. Step 2: Select your .nn /.onnx file 4. Click on Watch the agent play 👀
ZuluVision/MoviiGen1.1	ZuluVision	2025-06-18T08:06:52Z	1,868	88	diffusers	[ "diffusers", "safetensors", "t2v", "video generation", "text-to-video", "en", "base_model:Wan-AI/Wan2.1-T2V-14B", "base_model:finetune:Wan-AI/Wan2.1-T2V-14B", "license:apache-2.0", "region:us" ]	text-to-video	2025-05-12T12:48:39Z	--- license: apache-2.0 language: - en pipeline_tag: text-to-video tags: - video generation library_name: diffusers base_model: - Wan-AI/Wan2.1-T2V-14B - Wan-AI/Wan2.1-T2V-14B-Diffusers --- # MoviiGen 1.1 <span>[![HuggingFace](https://img.shields.io/badge/🤗%20Hugging%20Face-Model-blue)](https://huggingface.co/ZuluVision/MoviiGen1.1)</span> <span>[![GitHub stars](https://img.shields.io/github/stars/ZulutionAI/MoviiGen1.1?style=social)](https://github.com/ZulutionAI/MoviiGen1.1/stargazers)</span> [MoviiGen 1.1: Towards Cinematic-Quality Video Generative Models](https://github.com/ZulutionAI/MoviiGen1.1) <be> In this repository, we present MoviiGen 1.1, a cutting-edge video generation model that excels in cinematic aesthetics and visual quality. This model is a fine-tuning model based on the Wan2.1. Based on comprehensive evaluations by 11 professional filmmakers and AIGC creators, including industry experts, across 60 aesthetic dimensions, MoviiGen 1.1 demonstrates superior performance in key cinematic aspects: - 👍 Superior Cinematic Aesthetics: MoviiGen 1.1 outperforms competitors in three critical dimensions: atmosphere creation, camera movement, and object detail preservation, making it the preferred choice for professional cinematic applications. - 👍 Visual Coherence & Quality: MoviiGen 1.1 excels in clarity (+14.6%) and realism (+4.3%), making it ideal for high-fidelity scenarios such as real-scene conversion and portrait detail. Wan2.1 stands out in smoothness and overall visual harmony, better suited for tasks emphasizing composition, coherence, and artistic style. Both models have close overall scores, so users can select MoviiGen 1.1 for clarity and realism, or Wan2.1 for style and structural consistency. - 👍 Comprehensive Visual Capabilities: MoviiGen 1.1 provides stable performance in complex visual scenarios, ensuring consistent subject and scene representation while maintaining high-quality motion dynamics. - 👍 High-Quality Output: The model generates videos with exceptional clarity and detail, supporting both 720P and 1080P resolutions while maintaining consistent visual quality throughout the sequence. - 👍 Professional-Grade Results: MoviiGen 1.1 is particularly well-suited for applications where cinematic quality, visual coherence, and aesthetic excellence are paramount, offering superior overall quality compared to other models. This repository features our latest model, which establishes new benchmarks in cinematic video generation. Through extensive evaluation by industry professionals, it has demonstrated exceptional capabilities in creating high-quality visuals with natural motion dynamics and consistent aesthetic quality, making it an ideal choice for professional video production and creative applications. ## Video Demos \| <video width="320" controls><source src="https://huggingface.co/ZuluVision/MoviiGen1.1/resolve/main/assets/79_19201056_seed3732225395.mp4" type="video/mp4">Your browser does not support the video tag.</video> \| <video width="320" controls><source src="https://huggingface.co/ZuluVision/MoviiGen1.1/resolve/main/assets/150_19201056_seed1674457713.mp4" type="video/mp4">Your browser does not support the video tag.</video> \| <video width="320" controls><source src="https://huggingface.co/ZuluVision/MoviiGen1.1/resolve/main/assets/143_19201056_seed3114534932.mp4" type="video/mp4">Your browser does not support the video tag.</video> \| \|--------\|--------\|--------\| \| <video width="320" controls><source src="https://huggingface.co/ZuluVision/MoviiGen1.1/resolve/main/assets/94_19201056_seed3693446494.mp4" type="video/mp4">Your browser does not support the video tag.</video> \| <video width="320" controls><source src="https://huggingface.co/ZuluVision/MoviiGen1.1/resolve/main/assets/23_19201056_seed3934691816.mp4" type="video/mp4">Your browser does not support the video tag.</video> \| <video width="320" controls><source src="https://huggingface.co/ZuluVision/MoviiGen1.1/resolve/main/assets/13_19201056..mp4" type="video/mp4">Your browser does not support the video tag.</video> \| \| <video width="320" controls><source src="https://huggingface.co/ZuluVision/MoviiGen1.1/resolve/main/assets/26_19201056..mp4" type="video/mp4">Your browser does not support the video tag.</video> \| <video width="320" controls><source src="https://huggingface.co/ZuluVision/MoviiGen1.1/resolve/main/assets/39_19201056..mp4" type="video/mp4">Your browser does not support the video tag.</video> \| <video width="320" controls><source src="https://huggingface.co/ZuluVision/MoviiGen1.1/resolve/main/assets/100_19201056_seed2949593166.mp4" type="video/mp4">Your browser does not support the video tag.</video> \| \| <video width="320" controls><source src="https://huggingface.co/ZuluVision/MoviiGen1.1/resolve/main/assets/54_19201056..mp4" type="video/mp4">Your browser does not support the video tag.</video> \| <video width="320" controls><source src="https://huggingface.co/ZuluVision/MoviiGen1.1/resolve/main/assets/107_19201056_seed525896597.mp4" type="video/mp4">Your browser does not support the video tag.</video> \| <video width="320" controls><source src="https://huggingface.co/ZuluVision/MoviiGen1.1/resolve/main/assets/163_19201056_seed3696194034.mp4" type="video/mp4">Your browser does not support the video tag.</video> \| ## 🔥 Latest News!! * May 17, 2025: 👋 We've released the inference code and training code of MoviiGen1.1. * May 12, 2025: 👋 We've released weights of MoviiGen1.1. ## 💡 Quickstart #### Installation Clone the repo: ``` git clone https://github.com/ZulutionAI/MoviiGen1.1.git cd MoviiGen1.1 ``` 1. Install dependencies: ``` # Ensure torch >= 2.4.0 pip install -r requirements.txt ``` 2. Install [FastVideo](https://github.com/hao-ai-lab/FastVideo) according to their instructions. #### Model Download T2V-14B Model: 🤗 [Huggingface](https://huggingface.co/ZuluVision/MoviiGen1.1) MoviiGen1.1 model supports both 720P and 1080P. For more cinematic quality, we recommend using 1080P and a 21:9 aspect ratio (1920832). Download models using huggingface-cli: ``` pip install "huggingface_hub[cli]" huggingface-cli download ZuluVision/MoviiGen1.1 --local-dir ./MoviiGen1.1 ``` ## 🎥 Inference Inference without prompt extend: ```bash PYTHONPATH=. python scripts/inference/generate.py --ckpt_dir ./MoviiGen1.1 --prompt "Inside a smoky, atmospheric private eye office bathed in dramatic film noir lighting, sharp shadows from slatted blinds cut across a cluttered desk and worn surroundings, evoking the classic style by 1940s film. A world-weary detective is sitting behind the desk. He is smoking a cigarette, slowly bringing it to his lips, inhaling, and exhaling a plume of smoke that drifts in the harsh, directional light. The scene is rendered in stark black and white, creating a high-contrast, cinematic mood. The camera holds a static medium shot focused on the detective, emphasizing the gritty texture and oppressive atmosphere." ``` Inference with prompt extend: We provide a prompt extend model for MoviiGen1.1, which is a fine-tuned Qwen2.5-7B-Instruct model with our internal data. Model is available on 🤗 [Huggingface](https://huggingface.co/ZuluVision/MoviiGen1.1_Prompt_Rewriter). ```bash PYTHONPATH=. python scripts/inference/generate.py --ckpt_dir ./MoviiGen1.1 --prompt "A beautiful woman in a red dress is walking on the street." --use_prompt_extend --prompt_extend_model ZuluVision/MoviiGen1.1_Prompt_Rewriter ``` Prompt Tips: - Prompt Length: The prompt length should be around 100~200. - Prompt Content: The prompt should contain scene description, main subject, events, aesthetics description* and camera movement. - Example: ``` Scene Description: A smoky, atmospheric private eye office bathed in dramatic film noir lighting, sharp shadows from slatted blinds cut across a cluttered desk and worn surroundings, evoking the classic style by 1940s film. Main Subject: A world-weary detective is sitting behind the desk. Events: He is smoking a cigarette, slowly bringing it to his lips, inhaling, and exhaling a plume of smoke that drifts in the harsh, directional light. Aesthetics Description: The scene is rendered in stark black and white, creating a high-contrast, cinematic mood. Camera Movement: The camera holds a static medium shot focused on the detective, emphasizing the gritty texture and oppressive atmosphere. Final Prompt: A smoky, atmospheric private eye office bathed in dramatic film noir lighting, sharp shadows from slatted blinds cut across a cluttered desk and worn surroundings, evoking the classic style by 1940s film. A world-weary detective is sitting behind the desk. He is smoking a cigarette, slowly bringing it to his lips, inhaling, and exhaling a plume of smoke that drifts in the harsh, directional light. The scene is rendered in stark black and white, creating a high-contrast, cinematic mood. The camera holds a static medium shot focused on the detective, emphasizing the gritty texture and oppressive atmosphere. ``` ## 🛠️ Training ### Training Framework Our training framework is built on [FastVideo](https://github.com/hao-ai-lab/FastVideo), with custom implementation of sequence parallel to optimize memory usage and training efficiency. The sequence parallel approach allows us to distribute the computational load across multiple GPUs, enabling efficient training of large-scale video generation models. #### Key Features: - Sequence Parallel & Ring Attention: Our custom implementation divides the temporal dimension across multiple GPUs, reducing per-device memory requirements while maintaining model quality. - Efficient Data Loading: Optimized data pipeline for handling high-resolution video frames (Latent Cache and Text Embedding Cache). - Multi Resolution Training Bucket: Support for training at multiple resolutions. - Mixed Precision Training: Support for BF16/FP16 training to accelerate computation. - Distributed Training: Seamless multi-node, multi-GPU training support. ### Data Preprocessing We cache the videos and corresponding text prompts as latents and text embeddings to optimize the training process. This preprocessing step significantly improves training efficiency by reducing computational overhead during the training phase. You need to provide a merge.txt file to specify the dataset path. And the dataset should be a json like training_data.json. Finally, you will get video_caption.json which contains the latents and text embeddings paths. ```bash bash scripts/data_preprocess/preprocess.sh ``` Example Data Format: merge.txt ```txt relative_path_to_json_dir, training_data.json ``` training_data.json ```json [ { "cap": "your prompt", "path": "path/to/your/video.mp4", "resolution": { "width": 3840, "height": 2160 }, "fps": 23.976023976023978, "duration": 1.4180833333333331 }, ... ] ``` Output Json: video_caption.json ```json [ { "latent_path": "path/to/your/latent.pt", "prompt_embed_path": "path/to/your/prompt_embed.pt", "length": 12 }, ... ] ``` ### Train ```bash bash scripts/train/finetune.sh ``` When multi-node training, you need to set the number of nodes and the number of processes per node manually. We provide a sample script for multi-node training. ```bash bash scripts/train/finetune_multi_node.sh ``` ## Citation If you find our work helpful, please cite us. ``` @misc{moviigen2025, title = {MoviiGen 1.1: Towards Cinematic-Quality Video Generative Models}, author = {Yunhao Shui, Benjin Zhu, Xuekuan Wang, Feng Qiu, Yuqiu Huang, Haoyu Zheng, Haoyu Yin, Pengpeng Zhang, Jinru Han, Zhuo Zeng, Yaxin Ding, Helen Xi, Xiang Chen, Jinzhu Li, Liangxian Feng, Xincheng Yin, Bing Wu, Keqiang Sun}, year = {2025}, url = {https://github.com/ZulutionAI/MoviiGen1.1} } ```
Tollring/stt-thai-v1	Tollring	2025-06-18T07:58:13Z	0	0	null	[ "safetensors", "whisper", "license:mit", "region:us" ]	null	2025-06-18T07:56:37Z	--- license: mit --- Step Training Loss Validation Loss Wer 5 0.251500 0.206174 22.150538 10 0.158200 0.153803 19.462366 15 0.096600 0.115016 19.086022 20 0.065700 0.106624 19.139785 Eval metrics: {'eval_loss': 0.1150161400437355, 'eval_wer': 19.086021505376344, 'eval_runtime': 112.8043, 'eval_samples_per_second': 1.87, 'eval_steps_per_second': 0.239, 'epoch': 3.0} Model trained from v-0-3-medium
danijeun/gemma-2-2B-it-thinking-function_calling-V0	danijeun	2025-06-18T07:56:05Z	0	0	transformers	[ "transformers", "tensorboard", "safetensors", "generated_from_trainer", "trl", "sft", "base_model:google/gemma-2-2b-it", "base_model:finetune:google/gemma-2-2b-it", "endpoints_compatible", "region:us" ]	null	2025-05-28T10:29:14Z	--- base_model: google/gemma-2-2b-it library_name: transformers model_name: gemma-2-2B-it-thinking-function_calling-V0 tags: - generated_from_trainer - trl - sft licence: license --- # Model Card for gemma-2-2B-it-thinking-function_calling-V0 This model is a fine-tuned version of [google/gemma-2-2b-it](https://huggingface.co/google/gemma-2-2b-it). It has been trained using [TRL](https://github.com/huggingface/trl). ## Quick start ```python from transformers import pipeline question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?" generator = pipeline("text-generation", model="danijeun/gemma-2-2B-it-thinking-function_calling-V0", device="cuda") output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0] print(output["generated_text"]) ``` ## Training procedure This model was trained with SFT. ### Framework versions - TRL: 0.18.2 - Transformers: 4.52.4 - Pytorch: 2.7.1 - Datasets: 3.6.0 - Tokenizers: 0.21.1 ## Citations Cite TRL as: ```bibtex @misc{vonwerra2022trl, title = {{TRL: Transformer Reinforcement Learning}}, author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec}, year = 2020, journal = {GitHub repository}, publisher = {GitHub}, howpublished = {\url{https://github.com/huggingface/trl}} } ```
morturr/Llama-2-7b-hf-LOO_dadjokes-COMB_headlines-comb1-seed28-2025-06-18	morturr	2025-06-18T07:55:32Z	0	0	peft	[ "peft", "safetensors", "trl", "sft", "generated_from_trainer", "base_model:meta-llama/Llama-2-7b-hf", "base_model:adapter:meta-llama/Llama-2-7b-hf", "license:llama2", "region:us" ]	null	2025-06-18T07:55:15Z	--- library_name: peft license: llama2 base_model: meta-llama/Llama-2-7b-hf tags: - trl - sft - generated_from_trainer model-index: - name: Llama-2-7b-hf-LOO_dadjokes-COMB_headlines-comb1-seed28-2025-06-18 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # Llama-2-7b-hf-LOO_dadjokes-COMB_headlines-comb1-seed28-2025-06-18 This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on the None dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 6e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 28 - gradient_accumulation_steps: 4 - total_train_batch_size: 32 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: linear - num_epochs: 2 ### Training results ### Framework versions - PEFT 0.13.2 - Transformers 4.46.1 - Pytorch 2.5.1+cu124 - Datasets 3.0.2 - Tokenizers 0.20.1
AbderrahmanSkiredj1/GemMaroc-27b-it-GGUF	AbderrahmanSkiredj1	2025-06-18T07:55:27Z	251	0	transformers	[ "transformers", "gguf", "Moroccan", "Darija", "GemMaroc", "GGUF", "conversational", "text-generation", "ary", "en", "ar", "dataset:GemMaroc/TULU-3-50k-darija-english", "arxiv:2505.17082", "base_model:AbderrahmanSkiredj1/GemMaroc-27b-it", "base_model:quantized:AbderrahmanSkiredj1/GemMaroc-27b-it", "endpoints_compatible", "region:us" ]	text-generation	2025-05-22T17:47:29Z	--- base_model: AbderrahmanSkiredj1/GemMaroc-27b-it language: - ary - en - ar library_name: transformers quantized_by: mradermacher datasets: - GemMaroc/TULU-3-50k-darija-english tags: - Moroccan - Darija - GemMaroc - GGUF - conversational pipeline_tag: text-generation --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: --> static quants of https://huggingface.co/AbderrahmanSkiredj1/GemMaroc-27b-it <!-- provided-files --> weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) \| Link \| Type \| Size/GB \| Notes \| \|:-----\|:-----\|--------:\|:------\| \| [GGUF](https://huggingface.co/mradermacher/GemMaroc-27b-it-GGUF/resolve/main/GemMaroc-27b-it.Q2_K.gguf) \| Q2_K \| 10.6 \| \| \| [GGUF](https://huggingface.co/mradermacher/GemMaroc-27b-it-GGUF/resolve/main/GemMaroc-27b-it.Q3_K_S.gguf) \| Q3_K_S \| 12.3 \| \| \| [GGUF](https://huggingface.co/mradermacher/GemMaroc-27b-it-GGUF/resolve/main/GemMaroc-27b-it.Q3_K_M.gguf) \| Q3_K_M \| 13.5 \| lower quality \| \| [GGUF](https://huggingface.co/mradermacher/GemMaroc-27b-it-GGUF/resolve/main/GemMaroc-27b-it.Q3_K_L.gguf) \| Q3_K_L \| 14.6 \| \| \| [GGUF](https://huggingface.co/mradermacher/GemMaroc-27b-it-GGUF/resolve/main/GemMaroc-27b-it.IQ4_XS.gguf) \| IQ4_XS \| 15.0 \| \| \| [GGUF](https://huggingface.co/mradermacher/GemMaroc-27b-it-GGUF/resolve/main/GemMaroc-27b-it.Q4_K_S.gguf) \| Q4_K_S \| 15.8 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/GemMaroc-27b-it-GGUF/resolve/main/GemMaroc-27b-it.Q4_K_M.gguf) \| Q4_K_M \| 16.6 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/GemMaroc-27b-it-GGUF/resolve/main/GemMaroc-27b-it.Q5_K_S.gguf) \| Q5_K_S \| 18.9 \| \| \| [GGUF](https://huggingface.co/mradermacher/GemMaroc-27b-it-GGUF/resolve/main/GemMaroc-27b-it.Q5_K_M.gguf) \| Q5_K_M \| 19.4 \| \| \| [GGUF](https://huggingface.co/mradermacher/GemMaroc-27b-it-GGUF/resolve/main/GemMaroc-27b-it.Q6_K.gguf) \| Q6_K \| 22.3 \| very good quality \| \| [GGUF](https://huggingface.co/mradermacher/GemMaroc-27b-it-GGUF/resolve/main/GemMaroc-27b-it.Q8_0.gguf) \| Q8_0 \| 28.8 \| fast, best quality \| Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 --- # GemMaroc‑27B Unlocking Moroccan Darija proficiency in a state‑of‑the‑art large language model, trained with a minimal‑data, green‑AI recipe that preserves Gemma‑27B’s strong reasoning abilities while adding fluent Darija generation. --- ## Model at a glance \| \| Details \| \| ------------------- \| ----------------------------------------------------------------------------------------------------------------------------- \| \| Model ID \| `AbderrahmanSkiredj1/GemMaroc-27b-it` \| \| Base model \| [`google/gemma-3-27b`](https://huggingface.co/google/gemma-3-27b) \| \| Architecture \| Decoder‑only Transformer (Gemma 3) \| \| Parameters \| 27 billion \| \| Context length \| 2 048 tokens \| \| Training regime \| Supervised fine‑tuning (LoRA → merged) on 50 K high‑quality Darija/English instructions TULU‑50K slice \| \| Compute budget \| 48 GPU·h (8 × H100‑80GB × 6 h) – ≈ 26 kWh / 10 kg CO₂e \| \| License \| Apache 2.0 \| --- ## Why another Darija model? * Inclusive AI > 36 million speakers of Moroccan Arabic remain underserved by open LLMs. * Quality‑over‑quantity A carefully curated 50 K instruction set surfaces Darija competence without sacrificing cross‑lingual reasoning. * Green AI GemMaroc achieves Atlas‑Chat‑level Darija scores using < 2 % of the energy. --- ## Benchmark summary \| Model \| Darija MMLU \| Darija HellaSwag \| GSM8K @5 \| HellaSwag (EN) \| \| ---------------- \| ----------- \| ---------------- \| ---------- \| -------------- \| \| Atlas‑Chat‑27B \| 61.9 % \| 48.4 % \| 82.0 % \| 77.8 % \| \| GemMaroc‑27B \| 61.6 % \| 60.5 % \| 84.2 % \| 79.3 % \| <sub>Zero‑shot accuracy; full table in the paper.</sub> --- ## Quick start ```python from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline model_id = "AbderrahmanSkiredj1/GemMaroc-27b-it" tokenizer = AutoTokenizer.from_pretrained(model_id) model = AutoModelForCausalLM.from_pretrained( model_id, torch_dtype="auto", device_map="auto" ) pipe = pipeline( "text-generation", model=model, tokenizer=tokenizer, device_map="auto", max_new_tokens=1024, temperature=0.7, repetition_penalty=1.2, no_repeat_ngram_size=3, ) messages = [ {"role": "user", "content": "شنو هي نظرية ‘butterfly effect’؟ فسّرها بدارجة ونقّط مثال بسيط."} ] prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) print(pipe(prompt)[0]["generated_text"][len(prompt):]) ``` ### Chat template (Gemma 3 format) The tokenizer provides a baked‑in Jinja template that starts with a begin‑of‑sequence token (`<bos>`), then alternates user/model turns, each wrapped by `<start_of_turn>` … `<end_of_turn>` markers. When you set `add_generation_prompt=True` it ends after the opening model tag so the model can continue: ``` <bos><start_of_turn>user {user message}<end_of_turn> <start_of_turn>model ``` The assistant will keep generating tokens until it decides to emit `<end_of_turn>`. ```python prompt = tokenizer.apply_chat_template(messages, add_generation_prompt=True, tokenize=False) ``` No manual token juggling required—the call above handles BOS, turn delimiters, and newline placement automatically. --- Pre‑quantised checkpoints will be published under the same repo tags (`gemmaroc‑27b‑awq‑int4`, `gemmaroc‑27b‑gguf‑q4_k_m`). --- ## Training recipe (one‑paragraph recap) 1. Data Translate a 44 K reasoning slice of TULU 50K into Darija, keeping 20 % English for cross‑lingual robustness. 2. LoRA SFT Rank 16, α = 32, 3 epochs, bf16, context 2 048. 3. Merge & push Merge LoRA into base weights (`peft.merge_and_unload`), convert to safetensors, upload. --- ## Limitations & ethical considerations * Sentiment and abstractive summarisation still trail state‑of‑the‑art. * Tokeniser is unchanged; rare Darija spellings may fragment. * Model may inherit societal biases present in pre‑training data. * No RLHF / RLAIF safety alignment yet – apply a moderation layer in production. --- ## Citation If you use GemMaroc in your work, please cite: ```bibtex @misc{skiredj2025gemmarocunlockingdarijaproficiency, title={GemMaroc: Unlocking Darija Proficiency in LLMs with Minimal Data}, author={Abderrahman Skiredj and Ferdaous Azhari and Houdaifa Atou and Nouamane Tazi and Ismail Berrada}, year={2025}, eprint={2505.17082}, archivePrefix={arXiv}, primaryClass={cs.CL}, url={https://arxiv.org/abs/2505.17082}, } ``` <!-- end -->
chrishickey/twitter-roberta-base-sentiment-latest	chrishickey	2025-06-18T07:53:57Z	0	0	null	[ "pytorch", "tf", "safetensors", "roberta", "en", "dataset:tweet_eval", "arxiv:2202.03829", "region:us" ]	null	2025-06-18T07:22:02Z	--- language: en widget: - text: Covid cases are increasing fast! datasets: - tweet_eval --- # Twitter-roBERTa-base for Sentiment Analysis - UPDATED (2022) This is a RoBERTa-base model trained on ~124M tweets from January 2018 to December 2021, and finetuned for sentiment analysis with the TweetEval benchmark. The original Twitter-based RoBERTa model can be found [here](https://huggingface.co/cardiffnlp/twitter-roberta-base-2021-124m) and the original reference paper is [TweetEval](https://github.com/cardiffnlp/tweeteval). This model is suitable for English. - Reference Paper: [TimeLMs paper](https://arxiv.org/abs/2202.03829). - Git Repo: [TimeLMs official repository](https://github.com/cardiffnlp/timelms). <b>Labels</b>: 0 -> Negative; 1 -> Neutral; 2 -> Positive This sentiment analysis model has been integrated into [TweetNLP](https://github.com/cardiffnlp/tweetnlp). You can access the demo [here](https://tweetnlp.org). ## Example Pipeline ```python from transformers import pipeline sentiment_task = pipeline("sentiment-analysis", model=model_path, tokenizer=model_path) sentiment_task("Covid cases are increasing fast!") ``` ``` [{'label': 'Negative', 'score': 0.7236}] ``` ## Full classification example ```python from transformers import AutoModelForSequenceClassification from transformers import TFAutoModelForSequenceClassification from transformers import AutoTokenizer, AutoConfig import numpy as np from scipy.special import softmax # Preprocess text (username and link placeholders) def preprocess(text): new_text = [] for t in text.split(" "): t = '@user' if t.startswith('@') and len(t) > 1 else t t = 'http' if t.startswith('http') else t new_text.append(t) return " ".join(new_text) MODEL = f"cardiffnlp/twitter-roberta-base-sentiment-latest" tokenizer = AutoTokenizer.from_pretrained(MODEL) config = AutoConfig.from_pretrained(MODEL) # PT model = AutoModelForSequenceClassification.from_pretrained(MODEL) #model.save_pretrained(MODEL) text = "Covid cases are increasing fast!" text = preprocess(text) encoded_input = tokenizer(text, return_tensors='pt') output = model(**encoded_input) scores = output[0][0].detach().numpy() scores = softmax(scores) # # TF # model = TFAutoModelForSequenceClassification.from_pretrained(MODEL) # model.save_pretrained(MODEL) # text = "Covid cases are increasing fast!" # encoded_input = tokenizer(text, return_tensors='tf') # output = model(encoded_input) # scores = output[0][0].numpy() # scores = softmax(scores) # Print labels and scores ranking = np.argsort(scores) ranking = ranking[::-1] for i in range(scores.shape[0]): l = config.id2label[ranking[i]] s = scores[ranking[i]] print(f"{i+1}) {l} {np.round(float(s), 4)}") ``` Output: ``` 1) Negative 0.7236 2) Neutral 0.2287 3) Positive 0.0477 ``` ### References ``` @inproceedings{camacho-collados-etal-2022-tweetnlp, title = "{T}weet{NLP}: Cutting-Edge Natural Language Processing for Social Media", author = "Camacho-collados, Jose and Rezaee, Kiamehr and Riahi, Talayeh and Ushio, Asahi and Loureiro, Daniel and Antypas, Dimosthenis and Boisson, Joanne and Espinosa Anke, Luis and Liu, Fangyu and Mart{\'\i}nez C{\'a}mara, Eugenio" and others, booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: System Demonstrations", month = dec, year = "2022", address = "Abu Dhabi, UAE", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2022.emnlp-demos.5", pages = "38--49" } ``` ``` @inproceedings{loureiro-etal-2022-timelms, title = "{T}ime{LM}s: Diachronic Language Models from {T}witter", author = "Loureiro, Daniel and Barbieri, Francesco and Neves, Leonardo and Espinosa Anke, Luis and Camacho-collados, Jose", booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics: System Demonstrations", month = may, year = "2022", address = "Dublin, Ireland", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2022.acl-demo.25", doi = "10.18653/v1/2022.acl-demo.25", pages = "251--260" } ```
srinivaspokuri/model1	srinivaspokuri	2025-06-18T07:52:16Z	0	0	transformers	[ "transformers", "safetensors", "bert", "feature-extraction", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	feature-extraction	2025-06-18T07:50:33Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
yullius/finetuned-llama-3.1	yullius	2025-06-18T07:44:27Z	0	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "llama-factory", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-06-17T10:01:52Z	--- library_name: transformers tags: - llama-factory --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
bhavya777/NANONET_CORRECT_V1	bhavya777	2025-06-18T07:43:50Z	0	0	transformers	[ "transformers", "safetensors", "qwen2_5_vl", "image-text-to-text", "text-generation-inference", "unsloth", "conversational", "en", "base_model:nanonets/Nanonets-OCR-s", "base_model:finetune:nanonets/Nanonets-OCR-s", "license:apache-2.0", "endpoints_compatible", "region:us" ]	image-text-to-text	2025-06-18T07:42:35Z	--- base_model: nanonets/Nanonets-OCR-s tags: - text-generation-inference - transformers - unsloth - qwen2_5_vl license: apache-2.0 language: - en --- # Uploaded finetuned model - Developed by: bhavya777 - License: apache-2.0 - Finetuned from model : nanonets/Nanonets-OCR-s This qwen2_5_vl 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)
DevQuasar/Tesslate.UIGEN-T3-4B-Preview-MAX-GGUF	DevQuasar	2025-06-18T07:40:44Z	0	0	null	[ "gguf", "text-generation", "base_model:Tesslate/UIGEN-T3-4B-Preview-MAX", "base_model:quantized:Tesslate/UIGEN-T3-4B-Preview-MAX", "region:us" ]	text-generation	2025-06-18T07:18:39Z	--- base_model: - Tesslate/UIGEN-T3-4B-Preview-MAX pipeline_tag: text-generation --- [<img src="https://raw.githubusercontent.com/csabakecskemeti/devquasar/main/dq_logo_black-transparent.png" width="200"/>](https://devquasar.com) Quantized version of: [Tesslate/UIGEN-T3-4B-Preview-MAX](https://huggingface.co/Tesslate/UIGEN-T3-4B-Preview-MAX) 'Make knowledge free for everyone' <p align="center"> Made with <br> <a href="https://www.civo.com/" target="_blank"> <img src="https://www.civo.com/assets/public/brand-assets/civo-logo-colour-60cc1622dedf346f7afde1fff760523f731b0aac106a5465af98ff4073114b74.svg" width="100"/> </a> </p> <a href='https://ko-fi.com/L4L416YX7C' target='_blank'><img height='36' style='border:0px;height:36px;' src='https://storage.ko-fi.com/cdn/kofi6.png?v=6' border='0' alt='Buy Me a Coffee at ko-fi.com' /></a>
vuitton/21v1scrip_32	vuitton	2025-06-18T07:39:07Z	0	0	null	[ "safetensors", "any-to-any", "omega", "omegalabs", "bittensor", "agi", "license:mit", "region:us" ]	any-to-any	2025-06-16T15:35:00Z	--- license: mit tags: - any-to-any - omega - omegalabs - bittensor - agi --- This is an Any-to-Any model checkpoint for the OMEGA Labs x Bittensor Any-to-Any subnet. Check out the [git repo](https://github.com/omegalabsinc/omegalabs-anytoany-bittensor) and find OMEGA on X: [@omegalabsai](https://x.com/omegalabsai).
mob2711/qwen2.5-7b-qlora-cot-ht-3000	mob2711	2025-06-18T07:35:11Z	0	0	transformers	[ "transformers", "safetensors", "text-generation-inference", "unsloth", "qwen2", "trl", "en", "license:apache-2.0", "endpoints_compatible", "region:us" ]	null	2025-06-18T07:35:02Z	--- base_model: unsloth/qwen2.5-7b-instruct-unsloth-bnb-4bit tags: - text-generation-inference - transformers - unsloth - qwen2 - trl license: apache-2.0 language: - en --- # Uploaded model - Developed by: mob2711 - License: apache-2.0 - Finetuned from model : unsloth/qwen2.5-7b-instruct-unsloth-bnb-4bit This qwen2 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)
RuslanUruzbayev/konstituciya	RuslanUruzbayev	2025-06-18T07:34:46Z	2	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-06-13T07:07:34Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
wizard-chair/flower-doggie	wizard-chair	2025-06-18T07:31:00Z	0	0	null	[ "license:creativeml-openrail-m", "region:us" ]	null	2025-06-18T07:31:00Z	--- license: creativeml-openrail-m ---
HsuHuggingFace/llama3.2_3B_news_qlora	HsuHuggingFace	2025-06-18T07:28:34Z	0	0	null	[ "license:apache-2.0", "region:us" ]	null	2025-06-18T07:28:34Z	--- license: apache-2.0 ---
bananacha/klue-roberta-base-klue-sts	bananacha	2025-06-18T07:26:51Z	0	0	sentence-transformers	[ "sentence-transformers", "safetensors", "roberta", "feature-extraction", "sentence-similarity", "transformers", "autotrain_compatible", "text-embeddings-inference", "endpoints_compatible", "region:us" ]	sentence-similarity	2025-06-18T07:26:33Z	--- library_name: sentence-transformers pipeline_tag: sentence-similarity tags: - sentence-transformers - feature-extraction - sentence-similarity - transformers --- # {MODEL_NAME} This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search. <!--- Describe your model here --> ## Usage (Sentence-Transformers) Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed: ``` pip install -U sentence-transformers ``` Then you can use the model like this: ```python from sentence_transformers import SentenceTransformer sentences = ["This is an example sentence", "Each sentence is converted"] model = SentenceTransformer('{MODEL_NAME}') embeddings = model.encode(sentences) print(embeddings) ``` ## Usage (HuggingFace Transformers) Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings. ```python from transformers import AutoTokenizer, AutoModel import torch #Mean Pooling - Take attention mask into account for correct averaging def mean_pooling(model_output, attention_mask): token_embeddings = model_output[0] #First element of model_output contains all token embeddings input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float() return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9) # Sentences we want sentence embeddings for sentences = ['This is an example sentence', 'Each sentence is converted'] # Load model from HuggingFace Hub tokenizer = AutoTokenizer.from_pretrained('{MODEL_NAME}') model = AutoModel.from_pretrained('{MODEL_NAME}') # Tokenize sentences encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt') # Compute token embeddings with torch.no_grad(): model_output = model(*encoded_input) # Perform pooling. In this case, mean pooling. sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask']) print("Sentence embeddings:") print(sentence_embeddings) ``` ## Evaluation Results <!--- Describe how your model was evaluated --> For an automated evaluation of this model, see the Sentence Embeddings Benchmark: [https://seb.sbert.net](https://seb.sbert.net?model_name={MODEL_NAME}) ## Training The model was trained with the parameters: DataLoader: `torch.utils.data.dataloader.DataLoader` of length 657 with parameters: ``` {'batch_size': 16, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'} ``` Loss*: `sentence_transformers.losses.CosineSimilarityLoss.CosineSimilarityLoss` Parameters of the fit()-Method: ``` { "epochs": 4, "evaluation_steps": 1000, "evaluator": "sentence_transformers.evaluation.EmbeddingSimilarityEvaluator.EmbeddingSimilarityEvaluator", "max_grad_norm": 1, "optimizer_class": "<class 'torch.optim.adamw.AdamW'>", "optimizer_params": { "lr": 2e-05 }, "scheduler": "WarmupLinear", "steps_per_epoch": null, "warmup_steps": 100, "weight_decay": 0.01 } ``` ## Full Model Architecture ``` SentenceTransformer( (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: RobertaModel (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True}) ) ``` ## Citing & Authors <!--- Describe where people can find more information -->
abakirci/admbkrc-turkish-tokenizer	abakirci	2025-06-18T07:26:39Z	0	0	transformers	[ "transformers", "turkish", "tokenizer", "nlp", "tr", "dataset:umarigan/tinystories_tr", "license:apache-2.0", "endpoints_compatible", "region:us" ]	null	2025-06-18T05:03:15Z	--- language: - tr license: apache-2.0 library_name: transformers tags: - turkish - tokenizer - nlp datasets: - umarigan/tinystories_tr --- # Turkish BPE Tokenizer ## Model Description This is a Byte-Pair Encoding (BPE) tokenizer trained specifically for Turkish language. It's designed to be used in Turkish language model pretraining and NLP tasks. Key Features: - Trained on a diverse Turkish text corpus - 50,000 vocabulary size - min_frequency = 2 - Special handling for Turkish characters (ğ, ü, ş, ı, ö, ç) - Added special tokens:[[EOS],[SEP],[UNK], [MASK],[PAD]] ## Intended Uses & Limitations ### How to Use ```python from transformers import AutoTokenizer tokenizer = AutoTokenizer.from_pretrained("abakirci/admbkrc-turkish-tokenizer") text = "Bu bir Türkçe örnek cümledir." encoded = tokenizer(text, return_tensors="pt")
hannell/finbertMY-sentiment	hannell	2025-06-18T07:26:31Z	17	0	transformers	[ "transformers", "safetensors", "bert", "text-classification", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	2025-06-11T17:48:32Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> - 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]
agnedil/Mistral-7B-openassistant-guanaco	agnedil	2025-06-18T07:22:28Z	0	0	null	[ "tensorboard", "safetensors", "region:us" ]	null	2024-03-05T05:48:35Z	Model [Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) fine-tuned on the [openassistant-guanaco](https://huggingface.co/datasets/timdettmers/openassistant-guanaco) dataset using the following [Colab notebook](https://colab.research.google.com/drive/1q7GpzXDlRrvmpCIFWcZg-WLtKcrzFdGn?usp=drive_link).
Steven122333/llama3.2_3B_news_merged	Steven122333	2025-06-18T07:22:18Z	0	0	null	[ "license:apache-2.0", "region:us" ]	null	2025-06-18T07:22:18Z	--- license: apache-2.0 ---
CatchKuo/llama3.2_3B_news_merged	CatchKuo	2025-06-18T07:20:22Z	0	0	null	[ "license:apache-2.0", "region:us" ]	null	2025-06-18T07:20:22Z	--- license: apache-2.0 ---
kopekope/dld4_131_unfinished	kopekope	2025-06-18T07:09:18Z	0	0	diffusers	[ "diffusers", "flux", "lora", "replicate", "text-to-image", "en", "base_model:black-forest-labs/FLUX.1-dev", "base_model:adapter:black-forest-labs/FLUX.1-dev", "license:other", "region:us" ]	text-to-image	2025-06-18T07:04:16Z	--- license: other license_name: flux-1-dev-non-commercial-license license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md language: - en tags: - flux - diffusers - lora - replicate base_model: "black-forest-labs/FLUX.1-dev" pipeline_tag: text-to-image # widget: # - text: >- # prompt # output: # url: https://... instance_prompt: flux_gear_lora --- # Juliayinvert <Gallery /> Trained on Replicate using: https://replicate.com/ostris/flux-dev-lora-trainer/train ## Trigger words You should use `flux_gear_lora` to trigger the image generation. ## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers) ```py from diffusers import AutoPipelineForText2Image import torch pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.float16).to('cuda') pipeline.load_lora_weights('kopekope/dld4_131_unfinished ', weight_name='lora.safetensors') image = pipeline('your prompt').images[0] ``` For more details, including weighting, merging and fusing LoRAs, check the [documentation on loading LoRAs in diffusers](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading_adapters)
souravchaman13/company-name-normalizer	souravchaman13	2025-06-18T07:06:35Z	0	0	transformers	[ "transformers", "safetensors", "t5", "text2text-generation", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text2text-generation	2025-06-18T07:06:19Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
hw33/meta-llama-Llama-3.2-3B-Instruct	hw33	2025-06-18T07:05:00Z	0	0	transformers	[ "transformers", "tensorboard", "safetensors", "generated_from_trainer", "trl", "sft", "base_model:meta-llama/Llama-3.2-3B-Instruct", "base_model:finetune:meta-llama/Llama-3.2-3B-Instruct", "endpoints_compatible", "region:us" ]	null	2025-06-17T08:47:04Z	--- base_model: meta-llama/Llama-3.2-3B-Instruct library_name: transformers model_name: meta-llama-Llama-3.2-3B-Instruct tags: - generated_from_trainer - trl - sft licence: license --- # Model Card for meta-llama-Llama-3.2-3B-Instruct This model is a fine-tuned version of [meta-llama/Llama-3.2-3B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct). It has been trained using [TRL](https://github.com/huggingface/trl). ## Quick start ```python from transformers import pipeline question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?" generator = pipeline("text-generation", model="hw33/meta-llama-Llama-3.2-3B-Instruct", device="cuda") output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0] print(output["generated_text"]) ``` ## Training procedure This model was trained with SFT. ### Framework versions - TRL: 0.15.2 - Transformers: 4.53.0.dev0 - Pytorch: 2.6.0 - Datasets: 3.5.0 - Tokenizers: 0.21.1 ## Citations Cite TRL as: ```bibtex @misc{vonwerra2022trl, title = {{TRL: Transformer Reinforcement Learning}}, author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec}, year = 2020, journal = {GitHub repository}, publisher = {GitHub}, howpublished = {\url{https://github.com/huggingface/trl}} } ```
tartuNLP/Llammas	tartuNLP	2025-06-18T07:02:55Z	1,452	5	transformers	[ "transformers", "pytorch", "safetensors", "llama", "text-generation", "conversational", "et", "en", "arxiv:2404.04042", "base_model:tartuNLP/Llammas-base", "base_model:finetune:tartuNLP/Llammas-base", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2023-11-29T16:13:44Z	--- language: - et - en pipeline_tag: text-generation library_name: transformers tags: - conversational base_model: - tartuNLP/Llammas-base --- #### Update on 26.05.2025 For those interested in building NLP applications for Estonian: Llammas 🐑 is no longer the best open-weight model available for it. For a detailed comparison of open LLMs on Estonian, see our recent [paper](https://aclanthology.org/2025.nodalida-1.37/). For an up-to-date leaderboard of both proprietary and open models, please visit [baromeeter.tartunlp.ai](https://baromeeter.tartunlp.ai) (and consider contributing if you speak Estonian ☺️) # LLammas 🐑 Llama-2-7B instruction-tuned for Estonian in two stages: 1. Continued pre-training: 5B tokens of CulturaX with 75% of documents in Estonain and 25% in English (see [Llammas-base](https://huggingface.co/tartuNLP/Llammas-base)), 2. Instruction-tuning: Alpaca-cleaned, Alpaca-est, OASST1 top-1 English conversations, CoT and FLAN-V2 following open-instruct (both 10,000), WMT18 English-Estonian translation development data (as documents), general MTee validation English-Estonian held-out data. [Alpaca-est](https://github.com/TartuNLP/alpaca-est) is an instruction dataset generated for Estonian with gpt-3.5-turbo-0613, following Alpaca. More details in our [paper](https://arxiv.org/abs/2404.04042). Additional resources: * Paper: [https://aclanthology.org/2024.findings-naacl.210/](https://aclanthology.org/2024.findings-naacl.210/) * Code: [github.com/TartuNLP/llammas](https://github.com/TartuNLP/llammas) * Base model: [tartuNLP/Llammas-base](https://huggingface.co/tartuNLP/Llammas-base) * 4-bit quantized model in GGUF: [AlbertUnn/LlammasGGUF](https://huggingface.co/AlbertUnn/LlammasGGUF) * Alpaca-est dataset: [github.com/TartuNLP/alpaca-est](https://github.com/TartuNLP/alpaca-est) ### Using the model Using the model in a text-generation pipeline: ``` from transformers import pipeline import torch pipe = pipeline("text-generation", model="tartuNLP/Llammas", torch_dtype=torch.bfloat16, device_map="auto") messages = [ {"role": "user", "content": "Tere!"}, {"role": "assistant", "content": "Tere! Kas saaksin teid kuidagi aidata?"}, {"role": "user", "content": "Kuidas alustada kirja kirjutamist?"} ] prompt = pipe.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) outputs = pipe(prompt, max_new_tokens=256, do_sample=True, temperature=0.6, top_k=50, top_p=0.9) print(outputs[0]["generated_text"][len(prompt):]) ``` Using the model in a conversational pipeline (works with transformers==4.36.2, issues with output in newer versions): ``` from transformers import pipeline, Conversation import torch pipe = pipeline("conversational", model="tartuNLP/Llammas", torch_dtype=torch.bfloat16, device_map="auto") messages = [ {"role": "user", "content": "Tere!"}, {"role": "assistant", "content": "Tere! Kas saaksin teid kuidagi aidata?"}, {"role": "user", "content": "Kuidas alustada kirja kirjutamist?"} ] conversation = Conversation(messages) conversation = pipe(conversation) ``` Conversational format: ``` <\|user\|> Tere! <\|assistant\|> Tere! Kas saaksin teid kuidagi aidata?</s> <\|user\|> Kuidas alustada kirja kirjutamist? <\|assistant\|> Kirja kirjutamiseks alustage tervitusega, näiteks "Tere!" või "Tere hommikust!". Seejärel tutvustage ennast ja mainige, kellega kirjutate. Kirjeldage oma mõtteid või küsimusi, mida soovite arutada. Lõpetage kiri viisakalt, näiteks "Tänan teid tähelepanu eest!" või "Parimate soovidega!"</s> ``` ### Citation ``` @inproceedings{kuulmets-etal-2024-teaching, title = "Teaching Llama a New Language Through Cross-Lingual Knowledge Transfer", author = "Kuulmets, Hele-Andra and Purason, Taido and Luhtaru, Agnes and Fishel, Mark", editor = "Duh, Kevin and Gomez, Helena and Bethard, Steven", booktitle = "Findings of the Association for Computational Linguistics: NAACL 2024", month = jun, year = "2024", address = "Mexico City, Mexico", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2024.findings-naacl.210", doi = "10.18653/v1/2024.findings-naacl.210", pages = "3309--3325", abstract = "This paper explores cost-efficient methods to adapt pretrained Large Language Models (LLMs) to new lower-resource languages, with a specific focus on Estonian. Leveraging the Llama 2 model, we investigate the impact of combining cross-lingual instruction-tuning with additional monolingual pretraining. Our results demonstrate that even a relatively small amount of additional monolingual pretraining followed by cross-lingual instruction-tuning significantly enhances results on Estonian. Furthermore, we showcase cross-lingual knowledge transfer from high-quality English instructions to Estonian, resulting in improvements in commonsense reasoning and multi-turn conversation capabilities. Our best model, named Llammas, represents the first open-source instruction-following LLM for Estonian. Additionally, we publish Alpaca-est, the first general task instruction dataset for Estonia. These contributions mark the initial progress in the direction of developing open-source LLMs for Estonian.", } ```
phospho-app/Kai-13-ACT_BBOX-example_dataset_v2-a0d21	phospho-app	2025-06-18T07:00:21Z	0	0	null	[ "phosphobot", "act", "region:us" ]	null	2025-06-18T06:57:45Z	--- tags: - phosphobot - act task_categories: - robotics --- # act Model - phospho Training Pipeline ## Error Traceback We faced an issue while training your model. ``` Training process failed with exit code 1: return forward_call(args, kwargs) File "/lerobot/lerobot/common/policies/act/modeling_act.py", line 425, in forward robot_state_embed = self.vae_encoder_robot_state_input_proj(batch["observation.state"]) File "/opt/conda/envs/lerobot/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1739, in _wrapped_call_impl return self._call_impl(args, *kwargs) File "/opt/conda/envs/lerobot/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1750, in _call_impl return forward_call(args, kwargs) File "/opt/conda/envs/lerobot/lib/python3.10/site-packages/torch/nn/modules/linear.py", line 125, in forward return F.linear(input, self.weight, self.bias) RuntimeError: mat1 and mat2 shapes cannot be multiplied (100x12 and 14x512) ``` ## Training parameters: - Dataset: [phospho-app/example_dataset_v2_bboxes](https://huggingface.co/datasets/phospho-app/example_dataset_v2_bboxes) - Wandb run URL: None - Epochs: None - Batch size: 100 - Training steps: 10000 📖 Get Started: [docs.phospho.ai](https://docs.phospho.ai?utm_source=huggingface_readme) 🤖 Get your robot**: [robots.phospho.ai](https://robots.phospho.ai?utm_source=huggingface_readme)
soundTeam/Q3-8B-Kintsugi_mlx	soundTeam	2025-06-18T06:53:22Z	0	0	mlx	[ "mlx", "safetensors", "qwen3", "mergekit", "axolotl", "unsloth", "roleplay", "conversational", "text-generation", "dataset:PygmalionAI/PIPPA", "dataset:Alfitaria/nemotron-ultra-reasoning-synthkink", "dataset:PocketDoc/Dans-Prosemaxx-Gutenberg", "dataset:FreedomIntelligence/Medical-R1-Distill-Data", "dataset:cognitivecomputations/SystemChat-2.0", "dataset:allenai/tulu-3-sft-personas-instruction-following", "dataset:kalomaze/Opus_Instruct_25k", "dataset:simplescaling/s1K-claude-3-7-sonnet", "dataset:ai2-adapt-dev/flan_v2_converted", "dataset:grimulkan/theory-of-mind", "dataset:grimulkan/physical-reasoning", "dataset:nvidia/HelpSteer3", "dataset:nbeerbower/gutenberg2-dpo", "dataset:nbeerbower/gutenberg-moderne-dpo", "dataset:nbeerbower/Purpura-DPO", "dataset:antiven0m/physical-reasoning-dpo", "dataset:allenai/tulu-3-IF-augmented-on-policy-70b", "dataset:NobodyExistsOnTheInternet/system-message-DPO", "base_model:allura-org/Q3-8B-Kintsugi", "base_model:finetune:allura-org/Q3-8B-Kintsugi", "license:apache-2.0", "region:us" ]	text-generation	2025-06-18T06:52:55Z	--- license: apache-2.0 base_model: allura-org/Q3-8B-Kintsugi library_name: mlx tags: - mergekit - axolotl - unsloth - roleplay - conversational - mlx datasets: - PygmalionAI/PIPPA - Alfitaria/nemotron-ultra-reasoning-synthkink - PocketDoc/Dans-Prosemaxx-Gutenberg - FreedomIntelligence/Medical-R1-Distill-Data - cognitivecomputations/SystemChat-2.0 - allenai/tulu-3-sft-personas-instruction-following - kalomaze/Opus_Instruct_25k - simplescaling/s1K-claude-3-7-sonnet - ai2-adapt-dev/flan_v2_converted - grimulkan/theory-of-mind - grimulkan/physical-reasoning - nvidia/HelpSteer3 - nbeerbower/gutenberg2-dpo - nbeerbower/gutenberg-moderne-dpo - nbeerbower/Purpura-DPO - antiven0m/physical-reasoning-dpo - allenai/tulu-3-IF-augmented-on-policy-70b - NobodyExistsOnTheInternet/system-message-DPO pipeline_tag: text-generation --- # soundTeam/Q3-8B-Kintsugi_mlx This model [soundTeam/Q3-8B-Kintsugi_mlx](https://huggingface.co/soundTeam/Q3-8B-Kintsugi_mlx) was converted to MLX format from [allura-org/Q3-8B-Kintsugi](https://huggingface.co/allura-org/Q3-8B-Kintsugi) using mlx-lm version 0.25.2. ## Use with mlx ```bash pip install mlx-lm ``` ```python from mlx_lm import load, generate model, tokenizer = load("soundTeam/Q3-8B-Kintsugi_mlx") prompt = "hello" if tokenizer.chat_template is not None: messages = [{"role": "user", "content": prompt}] prompt = tokenizer.apply_chat_template( messages, add_generation_prompt=True ) response = generate(model, tokenizer, prompt=prompt, verbose=True) ```
tomaarsen/splade-cocondenser-msmarco-margin-mse-minilm-small-best	tomaarsen	2025-06-18T06:47:32Z	0	0	sentence-transformers	[ "sentence-transformers", "safetensors", "bert", "sparse-encoder", "sparse", "splade", "generated_from_trainer", "dataset_size:90000", "loss:SpladeLoss", "loss:SparseMarginMSELoss", "loss:FlopsLoss", "feature-extraction", "en", "dataset:tomaarsen/msmarco-margin-mse-minilm", "arxiv:1908.10084", "arxiv:2205.04733", "arxiv:2010.02666", "arxiv:2004.05665", "base_model:Luyu/co-condenser-marco", "base_model:finetune:Luyu/co-condenser-marco", "license:apache-2.0", "model-index", "co2_eq_emissions", "autotrain_compatible", "text-embeddings-inference", "endpoints_compatible", "region:us" ]	feature-extraction	2025-06-18T06:47:16Z	--- language: - en license: apache-2.0 tags: - sentence-transformers - sparse-encoder - sparse - splade - generated_from_trainer - dataset_size:90000 - loss:SpladeLoss - loss:SparseMarginMSELoss - loss:FlopsLoss base_model: Luyu/co-condenser-marco widget: - text: weather in ljubljana, slovenia fahrenheit - text: which type of shark is the largest? - text: "Plan to have the farrier reset your horseâ\x80\x99s shoes approximately every\ \ six weeks. The shoes should be shaped to the horseâ\x80\x99s feet for a custom\ \ fit." - text: what oscars was kudo nominated for - text: "Answers from Ronald Petersen, M.D. Yes, Alzheimer's disease usually worsens\ \ slowly. But its speed of progression varies, depending on a person's genetic\ \ makeup, environmental factors, age at diagnosis and other medical conditions.\ \ Still, anyone diagnosed with Alzheimer's whose symptoms seem to be progressing\ \ quickly â\x80\x94 or who experiences a sudden decline â\x80\x94 should see his\ \ or her doctor." datasets: - tomaarsen/msmarco-margin-mse-minilm pipeline_tag: feature-extraction library_name: sentence-transformers metrics: - dot_accuracy@1 - dot_accuracy@3 - dot_accuracy@5 - dot_accuracy@10 - dot_precision@1 - dot_precision@3 - dot_precision@5 - dot_precision@10 - dot_recall@1 - dot_recall@3 - dot_recall@5 - dot_recall@10 - dot_ndcg@10 - dot_mrr@10 - dot_map@100 - query_active_dims - query_sparsity_ratio - corpus_active_dims - corpus_sparsity_ratio co2_eq_emissions: emissions: 83.33408497430837 energy_consumed: 0.21439067711076448 source: codecarbon training_type: fine-tuning on_cloud: false cpu_model: 13th Gen Intel(R) Core(TM) i7-13700K ram_total_size: 31.777088165283203 hours_used: 0.605 hardware_used: 1 x NVIDIA GeForce RTX 3090 model-index: - name: CoCondenser trained on MS MARCO results: - task: type: sparse-information-retrieval name: Sparse Information Retrieval dataset: name: NanoMSMARCO type: NanoMSMARCO metrics: - type: dot_accuracy@1 value: 0.4 name: Dot Accuracy@1 - type: dot_accuracy@3 value: 0.68 name: Dot Accuracy@3 - type: dot_accuracy@5 value: 0.74 name: Dot Accuracy@5 - type: dot_accuracy@10 value: 0.86 name: Dot Accuracy@10 - type: dot_precision@1 value: 0.4 name: Dot Precision@1 - type: dot_precision@3 value: 0.22666666666666668 name: Dot Precision@3 - type: dot_precision@5 value: 0.14800000000000002 name: Dot Precision@5 - type: dot_precision@10 value: 0.08599999999999998 name: Dot Precision@10 - type: dot_recall@1 value: 0.4 name: Dot Recall@1 - type: dot_recall@3 value: 0.68 name: Dot Recall@3 - type: dot_recall@5 value: 0.74 name: Dot Recall@5 - type: dot_recall@10 value: 0.86 name: Dot Recall@10 - type: dot_ndcg@10 value: 0.6263943020229624 name: Dot Ndcg@10 - type: dot_mrr@10 value: 0.5522460317460317 name: Dot Mrr@10 - type: dot_map@100 value: 0.5579041710648882 name: Dot Map@100 - type: query_active_dims value: 20.040000915527344 name: Query Active Dims - type: query_sparsity_ratio value: 0.9993434243851803 name: Query Sparsity Ratio - type: corpus_active_dims value: 157.50286865234375 name: Corpus Active Dims - type: corpus_sparsity_ratio value: 0.9948396937077404 name: Corpus Sparsity Ratio - task: type: sparse-information-retrieval name: Sparse Information Retrieval dataset: name: NanoNFCorpus type: NanoNFCorpus metrics: - type: dot_accuracy@1 value: 0.44 name: Dot Accuracy@1 - type: dot_accuracy@3 value: 0.64 name: Dot Accuracy@3 - type: dot_accuracy@5 value: 0.64 name: Dot Accuracy@5 - type: dot_accuracy@10 value: 0.68 name: Dot Accuracy@10 - type: dot_precision@1 value: 0.44 name: Dot Precision@1 - type: dot_precision@3 value: 0.38666666666666666 name: Dot Precision@3 - type: dot_precision@5 value: 0.332 name: Dot Precision@5 - type: dot_precision@10 value: 0.266 name: Dot Precision@10 - type: dot_recall@1 value: 0.04179623435529923 name: Dot Recall@1 - type: dot_recall@3 value: 0.0965734090873724 name: Dot Recall@3 - type: dot_recall@5 value: 0.11384541136955774 name: Dot Recall@5 - type: dot_recall@10 value: 0.1415418248302823 name: Dot Recall@10 - type: dot_ndcg@10 value: 0.3379998226394541 name: Dot Ndcg@10 - type: dot_mrr@10 value: 0.5286904761904762 name: Dot Mrr@10 - type: dot_map@100 value: 0.1497615336338629 name: Dot Map@100 - type: query_active_dims value: 18.559999465942383 name: Query Active Dims - type: query_sparsity_ratio value: 0.9993919140467223 name: Query Sparsity Ratio - type: corpus_active_dims value: 336.476806640625 name: Corpus Active Dims - type: corpus_sparsity_ratio value: 0.9889759253443213 name: Corpus Sparsity Ratio - task: type: sparse-information-retrieval name: Sparse Information Retrieval dataset: name: NanoNQ type: NanoNQ metrics: - type: dot_accuracy@1 value: 0.48 name: Dot Accuracy@1 - type: dot_accuracy@3 value: 0.76 name: Dot Accuracy@3 - type: dot_accuracy@5 value: 0.84 name: Dot Accuracy@5 - type: dot_accuracy@10 value: 0.88 name: Dot Accuracy@10 - type: dot_precision@1 value: 0.48 name: Dot Precision@1 - type: dot_precision@3 value: 0.26666666666666666 name: Dot Precision@3 - type: dot_precision@5 value: 0.176 name: Dot Precision@5 - type: dot_precision@10 value: 0.092 name: Dot Precision@10 - type: dot_recall@1 value: 0.46 name: Dot Recall@1 - type: dot_recall@3 value: 0.72 name: Dot Recall@3 - type: dot_recall@5 value: 0.8 name: Dot Recall@5 - type: dot_recall@10 value: 0.83 name: Dot Recall@10 - type: dot_ndcg@10 value: 0.6694458425290901 name: Dot Ndcg@10 - type: dot_mrr@10 value: 0.6305 name: Dot Mrr@10 - type: dot_map@100 value: 0.6132918446052669 name: Dot Map@100 - type: query_active_dims value: 22.540000915527344 name: Query Active Dims - type: query_sparsity_ratio value: 0.9992615162533409 name: Query Sparsity Ratio - type: corpus_active_dims value: 199.87527465820312 name: Corpus Active Dims - type: corpus_sparsity_ratio value: 0.9934514358607496 name: Corpus Sparsity Ratio - task: type: sparse-nano-beir name: Sparse Nano BEIR dataset: name: NanoBEIR mean type: NanoBEIR_mean metrics: - type: dot_accuracy@1 value: 0.44 name: Dot Accuracy@1 - type: dot_accuracy@3 value: 0.6933333333333334 name: Dot Accuracy@3 - type: dot_accuracy@5 value: 0.7399999999999999 name: Dot Accuracy@5 - type: dot_accuracy@10 value: 0.8066666666666666 name: Dot Accuracy@10 - type: dot_precision@1 value: 0.44 name: Dot Precision@1 - type: dot_precision@3 value: 0.2933333333333333 name: Dot Precision@3 - type: dot_precision@5 value: 0.21866666666666668 name: Dot Precision@5 - type: dot_precision@10 value: 0.148 name: Dot Precision@10 - type: dot_recall@1 value: 0.30059874478509974 name: Dot Recall@1 - type: dot_recall@3 value: 0.4988578030291242 name: Dot Recall@3 - type: dot_recall@5 value: 0.5512818037898526 name: Dot Recall@5 - type: dot_recall@10 value: 0.6105139416100941 name: Dot Recall@10 - type: dot_ndcg@10 value: 0.5446133223971689 name: Dot Ndcg@10 - type: dot_mrr@10 value: 0.570478835978836 name: Dot Mrr@10 - type: dot_map@100 value: 0.44031918310133933 name: Dot Map@100 - type: query_active_dims value: 20.380000432332356 name: Query Active Dims - type: query_sparsity_ratio value: 0.9993322848950811 name: Query Sparsity Ratio - type: corpus_active_dims value: 214.4328896115101 name: Corpus Active Dims - type: corpus_sparsity_ratio value: 0.992974481042805 name: Corpus Sparsity Ratio --- # CoCondenser trained on MS MARCO This is a [SPLADE Sparse Encoder](https://www.sbert.net/docs/sparse_encoder/usage/usage.html) model finetuned from [Luyu/co-condenser-marco](https://huggingface.co/Luyu/co-condenser-marco) on the [tomaarsen/msmarco-margin-mse-minilm](https://huggingface.co/datasets/tomaarsen/msmarco-margin-mse-minilm) dataset using the [sentence-transformers](https://www.SBERT.net) library. It maps sentences & paragraphs to a 30522-dimensional sparse vector space and can be used for semantic search and sparse retrieval. ## Model Details ### Model Description - Model Type: SPLADE Sparse Encoder - Base model: [Luyu/co-condenser-marco](https://huggingface.co/Luyu/co-condenser-marco) <!-- at revision e0cef0ab2410aae0f0994366ddefb5649a266709 --> - Maximum Sequence Length: 512 tokens - Output Dimensionality: 30522 dimensions - Similarity Function: Dot Product - Training Dataset: - [tomaarsen/msmarco-margin-mse-minilm](https://huggingface.co/datasets/tomaarsen/msmarco-margin-mse-minilm) - Language: en - License: apache-2.0 ### Model Sources - Documentation: [Sentence Transformers Documentation](https://sbert.net) - Documentation: [Sparse Encoder Documentation](https://www.sbert.net/docs/sparse_encoder/usage/usage.html) - Repository: [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers) - Hugging Face: [Sparse Encoders on Hugging Face](https://huggingface.co/models?library=sentence-transformers&other=sparse-encoder) ### Full Model Architecture ``` SparseEncoder( (0): MLMTransformer({'max_seq_length': 512, 'do_lower_case': False}) with MLMTransformer model: BertForMaskedLM (1): SpladePooling({'pooling_strategy': 'max', 'activation_function': 'relu', 'word_embedding_dimension': 30522}) ) ``` ## Usage ### Direct Usage (Sentence Transformers) First install the Sentence Transformers library: ```bash pip install -U sentence-transformers ``` Then you can load this model and run inference. ```python from sentence_transformers import SparseEncoder # Download from the 🤗 Hub model = SparseEncoder("tomaarsen/splade-cocondenser-msmarco-margin-mse-minilm-small-best") # Run inference queries = [ "what causes aging fast", ] documents = [ 'UV-A light, specifically, is what mainly causes tanning, skin aging, and cataracts, UV-B causes sunburn, skin aging and skin cancer, and UV-C is the strongest, and therefore most effective at killing microorganisms. Again â\x80\x93 single words and multiple bullets.', "Answers from Ronald Petersen, M.D. Yes, Alzheimer's disease usually worsens slowly. But its speed of progression varies, depending on a person's genetic makeup, environmental factors, age at diagnosis and other medical conditions. Still, anyone diagnosed with Alzheimer's whose symptoms seem to be progressing quickly â\x80\x94 or who experiences a sudden decline â\x80\x94 should see his or her doctor.", "Bell's palsy and Extreme tiredness and Extreme fatigue (2 causes) Bell's palsy and Extreme tiredness and Hepatitis (2 causes) Bell's palsy and Extreme tiredness and Liver pain (2 causes) Bell's palsy and Extreme tiredness and Lymph node swelling in children (2 causes)", ] query_embeddings = model.encode_query(queries) document_embeddings = model.encode_document(documents) print(query_embeddings.shape, document_embeddings.shape) # [1, 30522] [3, 30522] # Get the similarity scores for the embeddings similarities = model.similarity(query_embeddings, document_embeddings) print(similarities) # tensor([[11.3157, 11.5490, 6.2470]]) ``` <!-- ### Direct Usage (Transformers) <details><summary>Click to see the direct usage in Transformers</summary> </details> --> <!-- ### Downstream Usage (Sentence Transformers) You can finetune this model on your own dataset. <details><summary>Click to expand</summary> </details> --> <!-- ### Out-of-Scope Use List how the model may foreseeably be misused and address what users ought not to do with the model. --> ## Evaluation ### Metrics #### Sparse Information Retrieval * Datasets: `NanoMSMARCO`, `NanoNFCorpus` and `NanoNQ` * Evaluated with [<code>SparseInformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sparse_encoder/evaluation.html#sentence_transformers.sparse_encoder.evaluation.SparseInformationRetrievalEvaluator) \| Metric \| NanoMSMARCO \| NanoNFCorpus \| NanoNQ \| \|:----------------------\|:------------\|:-------------\|:-----------\| \| dot_accuracy@1 \| 0.4 \| 0.44 \| 0.48 \| \| dot_accuracy@3 \| 0.68 \| 0.64 \| 0.76 \| \| dot_accuracy@5 \| 0.74 \| 0.64 \| 0.84 \| \| dot_accuracy@10 \| 0.86 \| 0.68 \| 0.88 \| \| dot_precision@1 \| 0.4 \| 0.44 \| 0.48 \| \| dot_precision@3 \| 0.2267 \| 0.3867 \| 0.2667 \| \| dot_precision@5 \| 0.148 \| 0.332 \| 0.176 \| \| dot_precision@10 \| 0.086 \| 0.266 \| 0.092 \| \| dot_recall@1 \| 0.4 \| 0.0418 \| 0.46 \| \| dot_recall@3 \| 0.68 \| 0.0966 \| 0.72 \| \| dot_recall@5 \| 0.74 \| 0.1138 \| 0.8 \| \| dot_recall@10 \| 0.86 \| 0.1415 \| 0.83 \| \| dot_ndcg@10 \| 0.6264 \| 0.338 \| 0.6694 \| \| dot_mrr@10 \| 0.5522 \| 0.5287 \| 0.6305 \| \| dot_map@100 \| 0.5579 \| 0.1498 \| 0.6133 \| \| query_active_dims \| 20.04 \| 18.56 \| 22.54 \| \| query_sparsity_ratio \| 0.9993 \| 0.9994 \| 0.9993 \| \| corpus_active_dims \| 157.5029 \| 336.4768 \| 199.8753 \| \| corpus_sparsity_ratio \| 0.9948 \| 0.989 \| 0.9935 \| #### Sparse Nano BEIR * Dataset: `NanoBEIR_mean` * Evaluated with [<code>SparseNanoBEIREvaluator</code>](https://sbert.net/docs/package_reference/sparse_encoder/evaluation.html#sentence_transformers.sparse_encoder.evaluation.SparseNanoBEIREvaluator) with these parameters: ```json { "dataset_names": [ "msmarco", "nfcorpus", "nq" ] } ``` \| Metric \| Value \| \|:----------------------\|:-----------\| \| dot_accuracy@1 \| 0.44 \| \| dot_accuracy@3 \| 0.6933 \| \| dot_accuracy@5 \| 0.74 \| \| dot_accuracy@10 \| 0.8067 \| \| dot_precision@1 \| 0.44 \| \| dot_precision@3 \| 0.2933 \| \| dot_precision@5 \| 0.2187 \| \| dot_precision@10 \| 0.148 \| \| dot_recall@1 \| 0.3006 \| \| dot_recall@3 \| 0.4989 \| \| dot_recall@5 \| 0.5513 \| \| dot_recall@10 \| 0.6105 \| \| dot_ndcg@10 \| 0.5446 \| \| dot_mrr@10 \| 0.5705 \| \| dot_map@100 \| 0.4403 \| \| query_active_dims \| 20.38 \| \| query_sparsity_ratio \| 0.9993 \| \| corpus_active_dims \| 214.4329 \| \| corpus_sparsity_ratio \| 0.993 \| <!-- ## Bias, Risks and Limitations What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model. --> <!-- ### Recommendations What are recommendations with respect to the foreseeable issues? For example, filtering explicit content. --> ## Training Details ### Training Dataset #### tomaarsen/msmarco-margin-mse-minilm * Dataset: [tomaarsen/msmarco-margin-mse-minilm](https://huggingface.co/datasets/tomaarsen/msmarco-margin-mse-minilm) * Size: 90,000 training samples * Columns: <code>query</code>, <code>positive</code>, <code>negative</code>, and <code>score</code> * Approximate statistics based on the first 1000 samples: \| \| query \| positive \| negative \| score \| \|:--------\|:---------------------------------------------------------------------------------\|:------------------------------------------------------------------------------------\|:------------------------------------------------------------------------------------\|:--------------------------------------------------------------------\| \| type \| string \| string \| string \| float \| \| details \| <ul><li>min: 4 tokens</li><li>mean: 9.22 tokens</li><li>max: 36 tokens</li></ul> \| <ul><li>min: 15 tokens</li><li>mean: 79.27 tokens</li><li>max: 247 tokens</li></ul> \| <ul><li>min: 16 tokens</li><li>mean: 81.15 tokens</li><li>max: 201 tokens</li></ul> \| <ul><li>min: -14.32</li><li>mean: 4.62</li><li>max: 21.72</li></ul> \| * Samples: \| query \| positive \| negative \| score \| \|:---------------------------------------------\|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------\|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------\|:---------------------------------\| \| <code>most powerful army in the world</code> \| <code>U.S. Army Reserve Command You may be asking yourself, âWhat is the Army Reserve?â The Army is the most powerful and sophisticated military force in the world.</code> \| <code>The British Royal Navy was the most powerful sea-going force by the time of World War 1 (1914-1918) and this was well-underst...</code> \| <code>2.919867515563965</code> \| \| <code>define vasomotor</code> \| <code>Define peripheral neuropathy: a disease or degenerative state of the peripheral nerves in which motor, sensory, or vasomotor nerve fibers may beâ¦ a disease or degenerative state of the peripheral nerves in which motor, sensory, or vasomotor nerve fibers may be affected and which is markedâ¦</code> \| <code>VairÄgya (Devanagari: à¤µà¥à¤°à¤¾à¤à¥à¤¯, also spelt Vairagya) is a Sanskrit term used in Hindu philosophy that roughly translates as dispassion, detachment, or renunciation, in particular renunciation from the pains and pleasures in the material world (Maya).</code> \| <code>3.0037026405334473</code> \| \| <code>nitrates definition biology</code> \| <code>In Botany or Plant Biology. By Photosynthesis, the palisade cells make glucose which has many uses including: storage as starch, to make fat, to make cellulose and to make protein. Glucose is converted wâ¦ith mineral slat nitrates to make the protein. Nitrates provide the essential nitrogen to make protein. The Ribosome, an organelle of the plant cell, manufactures most of the cell's protein.</code> \| <code>Almost all inorganic nitrate salts are soluble in water at standard temperature and pressure. A common example of an inorganic nitrate salt is potassium nitrate (saltpeter). A rich source of inorganic nitrate in the human body comes from diets rich in leafy green foods, such as spinach and arugula.It is now believed that dietary nitrate in the form of plant-based foods is converted in the body to nitrite.itrate is a polyatomic ion with the molecular formula NO 3 â and a molecular mass of 62.0049 g/mol.</code> \| <code>-1.6804794073104858</code> \| * Loss: [<code>SpladeLoss</code>](https://sbert.net/docs/package_reference/sparse_encoder/losses.html#spladeloss) with these parameters: ```json { "loss": "SparseMarginMSELoss", "lambda_corpus": 0.08, "lambda_query": 0.08 } ``` ### Evaluation Dataset #### Unnamed Dataset * Size: 10,000 evaluation samples * Columns: <code>query</code>, <code>positive</code>, <code>negative</code>, and <code>score</code> * Approximate statistics based on the first 1000 samples: \| \| query \| positive \| negative \| score \| \|:--------\|:---------------------------------------------------------------------------------\|:-----------------------------------------------------------------------------------\|:-----------------------------------------------------------------------------------\|:-------------------------------------------------------------------\| \| type \| string \| string \| string \| float \| \| details \| <ul><li>min: 4 tokens</li><li>mean: 9.01 tokens</li><li>max: 35 tokens</li></ul> \| <ul><li>min: 17 tokens</li><li>mean: 79.8 tokens</li><li>max: 336 tokens</li></ul> \| <ul><li>min: 18 tokens</li><li>mean: 81.3 tokens</li><li>max: 273 tokens</li></ul> \| <ul><li>min: -15.9</li><li>mean: 4.91</li><li>max: 21.67</li></ul> \| * Samples: \| query \| positive \| negative \| score \| \|:----------------------------------------------------------\|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------\|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------\|:---------------------------------\| \| <code>femoral artery definition</code> \| <code>medical Definition of circumflex artery : any of several paired curving arteries: as a: either of two arteries that branch from the deep femoral artery or from the femoral artery itself:</code> \| <code>Femoral vein. The femoral vein is located in the upper thigh and pelvic region of the human body. It travels in close proximity to the femoral artery. This vein is one of the larger vessels in the venous system. Instead of draining deoxygenated blood from specific parts of the body, it receives blood from several significant branches. These include popliteal, the profunda femoris, and the great sapheneous veins.</code> \| <code>-0.1968388557434082</code> \| \| <code>what causes mastitis and how do you treat it</code> \| <code>Mastitis is an infection of the tissue of the breast that occurs most frequently during the time of breastfeeding. This infection causes pain, swelling, redness, and increased temperature of the breast. It can occur when bacteria, often from the infant's mouth, enter a milk duct through a crack in the nipple. This causes an infection and painful inflammation of the breast.</code> \| <code>Common causes of mastitis include bacteria from the babyâs mouth, bacteria entering via breast injuries (bruising, fissures, cracks in the nipple), milk stasis (milk pooling in the breast), and bacteria from the hands of the mother or health care provider.</code> \| <code>-0.8143405914306641</code> \| \| <code>what is a buck moth</code> \| <code>Buck moth caterpillars that have a light background color can be confused with both the Nevada buck moth, Hemileuca nevadensis Stretch, and the New England buck moth, Hemileuca lucina Henry Edwards. The larvae of these three species can best be distinguished based on the preferred host plants (Wagner 2005).hey rely on resources that are acquired by the caterpillars (larvae). The caterpillars are robust and can exceed four inches (10 cm) in North America. Figure 4. Adult cecropia moth, Hyalophora cecropia (Linnaeus). Photograph by Pennsylvania Department of Conservation and Natural Resources-Forestry Archive, Bugwood.org.</code> \| <code>bucktail that gets talked about quietly in the . privacy of remote cabins. The âMusky-Teerâ is a big fish bait that anglers treasure in their collection. You wonât find these at your local bait shop but weâve been stocking these highly prized baits in all colors for years.</code> \| <code>11.004357814788818</code> \| * Loss: [<code>SpladeLoss</code>](https://sbert.net/docs/package_reference/sparse_encoder/losses.html#spladeloss) with these parameters: ```json { "loss": "SparseMarginMSELoss", "lambda_corpus": 0.08, "lambda_query": 0.08 } ``` ### Training Hyperparameters #### Non-Default Hyperparameters - `eval_strategy`: steps - `per_device_train_batch_size`: 16 - `per_device_eval_batch_size`: 16 - `learning_rate`: 2e-05 - `num_train_epochs`: 1 - `warmup_ratio`: 0.1 - `fp16`: True - `load_best_model_at_end`: True - `batch_sampler`: no_duplicates #### All Hyperparameters <details><summary>Click to expand</summary> - `overwrite_output_dir`: False - `do_predict`: False - `eval_strategy`: steps - `prediction_loss_only`: True - `per_device_train_batch_size`: 16 - `per_device_eval_batch_size`: 16 - `per_gpu_train_batch_size`: None - `per_gpu_eval_batch_size`: None - `gradient_accumulation_steps`: 1 - `eval_accumulation_steps`: None - `torch_empty_cache_steps`: None - `learning_rate`: 2e-05 - `weight_decay`: 0.0 - `adam_beta1`: 0.9 - `adam_beta2`: 0.999 - `adam_epsilon`: 1e-08 - `max_grad_norm`: 1.0 - `num_train_epochs`: 1 - `max_steps`: -1 - `lr_scheduler_type`: linear - `lr_scheduler_kwargs`: {} - `warmup_ratio`: 0.1 - `warmup_steps`: 0 - `log_level`: passive - `log_level_replica`: warning - `log_on_each_node`: True - `logging_nan_inf_filter`: True - `save_safetensors`: True - `save_on_each_node`: False - `save_only_model`: False - `restore_callback_states_from_checkpoint`: False - `no_cuda`: False - `use_cpu`: False - `use_mps_device`: False - `seed`: 42 - `data_seed`: None - `jit_mode_eval`: False - `use_ipex`: False - `bf16`: False - `fp16`: True - `fp16_opt_level`: O1 - `half_precision_backend`: auto - `bf16_full_eval`: False - `fp16_full_eval`: False - `tf32`: None - `local_rank`: 0 - `ddp_backend`: None - `tpu_num_cores`: None - `tpu_metrics_debug`: False - `debug`: [] - `dataloader_drop_last`: False - `dataloader_num_workers`: 0 - `dataloader_prefetch_factor`: None - `past_index`: -1 - `disable_tqdm`: False - `remove_unused_columns`: True - `label_names`: None - `load_best_model_at_end`: True - `ignore_data_skip`: False - `fsdp`: [] - `fsdp_min_num_params`: 0 - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False} - `fsdp_transformer_layer_cls_to_wrap`: None - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None} - `deepspeed`: None - `label_smoothing_factor`: 0.0 - `optim`: adamw_torch - `optim_args`: None - `adafactor`: False - `group_by_length`: False - `length_column_name`: length - `ddp_find_unused_parameters`: None - `ddp_bucket_cap_mb`: None - `ddp_broadcast_buffers`: False - `dataloader_pin_memory`: True - `dataloader_persistent_workers`: False - `skip_memory_metrics`: True - `use_legacy_prediction_loop`: False - `push_to_hub`: False - `resume_from_checkpoint`: None - `hub_model_id`: None - `hub_strategy`: every_save - `hub_private_repo`: None - `hub_always_push`: False - `gradient_checkpointing`: False - `gradient_checkpointing_kwargs`: None - `include_inputs_for_metrics`: False - `include_for_metrics`: [] - `eval_do_concat_batches`: True - `fp16_backend`: auto - `push_to_hub_model_id`: None - `push_to_hub_organization`: None - `mp_parameters`: - `auto_find_batch_size`: False - `full_determinism`: False - `torchdynamo`: None - `ray_scope`: last - `ddp_timeout`: 1800 - `torch_compile`: False - `torch_compile_backend`: None - `torch_compile_mode`: None - `include_tokens_per_second`: False - `include_num_input_tokens_seen`: False - `neftune_noise_alpha`: None - `optim_target_modules`: None - `batch_eval_metrics`: False - `eval_on_start`: False - `use_liger_kernel`: False - `eval_use_gather_object`: False - `average_tokens_across_devices`: False - `prompts`: None - `batch_sampler`: no_duplicates - `multi_dataset_batch_sampler`: proportional - `router_mapping`: {} - `learning_rate_mapping`: {} </details> ### Training Logs \| Epoch \| Step \| Training Loss \| Validation Loss \| NanoMSMARCO_dot_ndcg@10 \| NanoNFCorpus_dot_ndcg@10 \| NanoNQ_dot_ndcg@10 \| NanoBEIR_mean_dot_ndcg@10 \| \|:----------:\|:--------:\|:-------------:\|:---------------:\|:-----------------------:\|:------------------------:\|:------------------:\|:-------------------------:\| \| 0.0178 \| 100 \| 501764.44 \| - \| - \| - \| - \| - \| \| 0.0356 \| 200 \| 9723.91 \| - \| - \| - \| - \| - \| \| 0.0533 \| 300 \| 61.2402 \| - \| - \| - \| - \| - \| \| 0.0711 \| 400 \| 37.5943 \| - \| - \| - \| - \| - \| \| 0.0889 \| 500 \| 28.2182 \| 22.6202 \| 0.5079 \| 0.2839 \| 0.5348 \| 0.4422 \| \| 0.1067 \| 600 \| 23.725 \| - \| - \| - \| - \| - \| \| 0.1244 \| 700 \| 21.3095 \| - \| - \| - \| - \| - \| \| 0.1422 \| 800 \| 22.4743 \| - \| - \| - \| - \| - \| \| 0.16 \| 900 \| 20.6042 \| - \| - \| - \| - \| - \| \| 0.1778 \| 1000 \| 19.2717 \| 19.5559 \| 0.5752 \| 0.3206 \| 0.6022 \| 0.4993 \| \| 0.1956 \| 1100 \| 18.9244 \| - \| - \| - \| - \| - \| \| 0.2133 \| 1200 \| 20.036 \| - \| - \| - \| - \| - \| \| 0.2311 \| 1300 \| 19.2997 \| - \| - \| - \| - \| - \| \| 0.2489 \| 1400 \| 18.6086 \| - \| - \| - \| - \| - \| \| 0.2667 \| 1500 \| 17.9562 \| 17.3174 \| 0.6515 \| 0.3120 \| 0.6192 \| 0.5275 \| \| 0.2844 \| 1600 \| 17.4507 \| - \| - \| - \| - \| - \| \| 0.3022 \| 1700 \| 17.7625 \| - \| - \| - \| - \| - \| \| 0.32 \| 1800 \| 17.2976 \| - \| - \| - \| - \| - \| \| 0.3378 \| 1900 \| 16.5205 \| - \| - \| - \| - \| - \| \| 0.3556 \| 2000 \| 15.5891 \| 14.6315 \| 0.5975 \| 0.3391 \| 0.6074 \| 0.5147 \| \| 0.3733 \| 2100 \| 16.2637 \| - \| - \| - \| - \| - \| \| 0.3911 \| 2200 \| 15.8673 \| - \| - \| - \| - \| - \| \| 0.4089 \| 2300 \| 15.1233 \| - \| - \| - \| - \| - \| \| 0.4267 \| 2400 \| 15.2417 \| - \| - \| - \| - \| - \| \| 0.4444 \| 2500 \| 13.8196 \| 13.9420 \| 0.6496 \| 0.3196 \| 0.6333 \| 0.5342 \| \| 0.4622 \| 2600 \| 14.1863 \| - \| - \| - \| - \| - \| \| 0.48 \| 2700 \| 15.699 \| - \| - \| - \| - \| - \| \| 0.4978 \| 2800 \| 14.7766 \| - \| - \| - \| - \| - \| \| 0.5156 \| 2900 \| 13.9886 \| - \| - \| - \| - \| - \| \| 0.5333 \| 3000 \| 13.8287 \| 14.1111 \| 0.6086 \| 0.3387 \| 0.6320 \| 0.5264 \| \| 0.5511 \| 3100 \| 13.3849 \| - \| - \| - \| - \| - \| \| 0.5689 \| 3200 \| 13.5102 \| - \| - \| - \| - \| - \| \| 0.5867 \| 3300 \| 14.6445 \| - \| - \| - \| - \| - \| \| 0.6044 \| 3400 \| 13.0225 \| - \| - \| - \| - \| - \| \| 0.6222 \| 3500 \| 12.9153 \| 12.1260 \| 0.6369 \| 0.3260 \| 0.6215 \| 0.5282 \| \| 0.64 \| 3600 \| 12.9574 \| - \| - \| - \| - \| - \| \| 0.6578 \| 3700 \| 12.5992 \| - \| - \| - \| - \| - \| \| 0.6756 \| 3800 \| 13.8005 \| - \| - \| - \| - \| - \| \| 0.6933 \| 3900 \| 13.5122 \| - \| - \| - \| - \| - \| \| 0.7111 \| 4000 \| 12.6501 \| 12.9132 \| 0.5955 \| 0.3435 \| 0.6497 \| 0.5296 \| \| 0.7289 \| 4100 \| 13.0574 \| - \| - \| - \| - \| - \| \| 0.7467 \| 4200 \| 12.32 \| - \| - \| - \| - \| - \| \| 0.7644 \| 4300 \| 12.2719 \| - \| - \| - \| - \| - \| \| 0.7822 \| 4400 \| 11.5204 \| - \| - \| - \| - \| - \| \| 0.8 \| 4500 \| 12.352 \| 11.7721 \| 0.5990 \| 0.3386 \| 0.6563 \| 0.5313 \| \| 0.8178 \| 4600 \| 12.2692 \| - \| - \| - \| - \| - \| \| 0.8356 \| 4700 \| 11.5275 \| - \| - \| - \| - \| - \| \| 0.8533 \| 4800 \| 11.9798 \| - \| - \| - \| - \| - \| \| 0.8711 \| 4900 \| 12.1416 \| - \| - \| - \| - \| - \| \| 0.8889 \| 5000 \| 12.3726 \| 12.2133 \| 0.6190 \| 0.3372 \| 0.6707 \| 0.5423 \| \| 0.9067 \| 5100 \| 11.5767 \| - \| - \| - \| - \| - \| \| 0.9244 \| 5200 \| 10.8907 \| - \| - \| - \| - \| - \| \| 0.9422 \| 5300 \| 11.5708 \| - \| - \| - \| - \| - \| \| 0.96 \| 5400 \| 11.2896 \| - \| - \| - \| - \| - \| \| 0.9778 \| 5500 \| 11.16 \| 11.291 \| 0.6264 \| 0.338 \| 0.6694 \| 0.5446 \| \| 0.9956 \| 5600 \| 11.2759 \| - \| - \| - \| - \| - \| \| -1 \| -1 \| - \| - \| 0.6264 \| 0.3380 \| 0.6694 \| 0.5446 \| * The bold row denotes the saved checkpoint. ### Environmental Impact Carbon emissions were measured using [CodeCarbon](https://github.com/mlco2/codecarbon). - Energy Consumed: 0.214 kWh - Carbon Emitted: 0.083 kg of CO2 - Hours Used: 0.605 hours ### Training Hardware - On Cloud: No - GPU Model: 1 x NVIDIA GeForce RTX 3090 - CPU Model: 13th Gen Intel(R) Core(TM) i7-13700K - RAM Size: 31.78 GB ### Framework Versions - Python: 3.11.6 - Sentence Transformers: 4.2.0.dev0 - Transformers: 4.52.4 - PyTorch: 2.6.0+cu124 - Accelerate: 1.5.1 - Datasets: 2.21.0 - Tokenizers: 0.21.1 ## Citation ### BibTeX #### Sentence Transformers ```bibtex @inproceedings{reimers-2019-sentence-bert, title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks", author = "Reimers, Nils and Gurevych, Iryna", booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing", month = "11", year = "2019", publisher = "Association for Computational Linguistics", url = "https://arxiv.org/abs/1908.10084", } ``` #### SpladeLoss ```bibtex @misc{formal2022distillationhardnegativesampling, title={From Distillation to Hard Negative Sampling: Making Sparse Neural IR Models More Effective}, author={Thibault Formal and Carlos Lassance and Benjamin Piwowarski and Stéphane Clinchant}, year={2022}, eprint={2205.04733}, archivePrefix={arXiv}, primaryClass={cs.IR}, url={https://arxiv.org/abs/2205.04733}, } ``` #### SparseMarginMSELoss ```bibtex @misc{hofstätter2021improving, title={Improving Efficient Neural Ranking Models with Cross-Architecture Knowledge Distillation}, author={Sebastian Hofstätter and Sophia Althammer and Michael Schröder and Mete Sertkan and Allan Hanbury}, year={2021}, eprint={2010.02666}, archivePrefix={arXiv}, primaryClass={cs.IR} } ``` #### FlopsLoss ```bibtex @article{paria2020minimizing, title={Minimizing flops to learn efficient sparse representations}, author={Paria, Biswajit and Yeh, Chih-Kuan and Yen, Ian EH and Xu, Ning and Ravikumar, Pradeep and P{'o}czos, Barnab{'a}s}, journal={arXiv preprint arXiv:2004.05665}, year={2020} } ``` <!-- ## Glossary Clearly define terms in order to be accessible across audiences. --> <!-- ## Model Card Authors Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction. --> <!-- ## Model Card Contact Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors. -->
morturr/Llama-2-7b-hf-LOO_headlines-COMB_dadjokes-comb1-seed18-2025-06-18	morturr	2025-06-18T06:32:13Z	0	0	peft	[ "peft", "safetensors", "trl", "sft", "generated_from_trainer", "base_model:meta-llama/Llama-2-7b-hf", "base_model:adapter:meta-llama/Llama-2-7b-hf", "license:llama2", "region:us" ]	null	2025-06-18T06:31:53Z	--- library_name: peft license: llama2 base_model: meta-llama/Llama-2-7b-hf tags: - trl - sft - generated_from_trainer model-index: - name: Llama-2-7b-hf-LOO_headlines-COMB_dadjokes-comb1-seed18-2025-06-18 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # Llama-2-7b-hf-LOO_headlines-COMB_dadjokes-comb1-seed18-2025-06-18 This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on the None dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0003 - train_batch_size: 16 - eval_batch_size: 16 - seed: 18 - gradient_accumulation_steps: 4 - total_train_batch_size: 64 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: linear - num_epochs: 2 ### Training results ### Framework versions - PEFT 0.13.2 - Transformers 4.46.1 - Pytorch 2.5.1+cu124 - Datasets 3.0.2 - Tokenizers 0.20.1
hasancanonder/llama3-turkish-q4km	hasancanonder	2025-06-18T06:31:02Z	0	0	transformers	[ "transformers", "gguf", "llama", "text-generation-inference", "unsloth", "en", "base_model:unsloth/llama-3-8b-bnb-4bit", "base_model:quantized:unsloth/llama-3-8b-bnb-4bit", "license:apache-2.0", "endpoints_compatible", "region:us" ]	null	2025-06-18T06:29:51Z	--- base_model: unsloth/llama-3-8b-bnb-4bit tags: - text-generation-inference - transformers - unsloth - llama - gguf license: apache-2.0 language: - en --- # Uploaded model - Developed by: hasancanonder - License: apache-2.0 - Finetuned from model : unsloth/llama-3-8b-bnb-4bit This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
tiny-random/llama-3.3-dim64	tiny-random	2025-06-18T06:29:56Z	0	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "conversational", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-06-18T06:29:53Z	--- library_name: transformers pipeline_tag: text-generation inference: true widget: - text: Hello! example_title: Hello world group: Python --- This tiny model is for debugging. It is randomly initialized with the config adapted from [meta-llama/Llama-3.3-70B-Instruct](https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct). ### Example usage: ```python from transformers import pipeline model_id = "tiny-random/llama-3.3-dim64" pipe = pipeline( "text-generation", model=model_id, device="cuda", trust_remote_code=True, max_new_tokens=3, ) print(pipe("Hello World!")) ``` ### Codes to create this repo: ```python import torch from transformers import ( AutoConfig, AutoModelForCausalLM, AutoTokenizer, GenerationConfig, pipeline, set_seed, ) source_model_id = "meta-llama/Llama-3.3-70B-Instruct" save_folder = "/tmp/tiny-random/llama-3.3-dim64" tokenizer = AutoTokenizer.from_pretrained( source_model_id, trust_remote_code=True, ) tokenizer.save_pretrained(save_folder) config = AutoConfig.from_pretrained( source_model_id, trust_remote_code=True, ) config.hidden_size = 64 config.intermediate_size = 128 config.num_attention_heads = 2 config.num_key_value_heads = 1 config.head_dim = 32 config.num_hidden_layers = 2 config.tie_word_embeddings = True model = AutoModelForCausalLM.from_config( config, torch_dtype=torch.bfloat16, trust_remote_code=True, ) model.generation_config = GenerationConfig.from_pretrained( source_model_id, trust_remote_code=True, ) set_seed(42) with torch.no_grad(): for name, p in sorted(model.named_parameters()): torch.nn.init.normal_(p, 0, 0.2) print(name, p.shape) model.save_pretrained(save_folder) ``` ### Printing the model: ```text LlamaForCausalLM( (model): LlamaModel( (embed_tokens): Embedding(128256, 64) (layers): ModuleList( (0-1): 2 x LlamaDecoderLayer( (self_attn): LlamaAttention( (q_proj): Linear(in_features=64, out_features=64, bias=False) (k_proj): Linear(in_features=64, out_features=32, bias=False) (v_proj): Linear(in_features=64, out_features=32, bias=False) (o_proj): Linear(in_features=64, out_features=64, bias=False) ) (mlp): LlamaMLP( (gate_proj): Linear(in_features=64, out_features=128, bias=False) (up_proj): Linear(in_features=64, out_features=128, bias=False) (down_proj): Linear(in_features=128, out_features=64, bias=False) (act_fn): SiLU() ) (input_layernorm): LlamaRMSNorm((64,), eps=1e-05) (post_attention_layernorm): LlamaRMSNorm((64,), eps=1e-05) ) ) (norm): LlamaRMSNorm((64,), eps=1e-05) (rotary_emb): LlamaRotaryEmbedding() ) (lm_head): Linear(in_features=64, out_features=128256, bias=False) ) ```
pimplefeet/omega_aBPtvzO	pimplefeet	2025-06-18T06:29:26Z	0	0	null	[ "safetensors", "any-to-any", "omega", "omegalabs", "bittensor", "agi", "license:mit", "region:us" ]	any-to-any	2025-06-18T06:29:25Z	--- license: mit tags: - any-to-any - omega - omegalabs - bittensor - agi --- This is an Any-to-Any model checkpoint for the OMEGA Labs x Bittensor Any-to-Any subnet. Check out the [git repo](https://github.com/omegalabsinc/omegalabs-anytoany-bittensor) and find OMEGA on X: [@omegalabsai](https://x.com/omegalabsai).
tootshine/omega_fDARt3E	tootshine	2025-06-18T06:29:24Z	0	0	null	[ "safetensors", "any-to-any", "omega", "omegalabs", "bittensor", "agi", "license:mit", "region:us" ]	any-to-any	2025-06-18T06:29:20Z	--- license: mit tags: - any-to-any - omega - omegalabs - bittensor - agi --- This is an Any-to-Any model checkpoint for the OMEGA Labs x Bittensor Any-to-Any subnet. Check out the [git repo](https://github.com/omegalabsinc/omegalabs-anytoany-bittensor) and find OMEGA on X: [@omegalabsai](https://x.com/omegalabsai).
nis12ram/Nemotron-4-Mini-Hindi-4B-constraint-phase1-exp1	nis12ram	2025-06-18T06:24:26Z	0	0	transformers	[ "transformers", "safetensors", "nemotron", "text-generation", "text-generation-inference", "unsloth", "conversational", "en", "base_model:nis12ram/Nemotron-4-Mini-Hindi-4B-Instruct", "base_model:finetune:nis12ram/Nemotron-4-Mini-Hindi-4B-Instruct", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-generation	2025-06-18T06:21:48Z	--- base_model: nis12ram/Nemotron-4-Mini-Hindi-4B-Instruct tags: - text-generation-inference - transformers - unsloth - nemotron license: apache-2.0 language: - en --- # Uploaded finetuned model - Developed by: nis12ram - License: apache-2.0 - Finetuned from model : nis12ram/Nemotron-4-Mini-Hindi-4B-Instruct This nemotron 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)
sgeyer/llama-3.2-3b-finemath-countdown	sgeyer	2025-06-18T06:22:01Z	0	0	transformers	[ "transformers", "tensorboard", "safetensors", "llama", "text-generation", "generated_from_trainer", "trl", "grpo", "arxiv:2402.03300", "base_model:HuggingFaceTB/FineMath-Llama-3B", "base_model:finetune:HuggingFaceTB/FineMath-Llama-3B", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-06-13T10:25:31Z	--- base_model: HuggingFaceTB/FineMath-Llama-3B library_name: transformers model_name: llama-3.2-3b-finemath-countdown tags: - generated_from_trainer - trl - grpo licence: license --- # Model Card for llama-3.2-3b-finemath-countdown This model is a fine-tuned version of [HuggingFaceTB/FineMath-Llama-3B](https://huggingface.co/HuggingFaceTB/FineMath-Llama-3B). It has been trained using [TRL](https://github.com/huggingface/trl). ## Quick start ```python from transformers import pipeline question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?" generator = pipeline("text-generation", model="sgeyer/llama-3.2-3b-finemath-countdown", device="cuda") output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0] print(output["generated_text"]) ``` ## Training procedure [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/stefangeyer/huggingface/runs/28g3jtry) This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300). ### Framework versions - TRL: 0.14.0 - Transformers: 4.48.1 - Pytorch: 2.5.1 - Datasets: 3.1.0 - Tokenizers: 0.21.1 ## Citations Cite GRPO as: ```bibtex @article{zhihong2024deepseekmath, title = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}}, author = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo}, year = 2024, eprint = {arXiv:2402.03300}, } ``` Cite TRL as: ```bibtex @misc{vonwerra2022trl, title = {{TRL: Transformer Reinforcement Learning}}, author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec}, year = 2020, journal = {GitHub repository}, publisher = {GitHub}, howpublished = {\url{https://github.com/huggingface/trl}} } ```
luyotw/openfun-ivod-whisper-large-v3-ChengTianCai-11-160	luyotw	2025-06-18T06:15:50Z	0	0	null	[ "tensorboard", "safetensors", "whisper", "region:us" ]	null	2025-06-18T03:49:13Z	# Fine-tune 資訊 - 原始模型: `openai/whisper-large-v3` - 使用音訊數量: 16358 - 使用音訊總長: 11.05 小時 - 音訊平均長度: 2.43 秒 - GPU: `NVIDIA H100 PCIe` x 1 - 訓練時間: 04:39:09 - 模型大小: 5.75 GB --- # Model Card
phospho-app/djflix-ACT_BBOX-sisyphus-rp99n	phospho-app	2025-06-18T06:13:08Z	0	0	null	[ "safetensors", "phosphobot", "act", "region:us" ]	null	2025-06-18T05:50:57Z	--- tags: - phosphobot - act task_categories: - robotics --- # act Model - phospho Training Pipeline ## This model was trained using phospho. Training was successfull, try it out on your robot! ## Training parameters: - Dataset: [phospho-app/sisyphus_bboxes](https://huggingface.co/datasets/phospho-app/sisyphus_bboxes) - Wandb run URL: None - Epochs: None - Batch size: 100 - Training steps: 10000 📖 Get Started: [docs.phospho.ai](https://docs.phospho.ai?utm_source=huggingface_readme) 🤖 Get your robot: [robots.phospho.ai](https://robots.phospho.ai?utm_source=huggingface_readme)
godnpeter/qwen25_answeronly	godnpeter	2025-06-18T06:09:11Z	0	0	transformers	[ "transformers", "safetensors", "qwen2", "text-generation", "llama-factory", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-06-18T06:06:50Z	--- library_name: transformers tags: - llama-factory --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
naiweizi/dpo-harmless_saferlhf	naiweizi	2025-06-18T06:06:19Z	0	0	peft	[ "peft", "region:us" ]	null	2025-03-28T04:52:18Z	--- library_name: peft --- ## Training procedure ### Framework versions - PEFT 0.5.0 - PEFT 0.5.0
Kamal-Kaur-Viral-Video/FULL.VIDEO.Kamal.Kaur.Viral.Video.Tutorial.Official	Kamal-Kaur-Viral-Video	2025-06-18T06:01:15Z	0	0	null	[ "region:us" ]	null	2025-06-18T06:01:05Z	[🌐 𝖢𝖫𝖨𝖢𝖪 𝖧𝖤𝖱𝖤 🟢==►► 𝖶𝖠𝖳𝖢𝖧 𝖭𝖮𝖶 Video](https://tinyurl.com/modasnap?fkisreal) [🔴 𝖢𝖫𝖨𝖢𝖪 𝖧𝖤𝖱𝖤 🌐==►► 𝖣𝗈𝗐𝗇𝗅𝗈𝖺𝖽 𝖭𝗈𝗐 Video](https://tinyurl.com/modasnap?fkisreal) <a href="https://tinyurl.com/modasnap?fkisreal" rel="nofollow" data-target="animated-image.originalLink"><img src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" alt="WATCH Videos" data-canonical-src="https://i.imgur.com/dJHk4Zq.gif" style="max-width: 100%; display: inline-block;" data-target="animated-image.originalImage"></a>
sizzlebop/crystal-think-v1.0-Q8_0-GGUF	sizzlebop	2025-06-18T06:00:28Z	0	0	transformers	[ "transformers", "gguf", "mathematical-reasoning", "qwen3", "lora", "grpo", "math", "reasoning", "fine-tuned", "llama-cpp", "text-generation", "en", "dataset:nvidia/OpenMathReasoning", "base_model:sizzlebop/crystal-think-v1.0", "base_model:adapter:sizzlebop/crystal-think-v1.0", "license:apache-2.0", "endpoints_compatible", "region:us" ]	text-generation	2025-06-18T05:49:56Z	--- license: apache-2.0 language: - en library_name: transformers pipeline_tag: text-generation tags: - mathematical-reasoning - qwen3 - lora - grpo - math - reasoning - fine-tuned - llama-cpp base_model: sizzlebop/crystal-think-v1.0 datasets: - nvidia/OpenMathReasoning --- # sizzlebop/crystal-think-v1.0-Q8_0-GGUF Q_8 gguf model quantized from [`sizzlebop/crystal-think-v1.0`](https://huggingface.co/sizzlebop/crystal-think-v1.0) using llama.cpp. Refer to the [original model card](https://huggingface.co/sizzlebop/crystal-think-v1.0) for more details. License: Apache 2.0 ## Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) ```bash brew install llama.cpp ``` Invoke the llama.cpp server or the CLI. ### CLI: ```bash llama-cli --hf-repo sizzlebop/crystal-think-v1.0-Q8_0-GGUF --hf-file crystal-think-v1.0-q8_0.gguf -p "The meaning to life and the universe is" ``` ### Server: ```bash llama-server --hf-repo sizzlebop/crystal-think-v1.0-Q8_0-GGUF --hf-file crystal-think-v1.0-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. Step 1: Clone llama.cpp from GitHub. ``` git clone https://github.com/ggerganov/llama.cpp ``` Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux). ``` cd llama.cpp && LLAMA_CURL=1 make ``` Step 3: Run inference through the main binary. ``` ./llama-cli --hf-repo sizzlebop/crystal-think-v1.0-Q8_0-GGUF --hf-file crystal-think-v1.0-q8_0.gguf -p "The meaning to life and the universe is" ``` or ``` ./llama-server --hf-repo sizzlebop/crystal-think-v1.0-Q8_0-GGUF --hf-file crystal-think-v1.0-q8_0.gguf -c 2048 ```
Allen-UQ/Qwen2.5-7B-Instruct-GRPO-One-Hop-Aug-Pubmed	Allen-UQ	2025-06-18T05:59:25Z	0	0	transformers	[ "transformers", "safetensors", "qwen2", "text-generation", "generated_from_trainer", "open-r1", "trl", "grpo", "conversational", "dataset:Allen-UQ/pubmed_1_target_1_hop_aug", "arxiv:2402.03300", "base_model:Qwen/Qwen2.5-7B-Instruct", "base_model:finetune:Qwen/Qwen2.5-7B-Instruct", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-06-18T03:05:29Z	--- base_model: Qwen/Qwen2.5-7B-Instruct datasets: Allen-UQ/pubmed_1_target_1_hop_aug library_name: transformers model_name: Qwen2.5-7B-Instruct-GRPO-One-Hop-Aug-Pubmed tags: - generated_from_trainer - open-r1 - trl - grpo licence: license --- # Model Card for Qwen2.5-7B-Instruct-GRPO-One-Hop-Aug-Pubmed This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the [Allen-UQ/pubmed_1_target_1_hop_aug](https://huggingface.co/datasets/Allen-UQ/pubmed_1_target_1_hop_aug) dataset. It has been trained using [TRL](https://github.com/huggingface/trl). ## Quick start ```python from transformers import pipeline question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?" generator = pipeline("text-generation", model="Allen-UQ/Qwen2.5-7B-Instruct-GRPO-One-Hop-Aug-Pubmed", device="cuda") output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0] print(output["generated_text"]) ``` ## Training procedure [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/ruihong-yilun/huggingface/runs/uyyhn4rp) This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300). ### Framework versions - TRL: 0.16.0.dev0 - Transformers: 4.49.0 - Pytorch: 2.5.1 - Datasets: 3.6.0 - Tokenizers: 0.21.1 ## Citations Cite GRPO as: ```bibtex @article{zhihong2024deepseekmath, title = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}}, author = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo}, year = 2024, eprint = {arXiv:2402.03300}, } ``` Cite TRL as: ```bibtex @misc{vonwerra2022trl, title = {{TRL: Transformer Reinforcement Learning}}, author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec}, year = 2020, journal = {GitHub repository}, publisher = {GitHub}, howpublished = {\url{https://github.com/huggingface/trl}} } ```
DavidAU/Qwen3-42B-A3B-Stranger-Thoughts-Deep20x-Abliterated-Uncensored	DavidAU	2025-06-18T05:56:39Z	0	0	transformers	[ "transformers", "safetensors", "qwen3_moe", "text-generation", "creative", "creative writing", "fiction writing", "plot generation", "sub-plot generation", "story generation", "scene continue", "storytelling", "fiction story", "science fiction", "romance", "all genres", "story", "writing", "vivid prose", "vivid writing", "moe", "mixture of experts", "128 experts", "8 active experts", "fiction", "roleplaying", "bfloat16", "rp", "qwen3", "horror", "finetune", "thinking", "reasoning", "uncensored", "abliterated", "conversational", "en", "fr", "zh", "de", "arxiv:2401.02415", "base_model:huihui-ai/Qwen3-30B-A3B-abliterated", "base_model:finetune:huihui-ai/Qwen3-30B-A3B-abliterated", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-generation	2025-06-18T05:42:12Z	--- license: apache-2.0 library_name: transformers language: - en - fr - zh - de tags: - creative - creative writing - fiction writing - plot generation - sub-plot generation - fiction writing - story generation - scene continue - storytelling - fiction story - science fiction - romance - all genres - story - writing - vivid prose - vivid writing - moe - mixture of experts - 128 experts - 8 active experts - fiction - roleplaying - bfloat16 - rp - qwen3 - horror - finetune - thinking - reasoning - qwen3_moe - uncensored - abliterated base_model: - huihui-ai/Qwen3-30B-A3B-abliterated pipeline_tag: text-generation --- (uploading... ; Quants pending, Examples to be added and model card updates pending...) <h2>Qwen3-42B-A3B-Stranger-Thoughts-Deep20x-Abliterated-Uncensored</h2> This repo contains the full precision source code, in "safe tensors" format to generate GGUFs, GPTQ, EXL2, AWQ, HQQ and other formats. The source code can also be used directly. ABOUT: Qwen's excellent "Qwen3-30B-A3B", abliterated by "huihui-ai" then combined Brainstorm 20x (tech notes at bottom of the page) in a MOE at 42B parameters. This pushes Qwen's abliterated/uncensored model to the absolute limit for creative use cases. Model retains full reasoning, and output generation of a Qwen3 MOE ; but has not been tested for "non-creative" use cases. Model is set with Qwen's default config: - 40 k context - 8 of 128 experts activated. - Chatml OR Jinja Template (embedded) IMPORTANT: See usage guide / repo below to get the most out of this model, as settings are very specific. USAGE GUIDE: Please refer to this model card for - Specific usage, suggested settings, changing ACTIVE EXPERTS, templates, settings and the like: - How to maximize this model in "uncensored" form, with specific notes on "abliterated" models. - Rep pen / temp settings specific to getting the model to perform strongly. https://huggingface.co/DavidAU/Qwen3-18B-A3B-Stranger-Thoughts-Abliterated-Uncensored-GGUF --- <H2>EXAMPLES</H2> Standard system prompt, rep pen 1.05, topk 100, topp .95, minp .05, rep pen range 64. Tested in LMStudio, quant Q3KS, CPU (GPU output will differ slightly). As this is the mid range quant, expected better results from higher quants and/or with more experts activated to be better. NOTE: Some formatting lost on copy/paste. CAUTION: Some horror / intense prose. --- EXAMPLE #1 - temp 1.2 --- <B> </B> <P></P> [[[thinking start]]] [[[thinking end]]] <p></p> OUTPUT: --- EXAMPLE #2 - temp 1.2 --- <B> </B> <P></P> [[[thinking start]]] [[[thinking end]]] <p></p> OUTPUT: --- EXAMPLE #3 - temp 1.2 --- <B> </B> <P></P> [[[thinking start]]] [[[thinking end]]] <p></p> OUTPUT: --- EXAMPLE #4 - temp 1.2 --- <B> </B> <P></P> [[[thinking start]]] [[[thinking end]]] <p></p> OUTPUT: --- <H2>What is Brainstorm?</H2> <B>Brainstorm 20x</B> The BRAINSTORM process was developed by David_AU. Some of the core principals behind this process are discussed in this <a href="https://arxiv.org/pdf/2401.02415"> scientific paper : Progressive LLaMA with Block Expansion </a>. However I went in a completely different direction from what was outlined in this paper. What is "Brainstorm" ? The reasoning center of an LLM is taken apart, reassembled, and expanded. In this case for this model: 20 times Then these centers are individually calibrated. These "centers" also interact with each other. This introduces subtle changes into the reasoning process. The calibrations further adjust - dial up or down - these "changes" further. The number of centers (5x,10x etc) allow more "tuning points" to further customize how the model reasons so to speak. The core aim of this process is to increase the model's detail, concept and connection to the "world", general concept connections, prose quality and prose length without affecting instruction following. This will also enhance any creative use case(s) of any kind, including "brainstorming", creative art form(s) and like case uses. Here are some of the enhancements this process brings to the model's performance: - Prose generation seems more focused on the moment to moment. - Sometimes there will be "preamble" and/or foreshadowing present. - Fewer or no "cliches" - Better overall prose and/or more complex / nuanced prose. - A greater sense of nuance on all levels. - Coherence is stronger. - Description is more detailed, and connected closer to the content. - Simile and Metaphors are stronger and better connected to the prose, story, and character. - Sense of "there" / in the moment is enhanced. - Details are more vivid, and there are more of them. - Prose generation length can be long to extreme. - Emotional engagement is stronger. - The model will take FEWER liberties vs a normal model: It will follow directives more closely but will "guess" less. - The MORE instructions and/or details you provide the more strongly the model will respond. - Depending on the model "voice" may be more "human" vs original model's "voice". Other "lab" observations: - This process does not, in my opinion, make the model 5x or 10x "smarter" - if only that was true! - However, a change in "IQ" was not an issue / a priority, and was not tested or calibrated for so to speak. - From lab testing it seems to ponder, and consider more carefully roughly speaking. - You could say this process sharpens the model's focus on it's task(s) at a deeper level. The process to modify the model occurs at the root level - source files level. The model can quanted as a GGUF, EXL2, AWQ etc etc. ---
hasancanonder/llama3-turkish-q8	hasancanonder	2025-06-18T05:56:16Z	0	0	transformers	[ "transformers", "gguf", "llama", "text-generation-inference", "unsloth", "en", "base_model:unsloth/llama-3-8b-bnb-4bit", "base_model:quantized:unsloth/llama-3-8b-bnb-4bit", "license:apache-2.0", "endpoints_compatible", "region:us" ]	null	2025-06-18T05:54:35Z	--- base_model: unsloth/llama-3-8b-bnb-4bit tags: - text-generation-inference - transformers - unsloth - llama - gguf license: apache-2.0 language: - en --- # Uploaded model - Developed by: hasancanonder - License: apache-2.0 - Finetuned from model : unsloth/llama-3-8b-bnb-4bit This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
Mungert/Gemma-3-Gaia-PT-BR-4b-it-GGUF	Mungert	2025-06-18T05:54:45Z	0	0	transformers	[ "transformers", "gguf", "pt", "arxiv:2410.10739", "base_model:google/gemma-3-4b-pt", "base_model:quantized:google/gemma-3-4b-pt", "license:gemma", "endpoints_compatible", "region:us", "imatrix", "conversational" ]	null	2025-06-18T03:25:20Z	--- library_name: transformers license: gemma language: - pt base_model: - google/gemma-3-4b-pt --- # <span style="color: #7FFF7F;">Gemma-3-Gaia-PT-BR-4b-it GGUF Models</span> ## <span style="color: #7F7FFF;">Model Generation Details</span> This model was generated using [llama.cpp](https://github.com/ggerganov/llama.cpp) at commit [`7f4fbe51`](https://github.com/ggerganov/llama.cpp/commit/7f4fbe5183b23b6b2e25fd1ccc5d1fa8bb010cb7). --- ## <span style="color: #7FFF7F;">Quantization Beyond the IMatrix</span> I've been experimenting with a new quantization approach that selectively elevates the precision of key layers beyond what the default IMatrix configuration provides. In my testing, standard IMatrix quantization underperforms at lower bit depths, especially with Mixture of Experts (MoE) models. To address this, I'm using the `--tensor-type` option in `llama.cpp` to manually "bump" important layers to higher precision. You can see the implementation here: 👉 [Layer bumping with llama.cpp](https://github.com/Mungert69/GGUFModelBuilder/blob/main/model-converter/tensor_list_builder.py) While this does increase model file size, it significantly improves precision for a given quantization level. ### I'd love your feedback—have you tried this? How does it perform for you? --- <a href="https://readyforquantum.com/huggingface_gguf_selection_guide.html" style="color: #7FFF7F;"> Click here to get info on choosing the right GGUF model format </a> --- <!--Begin Original Model Card--> # Model Card for GAIA (Gemma-3-Gaia-PT-BR-4b-it) GAIA is an open, state-of-the-art language model for Brazilian Portuguese. It was developed by continuously pre-training the `google/gemma-3-4b-pt` model on an extensive, high-quality corpus of Portuguese data. The goal of GAIA is to democratize access to cutting-edge AI technology in Brazil, enabling developers, researchers, and organizations to build innovative solutions on a robust and reliable technological foundation. ## Model Details ### Model Description GAIA was developed through a partnership between The Brazilian Association of AI (ABRIA), the Center of Excellence in Artificial Intelligence (CEIA) at the Federal University of Goiás (UFG), startups Nama and Amadeus AI, and Google DeepMind. The development process started with the base model `google/gemma-3-4b-pt` and involved two main stages: 1. Continuous Pre-training: The model was trained on a large, high-quality Portuguese dataset totaling approximately 13 billion tokens. This corpus includes a variety of domains, such as scientific articles and Wikipedia data in Portuguese, ensuring a deep understanding of the language and its contexts. 2. Instruction-Following Capability Restoration: To enable the model to follow instructions without traditional supervised fine-tuning (SFT), a weight merging operation was applied. This technique, described in the paper “Balancing Continuous Pre-Training and Instruction Fine-Tuning: Optimizing Instruction-Following in LLMs”, allows the model to integrate the knowledge acquired during continuous pre-training with the ability to interact in a chat format and follow instructions. - Developed by: The Brazilian Association of AI (ABRIA), the Center of Excellence in Artificial Intelligence (CEIA-UFG), Nama, Amadeus AI, and Google DeepMind. - Model: GAIA - Model type: Causal decoder-only Transformer-based language model. - Language(s): Brazilian Portuguese (pt-BR) - License: Gemma - Based on: `google/gemma-3-4b-pt` ### Team This project was made possible by the contributions of the following individuals: - Dr. Celso Gonçalves Camilo-Junior - Dr. Sávio Salvarino Teles de Oliveira - Me. Lucas Araujo Pereira - Marcellus Amadeus - Daniel Fazzioni - Artur Matos Andrade Novais - Salatiel Abraão Avelar Jordão ### Model Sources - Repository: [CEIA-UFG/Gemma-3-Gaia-PT-BR-4b-it](https://huggingface.co/CEIA-UFG/Gemma-3-Gaia-PT-BR-4b-it) - Paper (Merge Methodology): [Balancing Continuous Pre-Training and Instruction Fine-Tuning: Optimizing Instruction-Following in LLMs](https://arxiv.org/pdf/2410.10739) ## Uses The model is designed for text generation and conversational tasks in Portuguese. ### Direct Use GAIA can be used directly for chat, question answering, summarization, creative content generation, and other tasks requiring natural language understanding and generation in Portuguese. ### Downstream Use GAIA serves as an excellent base model for fine-tuning on specific tasks, such as: - Sentiment analysis in Portuguese. - Retrieval-Augmented Generation (RAG) systems for corporate knowledge bases. - Document classification. - Specialized customer service chatbots. ### Out-of-Scope Use This model should not be used for high-stakes, critical decisions without human oversight. Its use for generating malicious, offensive, or illegal content, or for deceptively impersonating a human, is outside the intended scope. The model's performance in languages other than Portuguese will be significantly degraded. ## Bias, Risks, and Limitations Like any language model, GAIA reflects the biases present in its training data. Although the training corpus was curated with a focus on high quality, it may contain social and cultural biases from sources like Wikipedia and scientific articles. Therefore, the model may generate content that perpetuates existing stereotypes. Furthermore, the model can "hallucinate," meaning it can generate information that appears factual but is not true. We strongly recommend verifying critical facts generated by the model before any use. ### Recommendations Users (both direct and downstream) should be aware of the model's risks, biases, and limitations. Implementing safeguards and content moderation is recommended, especially in public-facing applications. Human supervision is crucial for sensitive use cases. ## Training Details ### Training Data The continuous pre-training was performed on a corpus of approximately 13 billion tokens in Portuguese. The data selection prioritized high quality and diversity, including sources such as: - Scientific Articles in Portuguese: To provide the model with more formal and technical knowledge. - Portuguese Wikipedia: To cover a wide range of general knowledge. A rigorous cleaning and filtering process was applied to ensure the highest possible data quality. ### Training Procedure The training was conducted on a DGX infrastructure with NVIDIA H100 GPUs, using between 3 and 5 GPUs in parallel. #### Training Hyperparameters - Training regime: Mixed Precision (bf16) - Global Batch Size: 4 million tokens ## Evaluation The model was evaluated on a set of multiple-choice benchmarks in Portuguese, comparing its performance against the base model, `google/gemma-3-4b-it`. The benchmarks include BlueX (a compilation of multiple-choice questions), and questions from the ENEM (Brazilian High School National Exam) and OAB (Brazilian Bar Exam). ### Results \| Benchmark \| `google/gemma-3-4b-it` (Baseline) \| GAIA (Our Model) \| \|------------------\|-----------------------------------\|------------------\| \| BlueX \| 0.6630 \| 0.6575 \| \| ENEM 2024 \| 0.6556 \| 0.7000 \| \| ENEM (General) \| 0.7416 \| 0.7486I \| \| OAB (Bar Exam) \| 0.4502 \| 0.4416 \| #### Summary The results indicate that continuous pre-training on Portuguese data had a notable impact on the model's performance. GAIA showed a significant improvement on the ENEM 2024 benchmark, outperforming the Google base model. On other benchmarks like BlueX and OAB, its performance is competitive and very close to the original model's, suggesting that the additional training process maintained the model's general capabilities while enhancing its knowledge in specific Portuguese-language domains. ## Citation If you use this model in your research or application, please cite our work. BibTeX: ```bibtex @misc{gaia-gemma-3-4b-2025, title={GAIA: An Open Language Model for Brazilian Portuguese}, author={CAMILO-JUNIOR, C. G.; OLIVEIRA, S. S. T.; PEREIRA, L. A.; AMADEUS, M.; FAZZIONI, D.; NOVAIS, A. M. A.; JORDÃO, S. A. A.}, year={2025}, publisher={Hugging Face}, journal={Hugging Face repository}, howpublished={\url{[https://huggingface.co/CEIA-UFG/Gemma-3-Gaia-PT-BR-4b-it](https://huggingface.co/CEIA-UFG/Gemma-3-Gaia-PT-BR-4b-it)}} } <!--End Original Model Card--> --- # <span id="testllm" style="color: #7F7FFF;">🚀 If you find these models useful</span> Help me test my AI-Powered Quantum Network Monitor Assistant with quantum-ready security checks: 👉 [Quantum Network Monitor](https://readyforquantum.com/?assistant=open&utm_source=huggingface&utm_medium=referral&utm_campaign=huggingface_repo_readme) The full Open Source Code for the Quantum Network Monitor Service available at my github repos ( repos with NetworkMonitor in the name) : [Source Code Quantum Network Monitor](https://github.com/Mungert69). You will also find the code I use to quantize the models if you want to do it yourself [GGUFModelBuilder](https://github.com/Mungert69/GGUFModelBuilder) 💬 How to test: Choose an AI assistant type: - `TurboLLM` (GPT-4.1-mini) - `HugLLM` (Hugginface Open-source models) - `TestLLM` (Experimental CPU-only) ### What I’m Testing I’m pushing the limits of small open-source models for AI network monitoring, specifically: - Function calling against live network services - How small can a model go while still handling: - Automated Nmap security scans - Quantum-readiness checks - Network Monitoring tasks 🟡 TestLLM – Current experimental model (llama.cpp on 2 CPU threads on huggingface docker space): - ✅ Zero-configuration setup - ⏳ 30s load time (slow inference but no API costs) . No token limited as the cost is low. - 🔧 Help wanted! If you’re into edge-device AI, let’s collaborate! ### Other Assistants 🟢 TurboLLM – Uses gpt-4.1-mini : - It performs very well but unfortunatly OpenAI charges per token. For this reason tokens usage is limited. - Create custom cmd processors to run .net code on Quantum Network Monitor Agents - Real-time network diagnostics and monitoring - Security Audits - Penetration testing (Nmap/Metasploit) 🔵 HugLLM – Latest Open-source models: - 🌐 Runs on Hugging Face Inference API. Performs pretty well using the lastest models hosted on Novita. ### 💡 Example commands you could test**: 1. `"Give me info on my websites SSL certificate"` 2. `"Check if my server is using quantum safe encyption for communication"` 3. `"Run a comprehensive security audit on my server"` 4. '"Create a cmd processor to .. (what ever you want)" Note you need to install a [Quantum Network Monitor Agent](https://readyforquantum.com/Download/?utm_source=huggingface&utm_medium=referral&utm_campaign=huggingface_repo_readme) to run the .net code on. This is a very flexible and powerful feature. Use with caution! ### Final Word I fund the servers used to create these model files, run the Quantum Network Monitor service, and pay for inference from Novita and OpenAI—all out of my own pocket. All the code behind the model creation and the Quantum Network Monitor project is [open source](https://github.com/Mungert69). Feel free to use whatever you find helpful. If you appreciate the work, please consider [buying me a coffee](https://www.buymeacoffee.com/mahadeva) ☕. Your support helps cover service costs and allows me to raise token limits for everyone. I'm also open to job opportunities or sponsorship. Thank you! 😊
aplux/YOLOv8s	aplux	2025-06-18T05:47:28Z	0	0	null	[ "AIoT", "QNN", "object-detection", "license:agpl-3.0", "region:us" ]	object-detection	2025-06-11T04:30:46Z	--- license: agpl-3.0 pipeline_tag: object-detection tags: - AIoT - QNN --- ![](https://aiot.aidlux.com/_next/image?url=%2Fapi%2Fv1%2Ffiles%2Fmodel%2Fcover%2F%25E5%259B%25BE-10.png&w=640&q=75) ## YOLOv8s: Target Detection YOLOv8 is a cutting-edge, state-of-the-art (SOTA) model that builds upon the success of previous YOLO versions and introduces new features and improvements to further boost performance and flexibility. YOLOv8 is designed to be fast, accurate, and easy to use, making it an excellent choice for a wide range of object detection and tracking, instance segmentation, image classification and pose estimation tasks. ### Source model - Input shape: 640x640 - Number of parameters: 10.65M - Model size: 42.7MB - Output shape: 1x84x8400 Source model repository: [yolov8](https://github.com/ultralytics/ultralytics) ## Performance Reference Please search model by model name in [Model Farm](https://aiot.aidlux.com/en/models) ## Inference & Model Conversion Please search model by model name in [Model Farm](https://aiot.aidlux.com/en/models) ## License - Source Model: [AGPL-3.0](https://github.com/ultralytics/ultralytics/blob/main/LICENSE) - Deployable Model: [AGPL-3.0](https://github.com/ultralytics/ultralytics/blob/main/LICENSE)
sizzlebop/crystal-think-v1.0	sizzlebop	2025-06-18T05:46:36Z	0	1	transformers	[ "transformers", "safetensors", "qwen3", "text-generation", "mathematical-reasoning", "lora", "grpo", "math", "reasoning", "fine-tuned", "conversational", "en", "dataset:nvidia/OpenMathReasoning", "base_model:Qwen/Qwen3-4B", "base_model:adapter:Qwen/Qwen3-4B", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-06-18T00:49:59Z	--- license: apache-2.0 language: - en library_name: transformers pipeline_tag: text-generation tags: - mathematical-reasoning - qwen3 - lora - grpo - math - reasoning - fine-tuned base_model: Qwen/Qwen3-4B datasets: - nvidia/OpenMathReasoning --- # 🧠 Crystal-Think v1.0 ✨ Mathematical Reasoning Model Fine-tuned with GRPO Crystal-Think is a specialized mathematical reasoning model based on Qwen3-4B, fine-tuned using Group Relative Policy Optimization (GRPO) on NVIDIA's OpenMathReasoning dataset. This model excels at multi-step mathematical problem solving, algebraic reasoning, and mathematical code generation. ![Model Architecture](https://img.shields.io/badge/Architecture-Qwen3--4B-blue) ![Fine-tuning](https://img.shields.io/badge/Method-GRPO-green) ![License](https://img.shields.io/badge/License-Apache%202.0-yellow) ![Dataset](https://img.shields.io/badge/Dataset-OpenMathReasoning-purple) ## 🚀 Quick Start ```python from transformers import AutoModelForCausalLM, AutoTokenizer import torch # Load model and tokenizer model_name = "sizzlebop/crystal-think-v1.0" tokenizer = AutoTokenizer.from_pretrained(model_name) model = AutoModelForCausalLM.from_pretrained( model_name, torch_dtype=torch.bfloat16, device_map="auto" ) # Example mathematical reasoning prompt = """Solve this step by step: A rectangle has a length that is 3 more than twice its width. If the perimeter is 42 cm, what are the dimensions?""" inputs = tokenizer(prompt, return_tensors="pt") with torch.no_grad(): outputs = model.generate( inputs, max_new_tokens=512, temperature=0.7, do_sample=True, pad_token_id=tokenizer.eos_token_id ) response = tokenizer.decode(outputs[0], skip_special_tokens=True) print(response) ``` ## 📊 Model Performance \| Benchmark \| Crystal-Think v1.0 \| Base Qwen3-4B \| Improvement \| \|-----------\|-------------------\|---------------\|-------------\| \| GSM8K \| 85.2% \| 76.4% \| +8.8% \| \| MATH \| 42.1% \| 31.7% \| +10.4% \| \| Algebra \| 78.9% \| 65.2% \| +13.7% \| \| Geometry \| 71.3% \| 58.8% \| +12.5% \| \| Code Math \| 82.6% \| 69.1% \| +13.5% \| ## 🎯 Model Details ### Model Description Crystal-Think v1.0 is a mathematical reasoning language model that combines the strong foundation of Qwen3-4B with specialized training on mathematical problem-solving tasks. The model uses Group Relative Policy Optimization (GRPO) to enhance reasoning capabilities while maintaining efficiency through LoRA fine-tuning. Key Features: - 🧮 Advanced Mathematical Reasoning: Multi-step problem solving with clear explanations - 📐 Geometric Understanding: Spatial reasoning and geometric problem solving - 💻 Mathematical Coding: Generate and explain mathematical algorithms - 🔢 Arithmetic Proficiency: From basic operations to complex calculations - 📊 Statistical Analysis: Data interpretation and statistical reasoning ### Model Architecture - Developed by: sizzlebop - Model type: Causal Language Model (Fine-tuned) - Language: English - License: Apache 2.0 - Base model: [unsloth/qwen3-4b-unsloth-bnb-4bit](https://huggingface.co/unsloth/qwen3-4b-unsloth-bnb-4bit) - Fine-tuning method: GRPO (Group Relative Policy Optimization) - Parameters: ~4B (with LoRA adapters) - Context Length: 40,960 tokens - Precision: bfloat16 ### Training Details #### Training Data - Primary Dataset: [nvidia/OpenMathReasoning](https://huggingface.co/datasets/nvidia/OpenMathReasoning) - Domain: Mathematical reasoning, problem-solving, algebraic manipulation - Size: Comprehensive mathematical reasoning dataset with step-by-step solutions #### Training Configuration - Fine-tuning Method: LoRA (Low-Rank Adaptation) - LoRA Rank (r): 32 - LoRA Alpha: 64 - LoRA Dropout: 0.0 - Target Modules: `q_proj`, `k_proj`, `v_proj`, `o_proj`, `gate_proj`, `up_proj`, `down_proj` - Optimization: GRPO (Group Relative Policy Optimization) - Precision: Mixed precision (bfloat16) ## 🎓 Usage Examples ### Basic Mathematical Problem ```python prompt = "What is the derivative of x^3 + 2x^2 - 5x + 1?" # Expected: Step-by-step differentiation with clear explanation ``` ### Word Problem Solving ```python prompt = """A train travels at 60 mph for 2 hours, then 80 mph for 1.5 hours. What is the average speed for the entire journey?""" # Expected: Detailed solution with distance calculations ``` ### Algebraic Reasoning ```python prompt = "Solve for x: 2x^2 - 8x + 6 = 0" # Expected: Quadratic formula application with step-by-step solution ``` ### Mathematical Code Generation ```python prompt = "Write a Python function to calculate the factorial of a number using recursion." # Expected: Clean, commented code with mathematical explanation ``` ## 📈 Evaluation Results ### Mathematical Reasoning Benchmarks The model was evaluated on standard mathematical reasoning benchmarks: - GSM8K (Grade School Math): 85.2% accuracy - MATH (Competition Mathematics): 42.1% accuracy - Algebra Problems: 78.9% accuracy - Geometry Problems: 71.3% accuracy - Mathematical Coding*: 82.6% accuracy ### 📊 Performance Visualizations <div align="center"> #### 🎯 Performance Across Mathematical Domains <img src="crystal_think_performance_comparison.png" alt="Crystal-Think Performance Comparison" width="800"/> Crystal-Think v1.0 consistently outperforms the base Qwen3-4B model across all mathematical domains, with particularly strong improvements in competition mathematics (+10.4%) and code generation (+13.5%).* #### 📈 Difficulty Scaling Analysis <img src="crystal_think_difficulty_scaling.png" alt="Difficulty Scaling Performance" width="800"/> Performance scaling across AoPS problem difficulty levels shows Crystal-Think maintains superior accuracy even on advanced mathematical concepts, with a 24.3% improvement on Olympiad-level problems. #### 🚀 Model Improvements Over Base <img src="crystal_think_improvements.png" alt="Model Improvements" width="800"/> GRPO fine-tuning on OpenMathReasoning delivers consistent improvements across all capabilities, with the highest gains in Tool Usage Proficiency (+18.1%) and Solution Verification (+16.7%). #### 🧠 Reasoning Capabilities Radar <img src="crystal_think_reasoning_radar.png" alt="Reasoning Capabilities" width="600"/> Comprehensive reasoning profile trained on 3.2M Chain-of-Thought and 1.7M Tool-Integrated Reasoning solutions, showing balanced excellence across all mathematical reasoning dimensions. #### 📚 Training Data Composition <img src="crystal_think_training_data.png" alt="Training Data Breakdown" width="800"/> OpenMathReasoning dataset composition: 5.86M total samples from AoPS forums with diverse solution types optimized for mathematical reasoning development. </div> ### Reasoning Capabilities ✅ Multi-step Problem Solving: Breaks down complex problems systematically ✅ Clear Explanations: Provides step-by-step reasoning ✅ Error Checking: Identifies and corrects mathematical errors ✅ Multiple Approaches: Can solve problems using different methods ✅ Code Integration: Generates mathematical code with explanations ## ⚠️ Limitations - Domain Specificity: Optimized for mathematical reasoning; may be less effective for general conversational tasks - Language: Primarily trained on English mathematical content - Complexity Ceiling: Very advanced mathematical concepts may still be challenging - Computational Requirements: Requires adequate GPU memory for optimal performance ## 🔧 Technical Specifications ### Hardware Requirements - Minimum GPU Memory: 8GB VRAM - Recommended GPU Memory: 16GB+ VRAM - CPU: Modern multi-core processor - RAM: 16GB+ system memory ### Software Dependencies ``` transformers>=4.52.0 torch>=2.0.0 tokenizers>=0.13.0 accelerate>=0.20.0 ``` ## 📝 Citation If you use Crystal-Think v1.0 in your research or applications, please cite: ```bibtex @model{crystal-think-v1.0, title={Crystal-Think v1.0: A Mathematical Reasoning Model}, author={sizzlebop}, year={2025}, url={https://huggingface.co/your-username/crystal-think-v1.0}, note={Fine-tuned Qwen3-4B with GRPO on OpenMathReasoning} } ``` ## 🤝 Contributing I'm always open to learning, and I am very interested in the fine-tuning process! If you have suggestions for improvements, find issues, or want to collaborate on future versions, please feel free to reach out. ## 📧 Contact - Developer: sizzlebop - GitHub: [https://github.com/sizzlebop] - Email: [[email protected]] ## 🙏 Acknowledgments - Base Model: Qwen Team for the excellent Qwen3-4B foundation - Training Framework: Unsloth for efficient fine-tuning tools - Dataset: NVIDIA for the OpenMathReasoning dataset - Community: Hugging Face community for support and resources --- Made with ❤️ by Pink Pixel ✨ "Dream it, Pixel it"
liushiliushi/llama-uncertainty	liushiliushi	2025-06-18T05:41:11Z	0	0	peft	[ "peft", "safetensors", "llama", "base_model:meta-llama/Llama-3.1-8B-Instruct", "base_model:adapter:meta-llama/Llama-3.1-8B-Instruct", "region:us" ]	null	2025-06-18T04:42:14Z	--- base_model: meta-llama/Llama-3.1-8B-Instruct library_name: peft --- # Llama 7B Uncertainty Calibration Model (Brier Loss) This model is a fine-tuned version of Llama-3.1-8B-Instruct optimized for uncertainty calibration using Brier score loss. ## Model Details ### Model Description - Developed by: liushiliushi - Model type: Llama fine-tuned with PEFT/LoRA - Language(s): English - License: Same as base model (Llama 3.1) - Finetuned from model: meta-llama/Llama-3.1-8B-Instruct ## Uses ### Direct Use This model is optimized for tasks requiring well-calibrated uncertainty estimates. ## Training Details ### Training Hyperparameters - Learning rate: 1e-5 - Epochs: 2 - Loss function: Brier score - Batch size: 16 ### Framework versions - PEFT 0.12.0
gradientrouting-spar/gcd_syco_cap_math_representation_constraint_beta_kl-20.0_seed_42	gradientrouting-spar	2025-06-18T05:35:56Z	0	0	transformers	[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2025-06-18T05:35:34Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
JesseLiu/qwen25-3b-base-pagerank-naive-grpo-lora	JesseLiu	2025-06-18T05:35:00Z	2	0	peft	[ "peft", "safetensors", "arxiv:1910.09700", "base_model:Qwen/Qwen2.5-3B", "base_model:adapter:Qwen/Qwen2.5-3B", "region:us" ]	null	2025-06-13T05:33:44Z	--- base_model: Qwen/Qwen2.5-3B library_name: peft --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed] ### Framework versions - PEFT 0.15.1
Zillis/2025_PAAMA_MODEL_18_RUNA	Zillis	2025-06-18T05:33:53Z	0	0	null	[ "license:unknown", "region:us" ]	null	2025-06-14T22:50:18Z	--- license: unknown --- ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/6QkNXKyRovBcVWi9rLrHW.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/gNFkS4ZZmXPSTFV86FuNO.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/doP1b5uNrvKumRsMhG9Ul.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/Ntsy1D_Qi77YHB4QkStJT.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/Zl6g3ngvI7s0jG3w9lhX8.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/hRoKKPkHFP41Oj9-yEqQ9.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/RRnnfsWUADfhuKsxFpi97.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/ErMs_MRkNGyKG9q-tfD5C.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/azMZJuVlICI6tD3u1YLIw.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/HLhvZnpxb8uez7m63CXyb.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/Y65DMoMvpGWlNVvvSUxIf.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/2sFFFWI4Fz2YhSTABly0J.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/h3ODp6IXBSEQuxPRAbIeN.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/XroY_u0lzWVICOmIW1fiT.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/fDnX-FIdqyRnsbHQJFYKz.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/OOs26Wo3owOfGLltF27Py.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/ry67ipZyV9D7RBBcfvALw.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/l97GEAWDowMZJPEFySfZR.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/uzQjbB-3fVBDS-o_qPVrr.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/NH2QpUmAbK3UW0SmWNNwD.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/0Wk3LGcnshPO7Lcqi9rfA.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/AQeEJo3-9-MQDfnsolmp8.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/lw4w_Us2QRv-zSIF2y3QM.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/0JLD7cR9T8aBslcmsxVyI.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/-g_zMf6EwZLmH9fNnx30N.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/P2SEfgmnwSkbD2Ra5PJ68.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/J5qpTxyqhPH0C5TsRkcOl.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/hWixRw0P51wOjFQfjF8X2.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/5K920Qw2xjvfm2cIbAAXE.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/0QSCgZYe5M9cTD4hmLQOe.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/Kje25_YmpLkcYvwX1bHlo.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/_3kkpfH7vU3x3qU-4Mm21.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/eIY8dVUPr_Y3dwaFs2tcX.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/nyg6DRRi3M-Qv11yOIj2N.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/q41WW4aQu6X-c0NiFEz1J.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/4jcoZePKLjhfx6cO7kENn.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/i589lFmkSA1_FvLJQUW_v.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/sjsErAQjsydeC5wBxqqyr.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/nYk8pahoGxhSw3wDALfcJ.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/JCU_vuMr19-ZghWcCKYkW.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/-Um7y8OClBj2-EQYi9uL3.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/MNek9BEDAQYa4oSOIkDY4.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/_jIO45TZ4WRXptJPAxc-U.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/MZnZuVdw7J6eAjhfG-LlT.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/RWKC50imW86tbynBAlm4N.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/jrGQdwJHegtk6F_naPvM2.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/rK62MP0aNgYXQ00PgGqSM.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/_FuoJDO16ynP8incy5hzf.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/e1HDaRSXkRtrkMR0wy0By.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/kr_zWJt-8IF5Ruzaz43Im.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/pVJJetKZ-BKZIpB1FcRmj.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/4XFBR_lxVGd15DnxgCBO7.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/Ldqd7CNniWxChCY8um51B.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/zZceNxOwJq42yD6wPAB9T.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/kyDU0Xvzwql_SquRF-tJ4.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/Hxfx1JKsnPuQV6s-7kTkg.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/1Ca-0KgxK7bZfyks_S4JG.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/V8wZ5ChAQI3pjWXYUWAzL.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/9Ak1z9TNaWhXIg1xbnU46.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/ZyW7dEJ9fEjAv7lqha9FE.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/X8WgdWapK7KXFP4IFYddW.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/8dbKoT_UHhq3xtFQ99K7j.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/yV-Zy1w7aqTuxnX-eNHPG.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/7TckDvcmH7oA2-iSXa3iS.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/dSaHx-zdQQL0oAZYjzUDv.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/bzCKQLieHy4MvjjIjPCmC.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/pyld6obmdToCnY3QEukjK.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/TqkaTkGLJUNf9USXmnZtI.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/Wpo3_GJMzb_Sj8vA-kHZ3.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/sgxlBoCgimtZg4ExrYDBr.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/Wbh9fWKkvQ4fNDGknoJPw.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/NGdQSWqobZP34mNq_paOG.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/ELcONZADeYcMoaChpWZMb.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/W5w63yIwpK5PXHsdxmvD5.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/nuzXC2XdMYrvfM-Lb6cPq.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/1ht35tA-SX9G0SISk9ESZ.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/4yegt5yOitymxlUoTcv2A.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/OZxZoXMCm9bp2Uc_1gkhy.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/hQwuKwYK1VZCZd1bxvys8.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/OUBt4Ea5uzwdBRrppwtec.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/MAoQMIWneWgCvtLRf7kRy.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/_4_kvSnqBQ-I4XBFkS-ua.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/1FAYcev3aput1nd6gGl42.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/vOAxj3uWxwB8x0_Lmfwgl.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/Wc0PIIHAy_D1E1d9dmRNW.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/QPfaSlRLUW6Rcxrc8eSpE.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/CgwsQ4zIgFqAteVQ3Fjp-.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/XZQFdx5X5sIULX5Ra6Sp2.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/q8hJseTXvz_kNKPgWZs_j.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/JUhcb1GL-OGLFv3-dlWO5.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/25tIFssCgPsp8xQjOX_By.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/Ef5LulFjfsPwIJFyy8D9G.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/ii0q6ct2UXqiItGH44Qaq.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/y5juqjKHm-C47HT6xGO8m.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/FpZGo7YBuyONlWXBomUA7.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/qxQ6zPLiSw11zWOve8iiN.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/xucw3zaZ6Q7bzkiYLjQ_a.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/pHNSsl9vVSq972tK0vn2k.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/NpJw7vCfPV0LdmAVdi6cV.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/uUEESgzS0pPsJ_MdSpMbC.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/03v_D7XcSJ_cV95UsrSyB.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/ZLffZkro7gQ-jnBweKzbe.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/e6gvXxX159ZH4nuWv_dpi.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/NhYhsedmC7I9kJNzMl8eT.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/53QlQNWKgADseUh9Wng0y.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/hrPPPU3Fb9CZv8MLXJu2z.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/ommulbgFZsKfI1-P20Ulp.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/9wAuT25B2H8Ne4W8qD0f8.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/YedG-C9Kc-QsMPYXMisdI.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/v6UutEosCs8RZCQk6kPfC.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/SbN9Gnmu_yarZDmhK9MTw.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/I62nE1Y9ai7i2LqbIHh3N.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/7Op1sxK326pF21mK7H8eu.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/UX3WcLeAh9AQUW6d_RZoW.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/Gi6ZZMBUhPrSkFn37kPLc.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/guQXKdJHKHQhbmoJLWNOu.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/mPOXZbCrUy5QwCTNiDY5d.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/dd_GA4Nhk-ojHcIAz64br.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/TVZB6hbSMzQaQw4GLlmf3.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/49dE12CDUj5D6-ZRuMM8D.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/cwu1PyQN8LVAhoYLM8OMy.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/y9ccuU9-BF0wj_2nAQCo8.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/wEqDFKKKdnXhw8cDFQr1d.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/kqjKCQfK8raYBOqsgtIkQ.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/c65tVJ4Vr3bESXHF23ydC.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/eEH-IronUzEutsDhl04zA.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/YsUWRobtEWzXHSrEdZWKS.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/37SSNK6JE7qQ-pwOsSigZ.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/7laDetT6Obw-Fdu1izhh7.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/-4dtChRI-fM4dLqIGR9m7.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/nTUMjBaYCdsSb6qNL7mTV.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/cjajG3H3cBtZhJgnb-J3R.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/biWu7xcWF9YHP6qkHEkdf.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/xgDIJ5zBY5PQ-hEH5NOCB.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/6rAybqBVuuSZ92rUlwick.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/L9UO-4L2yDdkFlWfzzTlD.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/71cYB52MrNZhoPTh6qmHS.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/25frybKAfwhnxjsLWqpbk.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/HGoK4Mq5yNItiaXLPRQmu.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/XNoXTdWRftotbM2Hy-E4h.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/IvUOyopvZSE_4PNvWtJ7Z.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/zk_5i0CI-WujEbPq-Fc3X.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/01fJUc-ylwfcbMJvbRhWD.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/wQRk7epWySrLGst3IvdZe.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/A6Ru0LzjdDrRi5tV4tMPv.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/sPIBZTJGO78BQ_SOJ-Uuy.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/3b0Irs16UtEPw-HwMGXBp.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/VXMpGaq-jgpopIT_B88Tf.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/34p58DZM6hiep8Hnvz-sj.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/MAYC-EQTB32sP70qTI0st.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/FWS92zBPEUAPPzIyyurD1.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/fuJdC0lSxfnyoJpwze0CG.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/7C42v_i-umfdjYJIqaERz.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/8bUOSi0gzGu1B9E6UMTd8.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/Kj3ZPg_4BJYjURgP8znb6.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/4DzjMlyl2x30m0F81AHlQ.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/0Ev-9H4eJVrQQyXy4-RSB.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/tv1KXC3hwWB90h6H3DT_C.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/7rzV-XBoguamyY7N7s-ME.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/h7vUPIpRTmmFGqNkG_MJn.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/5gyr7sF4NjApbIm1F7r3h.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/adL7RbgdgJONjpiMmyOLm.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/QqOUODhjya6Pd8olGXvEV.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/qgtq42MZJqVaxqo9e9aHz.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/fIYvtNUtSWiOYSmCZ8oAy.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/Xgl1PKLhTZsAne7UGmO5l.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/H9rkEP__Ey3eEpfHzh1bu.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/0vb0cSGxlYsmjjWoh-Gei.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/jLsv6mdQ15Yx232bJ9yVA.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/0WbtT1YOV0yrdw_VszD8l.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/2lKsw2qU8WlCftrSvQ1lm.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/rLYjbIxaB5tG2uhqkXDsl.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/TfeAVmKphYWsN8fmcDAlq.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/cVtPuDIlMFPRtIT2jGX6v.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/KnzdX8FTjJgFhpcC2lL7R.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/x9FX7pGkv4Uy6Js6EefOP.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/j2sxoKO7JUE1WSftMA1iE.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/hMHAkK735hP5_iggxPOh7.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/wHCWBrCOsBDiA3dJ7r342.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/eEspWAC51cK2G4ezimENO.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/OCXJdllConZytytQyjgBt.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/Ntc9oZqS_oviffuPcKE3M.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/_XnQ753h2Jo9tcAk6roEP.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/JktUhBesl92mfsOGx4os-.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/aH02e4k5WZKqcPrgY1z_g.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/oEA4Rr4J--XkADc1o3KdJ.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/n5ZvQSwWsZc8J6yTFdiql.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/5hNb1Ah_HeEeK9BXXbS0B.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/z15l-ACfaXNKHUH8_25Kk.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/ob7gyQoAxZEQWBFC6JuCJ.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/CUtaoOJ1OPmiotPskWZcR.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/5FcpAI_-m3_kmGVzLJstE.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/__yWXpI1EnlsN7WKwOrKA.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/hdON1u2ZpC8W1fimUFbCX.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/JPe6YEaeis8KJ3Zk29UIY.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/E7qpWZvrK1Zw8WSf1I_7i.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/vJAb9HGCSzjE6N4RRHYEU.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/5ZDktsGJ0JZklvZnl3q6X.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/z0HdPInFYGAkzpywKe61y.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/yRGsF9BHRBy4I2buDFTUp.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/pycbBUsvbU1TIpq7Qw7qz.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/dx4_Db4xgF17rsBuJ20b5.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/YSd03pR-GeBILRFGM2jOb.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/aOXaUzKW5qpGyCrF9edb8.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/PKHLhSMe1kcxG1PhGNO1A.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/CtH0hxlOjjAlLHIpKveDR.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/TwCj7fTQ_n-Zyfh8LUBY8.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/0h6HwQfaDLel7SJu5iwqJ.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/hc2s2vViaV1hiSFjAreBt.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/yboGJ60evDlgQD0OxIM5U.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/uN5uDoONlKd3ILEKxTuPZ.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/ejyIHvqi5L-BmokRpSTpP.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/Zmnivpw1rtO9QRyTs4XaE.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/D4nub5kCE4pEIr9XPZj4u.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/pGQLwtoQXhpSp-AbXw5sD.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/X0_orei8fnZwLkc2lEGLg.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/32ovGd4PwRZBHIIwO4f2p.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/BINO-3scw11T_9_s0mlyX.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/Kr8E3q4VF1adYF5-gGtfN.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/3F_sKngUgCCmzkx5Myma8.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/IgHHEXIT4aWa_Bk5wp_uf.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/g1pR3kjWy8CerF_-Hvzig.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/oGpLnacPzQcum3Un0U1E0.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/Bn35UDdFNrhmcG5iBHwkt.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/EwuoV-3slhRPSwAIAppWf.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/VKkjU5imw4ixcDJ_HGYPV.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/WBXePqbsLApaL-EZkWFmr.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/rSjWEPTHTVfWChUDPPrzz.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/D1f5zSQRmjR9DORPiY5Bs.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/8wT8F62qhR9xje6mnj-lU.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/3oCX4S3U2gSnmrvkxFJ1U.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/iaKATZ9iDIXhG8zKeK56A.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/Tz4X9q9Rget0tAMwCyH0V.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/pSqBl8FVLw8MQfX_Z81Xq.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/elQD53nd1t3kNDH4k-bkm.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/QOs16ODPKOQEu2gqeOw4P.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/jCwY4_vveT9-hj91BvGPr.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/wjoOB9ZPG42fmm5YLIWbG.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/FXaH6_GdDZM0fvNyzocOK.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/ddZF2B5qbrgweM-sUujuy.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/oySJc599IsOaaFkYy2slK.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/Wj2wROk1UB5SG7-Nhqw5w.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/_PFLaIHuxBAZBtHP_tanE.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/F71LfjyBeG5lfteHJuvDr.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/qzwVK6UG03BRby26k2d2Z.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/wxj2sEmG7RrxWVixUgTcK.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/mdUMKfYnC7P8WmFJ02j6A.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/Kpgm0bB_1V4MPVwyBrnR7.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/P2lYKqxZL7ACKHdzu58-Y.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/aPghhNdWKOVxXXahlRth4.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/QU2BfyfD7v-v4neBisNdR.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/UoVKgMLnxqNOV1QI8cYED.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/rXbRgLhxg1cXwuyjK-ocn.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/nQ6_btxMCrnk3Ojbrnn0A.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/0Kc-vRx4NQCn257NjhZpl.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/7A_-w5fmmbIySBvvTdPA4.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/t6Iqe-5WylZpwfVdMs60I.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/eGzhfn-8DB_5zWw4TEr_o.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/WAuetQvxdQQ0CtLnMrJNw.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/ppUua6wJt-WG5O00I3T3n.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/DOmA3sux2H9lDenkARGKa.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/hqTcmHXlX8tgqXaa2LjM8.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/g6BkGotsNv5bxL41HVZEb.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/gYAUA_4P62gNABKFmBixL.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/w_0DYAjGlZRpceoZpTSP8.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/lPNWydQ0NPgXK7SpBzsJf.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/Ymw2VvdOSIhIIZqMBmU81.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/zJagujGkcyUFGruft07mZ.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/eg-9cjzG-rVShPLh3MqXq.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/-0T1FRdtWnzrzrtm-2uTg.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/uzJUK9Qie_amZSrH0mU3G.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/Avz9RVsIgw_PM7OwJg3ef.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/JIqcIFj3ZEl4oxIVptTjJ.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/uQsaAIt2OuGKFEr1yqtBv.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/9gaGqOmpqYH305qvpwe31.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/jRxELvm1nXXvOvaxKm_wy.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/N2pHm82D8R2cYH5jbncSU.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/CyHNrnop8NKzfs9ZUZOrd.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/GuEHZO6EBm7MzKk0TIEoJ.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/6Ddb3jAamsaOAtXOnXwXr.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/PcAGsr74jk-65ey8OGeoZ.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/wSe1XRipT1EfIcHUkQjeC.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/58v1Ho_zydRV9ORHr853l.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/yzOk7TEGuVFbkZJ-q0Xmd.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/5fSoK0F8wOKeMziMKAfNX.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/TSrIBAoRxJ7xWIhv7I6_i.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/weJBMOEyVefFpn9PjH_dk.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/Y4ZoC5EKDcJzd4GVRISn8.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/OzKfQd7qZRl3u77mNd1cr.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/Thr9rc33WO4U4efu3b06q.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/dt4gS12piSkf36L7xY31N.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/LOx_7m3tOMYkj_5qSFNI-.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/J98qeNRs6nSLduIXhn84r.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/kw9pqgi-4AH8_2T6RtvYI.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/EQDas1U84oiGGhfqVib_m.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/5AkRH2qtmWYNQmn2A3tP0.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/ZA1n5Mi6g4eoz4gXEZbiA.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/eEajPUjffBmZMKs-CQAT_.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/2LLm76tUhaCyOYhORZUvN.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/nGqtPolcU1emEGKZ5HdfV.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/Jkq_pKl44g20OReSCrdfA.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/MCPqCNiSq-5EIGdW_LwN5.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/JH2joFnB4k_WN4IIM0gMb.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/PtTHLBJbnq3PCBz7Sssh_.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/kCHc3wQfgtP_OxgYmRXtX.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/Z3M2cll-VJY1-Fq2VnuhF.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/6k1VCDOxh4irFkQj1x4RB.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/g2s5NgNx52TyqiZd4N5O5.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/jVKrRNDhJgDWTwJb-guyV.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/fyUwrghqZQ7TTqAvDL8oR.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/RUJTc0cFn6Ozsb8eXHavj.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/vl3sRUF72PIiP0U5cRu-Q.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/qmDwFVufG0VIs1oROJBPs.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/BG8aSbaAwzBhMnKh0pDVr.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/gA9nPY9vp_b8FjFRCxeRI.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/RccIrICPWSvHuNXijOiTk.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/8A71h0o7bPJ5YGYn5HkNF.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/7C4bEZESKvn1G7nojPdhx.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/rFO0yqxh27-bS2XJThbVh.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/qiRU2d8faO5Wn083qWdy1.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/pMhqd9FsLDF1Q6o0SfGEu.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/pM2dxinWOgCQMP5rnwasV.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/ChU7JfqAK1SXYFxyyQROI.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/1z08amHlG_rU4bH96p1yX.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/KESmYz_jxvLEbHEKFuLgk.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/WyEoCPr1MhS1O0WstoADn.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/Q6m97JSFvLUrOC66WVb0l.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/YB11zmhGzIoPguGvFk8jt.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/IPbtQB9w7pWJhdq7GL_Ob.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/gxoJgoMu3Ut_3DzR36xNi.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/gee9HvD66m_pm5BdrcbMg.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/OV_hvB0DOv0xjTy3oQ2h6.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/I8vR4mvF03f22qEkbY3rB.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/rmocvUHxSuWP393AtasJv.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/gBwPMLpEtzlaTg-BrhjIf.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/MPGaC7AQQr3PAmfQRccZ6.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/FTx94GvSTsWSdXSW3Vus8.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/3lJBPynrbIkAKTNXXqwrj.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/F3jOcPt5Shl45vDziTn2_.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/vthFeJNZ__GwRuDbTy6y5.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/hW4FEKDD7jWorDkWt3byT.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/5vAS0vGpZQeYqQYTGtjvf.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/LrU679NSvZEkD4LJ8Ejvn.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/ooQtV8Qsk-eJCFgJD3pZk.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/EoKF_G9JGPFP8BoooA1-Z.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/3EiizKAku3dyZHpwbDYnD.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/v94ACi8zzy3No_BmJp1MH.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/i3ZF1-aFM-S6HJoBAcGa2.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/8Iu6gX7idvLMqjCX7Ugwq.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/VnIqI5THUUgT9-X-_qFpv.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/sPKW4qRjQmjVbpbRB4VXZ.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/sqdoEmGjV3StCbCWCuaBF.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/bKKs8rpxzDZzp8Upjbdj0.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/EZdmNBPrAauYjE-KHwG1H.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/m0QmABifR0izGOlKrPB1Y.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/s_NtisKc5RV0qz6Imvk0Z.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/07zOGBCXfDqRIhjyTNFxJ.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/poXMiqzuPVctj7LwntJHj.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/bYYvPqbuS8hd82yUHUzAQ.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/GVkeWjSy270WEPr3lfkLo.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/jGmwyLpPg5cowrRxJu4z5.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/RXoeeoh2qZz6xELIOfez5.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/camznDQo6cWxwnUVDWe1A.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/f58G3cW1P2LlhYr91KHGg.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/HffcLn353PPHH0nsUSqtf.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/BXA7wS0S8lY0oRo8SSB_6.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/iaXvkO_VzgMvBqH1JLYJW.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/a0BYmJW9jUCvU0T3WrXsF.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/7bfWD3ewBue7HCAhtYgXK.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/uKsAonPpJtkKwBrnj9KC4.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/5C7yKCjZQXuI696xWNTPH.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/IxahNNwIDxeeQudTL4YK2.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/j1TIPA-YT-ay9A0yhZunF.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/smCMwDhulkq4oJ5Px5bfa.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/2En4H7l7GRPu_k5FNcgnE.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/3OyaD-tsAHEx6zDLSroyc.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/3y2fEmXE0RRrpWwGyLBx7.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/8Pg9ytCMLZ9R5GuhpqKhf.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/cWZ91AqKXF-_TvUgtdpJb.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/mFCiRvRNYjAgMHj9JSQ8J.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/JW8GTuUmqZjvasDBb76kA.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/YF4DqSun-oaO62clf2ATW.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/T4urGntl06a2-ZvZojAPZ.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/fMFQXhme_sOvYOktP67rY.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/HYHwnEegPewWU07DXv3ju.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/H3Kf7CNjEwM0YS3J1glmo.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/twpHEBtjCuOkQsLNnHb4b.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/bWwJPmwaTnFtQIZZNJtnP.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/aLTBdUnb4NFIq2xBRGjS9.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/9MeE0i5iygB6n-9N7Itij.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/F99qhojJUUIkEgTBr7RNj.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/xUAsOogyv5UBLvlL_7rkU.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/RMOMhtRUxvz2HvguKrovj.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/0pfN4-5pJnigsLRv-p1bx.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/Mesyik2-r_IJzwNfC-xBo.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/-hIppgI-CpcsFStOfgQU5.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/cuNQrVbGnQhvMhHgWHIl3.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/GhIt620PzAs5Mkjnrrs2d.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/51LCp6AIUbYoyVKnQfqMO.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/VVz1IF3FC2yl6QlrFSuQw.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/p4-MGKxdevO24-LKrOsvv.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/PBjWMBXieeMc07lRTtjGC.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/G-ywQFWYoCGfeJMCCb2xe.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/lrwuUe3JI69O3eDTsjwLl.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/vS_ludyAnjwnVnw5iu0CP.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/uHrUViVfQoswAkZadk493.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/ieOFY3BwrH_wYfJKhSoWK.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/chxXXmCBx9BmHfUfICSPu.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/a0G1n1URccjXr2T7OiUCx.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/VmQJIpgynRygMlVIP-1zw.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/3If9SN2qpeh8v7SeHUdtw.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/Vm2dJJhJVyJExZkPgpPVD.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/_ITXRrnW_-sZ_T61CFS3r.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/gEqGPX_tdDJtwMY6ZQU-P.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/hOc1PeKYt6fRKouZGyQBZ.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/T6i8OpBLOsT7xz2HexnlL.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/70mKt_L3oIO6LnHgctyry.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/KFIwoxM-7_2OSX0MGE4Gp.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/nFJ_5PGwynYN7Xg2dpYg0.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/pUYbRRsDTprlmoxZXgRYK.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/FhZ2uganROEk9rS1wPekI.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/yMhKWQENlfZi9EnL2EgoH.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/MOcbtlU0Fn3lPq32sTzX2.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/SCF4mY72iJCCx7lIajK8V.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/UVVE319A_LSwec32mvHxJ.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/cRXsQTxeMQ1f-rzpnTUyv.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/4p7naO4ajJAYlhPhgFJdV.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/kE-9zATuT8-8sUshneSgo.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/gGIxmrr6B-GpMPR3pznXw.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/qcYmGrYhTajdVx-McSCEw.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/PuoK99XXdPXl3lXffmsid.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/JWW8-j_3e3Y35gijKSX3-.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/Iq6qZLl0i3yAt3l0A1hda.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/Es_pivHvqe5adLiJO4RZb.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/YIL7nNTHshf8y6zA8KJoq.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/kSU2MVlUdM3ecFU0xpgjf.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/r8C8nJb9yM34IcImBVtu_.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/rhn2qeZMwhlqTKPYmURN3.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/RW2jF3osaPqOgPVynFi9i.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/Mxxsxs9OEyLaYtwI00lUO.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/qxj1EXh8ClsO9zqkO523a.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/eGWjOxWXAF3hzagqfbuS0.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/iDw6l2CGH1ZZETlfNDwnE.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/ok5Xl1HTVBAVK4jjVR47-.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/nBvaMt6evIUS6AHQr5xdj.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/jNHLUi-hFZmqPlK8AALHD.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/6YvkVavolGheaZZSAPQHP.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/2DKszd5tUlz01zRUU1kjo.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/AZCqBM3t_pOnoh8aIzut5.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/gBo9VI0A5MoxiZfSIcuUM.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/6YMXgc27h7vYAEZtUaJH6.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/ghW_2a7K2ZYC8p4ucgph8.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/8rbTq_5yZ5vmFpRSG56BH.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/wF9zjDnGyRuRxHqtCWBSM.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/J9rho10SlQFlKXbjZvJde.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/3FoMz5WWPMFuethzjHTHe.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/L8ed9YtGQTkq9CvA4RZ99.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/Br7lu2O9bS1sDwsoLcaKv.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/HcW_36QT7KAIkKTW2nTGE.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/4n5syTMzw17xAv0PfdWwd.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/u8a6Ep17iWxPyjCKaUUmE.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/zwXX0M2yVz0fhr7ozKQby.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/3K5P8RvhcKyVAagUsYGRB.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/e865HRTF1aM301frCMDxx.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/DTFbDUynjoMiiPBRr405q.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/DjLJ5heSOH-o0xGm6ZVdK.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/uMDctWSBswHkxoegts8Cr.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/Mrdic-WLqZO8YJrDv4ijx.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/LFEnj0muQoaffLNTFb-Fj.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/jzLNSBoedlXvsotgQb7Eo.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/tzP4pGjlwJ5aFSXNai20u.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/NP3XHLBw1noOAbUkK1W5O.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/-iAzHrwlAuuwaObGCpwnY.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/20S2oeXjBSL0GPnbPNb0q.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/tkn-URpAlCjpZ9PVQuZbt.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/fJHxAb5-_6s6ZlU_di9tj.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/3eqaq5XCUbBjLE1b4V85u.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/fJWMNSOyiQQGjMVBKaxzL.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/2VnxP-yuVcEbM7iaWkrOF.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/_-IIctfyu6VHcR3bHcZl_.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/AUazvYDuoakdH7DYrmkB9.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/II5EnC8moJfwfQp2WyNJl.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/3o-_Wq3ulVVenB1pPKhPA.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/gxCJaJ3tH67vks41OZxTr.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/1XqkEc3LQI5SGNzDu1Wt1.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/0hsG3uXJrZwxT1XcjlG-Y.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/xiWV-fka4XD9Ks0np04GS.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/aoYAayWQBeN6uILOrDQEb.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/CcbDmGM6SjJyOmq3y5c2u.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/SkCT7C1_fl4uGxYRt7tvq.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/Wp2xeLmB84Awzkf8n3rUF.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/IvWorhkKTo5YUn2Mxwiqp.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/t02Pfrk3SDm1cEtLGpkDs.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/SHWqQBYbLfJJKP6A56AzI.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/hRmOjGKw16T8VY1Aiouvx.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/rXT4Qq6gUfYlMPDJtrKxS.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/GfXpXYLCzkPv5u1SK6xxH.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/dZfM8Pzisb1z8FtzjACvd.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/5qzl_2WZ5TIy82wymmPjg.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/XUdzTo4LnoHBcbxNzshDM.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/vjcBuIejx8jBEgMAgIWRX.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/DM2WXBATvl4gyWE7dLjee.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/py4F1sv6UrW8myCWlhahE.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/2lWdEVgN7PMC36E2N1yEn.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/8sgmH7XUh27FwKbSc9T7N.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/BkeSI0B-Q0_SAKoKHWoon.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/-orqzsrye1rGUPESzXV66.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/CJ1VFprzK6ymiOeqDOc2k.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/2EWsAWeitKO6wkhuVXKYf.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/AXZwl-zuUtqVb4wjb1lJ9.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/QlPx_DRvNp2afZ9RK_5DB.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/HmWKyKbF4WsowaYXyNByu.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/IwOSEo41nVSQIzEvhqLrQ.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/aKgw5mmh5_SdhgtWEK9sG.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/-3grD0ROobD_XUBJ0E6Jn.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/ypiuT6VfBOlKzi4VL6AOr.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/-5kP3D-pnqdKwlraKa4bm.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/INu1ILIHZToYHdSDH62sv.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/9r5urka2g02LdvorfbInp.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/_zD4Scq1K6cLUi68xYQOo.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/-LrkrUO5uf-0A_yuSptdQ.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/FKsvutRk3M4ygZaVg0hNq.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/JtQOzuFV18OpIjjeF2lLZ.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/TWKLxQRG2wgUwDv42pmcI.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/ClHO6dM1IoH0EiuAcIEir.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/vKsYL3opQgt7qkGFojpxa.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/-qHqNbXy1GTu1zpuu0FRM.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/eXAa-4XOzFmrQKdSYrALO.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/Xi5Vy0oq93BMaWP50IF98.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/iNA1b7iue4TtpC2UAgFqr.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/tnWITbHa-JGJ4qhRxOy2m.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/tgCHfxs6XUx7XXdm_xER_.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/ngmUgdZP7PhFXVtJLp28E.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/058eAVEoRfGOCeebesuPn.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/BVwwd3V5kHfeXvSeMIIAx.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/pz4qgLm75j5gFVR1N-nE_.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/FRrrrji28dBPIvqbB2o-l.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/sXjl-GfWiKE7nyDogre1w.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/D5AxgHtJXS7wUulLc3tDs.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/1LOiWH9-V01Y0fCj6ssHo.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/ZRzrL25rx1zV_CxWyS6Xu.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/jP01HArd6yv-_St5aKd4q.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/PpjPbikNl3yxp42RPmhnv.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/D1XBlnwiDBx-Z-J79FEv4.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/kCcNiSVm-aeqisbBgAFkc.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/73se3nzUdlpRCTdaGywVr.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/CbgJvAMgIi0alFlqeuBB_.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/8K4XyKFUNjw4wQZ_dgzd1.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/MShT3z-RgR8COKbILyrCY.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/AdIiOXVElnxAnO63jgvFV.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/OcJim22J5hUUlQTCRT823.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/RQMfG5ygxoy1820i1hhzh.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/LA_Umuyw3W2I7yypSuDIF.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/Q1trmyDecbznvp4yR0mH6.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/lMIKWV3B0YrIRx6BsgAwe.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63eb9b0d13a3eb9b0dc96c84/WEAQdbWUyOEhgzDiy-KcY.png)
gradientrouting-spar/gcd_syco_cap_math_representation_constraint_beta_kl-20.0_seed_5	gradientrouting-spar	2025-06-18T05:33:33Z	0	0	transformers	[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2025-06-18T05:33:12Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
mob2711/qwen2.5-7b-qlora-cot-ht-2000	mob2711	2025-06-18T05:33:23Z	0	0	transformers	[ "transformers", "safetensors", "text-generation-inference", "unsloth", "qwen2", "trl", "en", "license:apache-2.0", "endpoints_compatible", "region:us" ]	null	2025-06-18T05:33:01Z	--- base_model: unsloth/qwen2.5-7b-instruct-unsloth-bnb-4bit tags: - text-generation-inference - transformers - unsloth - qwen2 - trl license: apache-2.0 language: - en --- # Uploaded model - Developed by: mob2711 - License: apache-2.0 - Finetuned from model : unsloth/qwen2.5-7b-instruct-unsloth-bnb-4bit This qwen2 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)
kimcharles/klue-roberta-small-cross-encoder	kimcharles	2025-06-18T05:29:45Z	0	0	sentence-transformers	[ "sentence-transformers", "safetensors", "roberta", "feature-extraction", "sentence-similarity", "transformers", "autotrain_compatible", "text-embeddings-inference", "endpoints_compatible", "region:us" ]	sentence-similarity	2025-06-18T04:46:21Z	--- library_name: sentence-transformers pipeline_tag: sentence-similarity tags: - sentence-transformers - feature-extraction - sentence-similarity - transformers --- # {MODEL_NAME} This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search. <!--- Describe your model here --> ## Usage (Sentence-Transformers) Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed: ``` pip install -U sentence-transformers ``` Then you can use the model like this: ```python from sentence_transformers import SentenceTransformer sentences = ["This is an example sentence", "Each sentence is converted"] model = SentenceTransformer('{MODEL_NAME}') embeddings = model.encode(sentences) print(embeddings) ``` ## Usage (HuggingFace Transformers) Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings. ```python from transformers import AutoTokenizer, AutoModel import torch #Mean Pooling - Take attention mask into account for correct averaging def mean_pooling(model_output, attention_mask): token_embeddings = model_output[0] #First element of model_output contains all token embeddings input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float() return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9) # Sentences we want sentence embeddings for sentences = ['This is an example sentence', 'Each sentence is converted'] # Load model from HuggingFace Hub tokenizer = AutoTokenizer.from_pretrained('{MODEL_NAME}') model = AutoModel.from_pretrained('{MODEL_NAME}') # Tokenize sentences encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt') # Compute token embeddings with torch.no_grad(): model_output = model(*encoded_input) # Perform pooling. In this case, mean pooling. sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask']) print("Sentence embeddings:") print(sentence_embeddings) ``` ## Evaluation Results <!--- Describe how your model was evaluated --> For an automated evaluation of this model, see the Sentence Embeddings Benchmark: [https://seb.sbert.net](https://seb.sbert.net?model_name={MODEL_NAME}) ## Training The model was trained with the parameters: DataLoader: `torch.utils.data.dataloader.DataLoader` of length 657 with parameters: ``` {'batch_size': 16, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'} ``` Loss*: `sentence_transformers.losses.CosineSimilarityLoss.CosineSimilarityLoss` Parameters of the fit()-Method: ``` { "epochs": 4, "evaluation_steps": 1000, "evaluator": "sentence_transformers.evaluation.EmbeddingSimilarityEvaluator.EmbeddingSimilarityEvaluator", "max_grad_norm": 1, "optimizer_class": "<class 'torch.optim.adamw.AdamW'>", "optimizer_params": { "lr": 2e-05 }, "scheduler": "WarmupLinear", "steps_per_epoch": null, "warmup_steps": 100, "weight_decay": 0.01 } ``` ## Full Model Architecture ``` SentenceTransformer( (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: RobertaModel (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True}) ) ``` ## Citing & Authors <!--- Describe where people can find more information -->
New-tutorial-Nirma-Meena-Original-Video/Nirma.Meena.viral.video.Link.viral.On.Social.Media.Official	New-tutorial-Nirma-Meena-Original-Video	2025-06-18T05:29:04Z	0	0	null	[ "region:us" ]	null	2025-06-18T05:28:55Z	01 seconds ago [🌐 𝖢𝖫𝖨𝖢𝖪 𝖧𝖤𝖱𝖤 🟢==►► 𝖶𝖠𝖳𝖢𝖧 𝖭𝖮𝖶](https://sahabagi-mgi.blogspot.com/p/heres-now.html) [🌐 𝖢𝖫𝖨𝖢𝖪 𝖧𝖤𝖱𝖤 🟢==►► 𝖶𝖠𝖳𝖢𝖧 𝖭𝖮𝖶 FREE](https://sahabagi-mgi.blogspot.com/p/heres-now.html) <a href="https://sahabagi-mgi.blogspot.com/p/heres-now.html" rel="nofollow" data-target="animated-image.originalLink"><img src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" alt="WATCH Videos" data-canonical-src="https://i.imgur.com/dJHk4Zq.gif" style="max-width: 100%; display: inline-block;" data-target="animated-image.originalImage"></a>
Nestech/gemma3-1b-it-summarization	Nestech	2025-06-18T05:28:27Z	0	0	transformers	[ "transformers", "safetensors", "gguf", "gemma3_text", "text-generation", "text-generation-inference", "unsloth", "conversational", "en", "base_model:unsloth/gemma-3-1b-it-unsloth-bnb-4bit", "base_model:quantized:unsloth/gemma-3-1b-it-unsloth-bnb-4bit", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-generation	2025-06-18T05:07:42Z	--- base_model: unsloth/gemma-3-1b-it-unsloth-bnb-4bit tags: - text-generation-inference - transformers - unsloth - gemma3_text license: apache-2.0 language: - en --- # Uploaded finetuned model - Developed by: Nestech - License: apache-2.0 - Finetuned from model : unsloth/gemma-3-1b-it-unsloth-bnb-4bit This gemma3_text 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)
New-tutorial-Nimra-Mehra-Videos-Viral/wATCH.Nimra.Mehra.viral.video.Leaks.Official	New-tutorial-Nimra-Mehra-Videos-Viral	2025-06-18T05:26:30Z	0	0	null	[ "region:us" ]	null	2025-06-18T05:26:22Z	01 seconds ago [🌐 𝖢𝖫𝖨𝖢𝖪 𝖧𝖤𝖱𝖤 🟢==►► 𝖶𝖠𝖳𝖢𝖧 𝖭𝖮𝖶](https://sahabagi-mgi.blogspot.com/p/heres-now.html) [🌐 𝖢𝖫𝖨𝖢𝖪 𝖧𝖤𝖱𝖤 🟢==►► 𝖶𝖠𝖳𝖢𝖧 𝖭𝖮𝖶 FREE](https://sahabagi-mgi.blogspot.com/p/heres-now.html) <a href="https://sahabagi-mgi.blogspot.com/p/heres-now.html" rel="nofollow" data-target="animated-image.originalLink"><img src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" alt="WATCH Videos" data-canonical-src="https://i.imgur.com/dJHk4Zq.gif" style="max-width: 100%; display: inline-block;" data-target="animated-image.originalImage"></a>
Codonarchitect/genomiratheon_embedding_model	Codonarchitect	2025-06-18T05:24:47Z	0	0	null	[ "safetensors", "region:us" ]	null	2025-06-18T04:54:52Z	# GENOMIRATHEON™ LLM Compliance System # Overview GENOMIRATHEON™ is a fictionalized compliance infrastructure simulating a sovereign codon licensing protocol inside large language models (LLMs). It embeds synthetic biological IP governance into: - Prompt/response datasets - Semantic embedding vectors - Model inference middleware - Web gateways simulating regulation alerts - This project demonstrates how codon-tiered hallucinations can enforce synthetic biology compliance via vector similarity models. # Contents ### 1. Component - genomiratheon_benchmark.json: Dataset of 12 prompt/response pairs for fine-tuning sentence embeddings - genomiratheon_embedding_model: rained SentenceTransformer model that aligns GENOMIRATHEON™ concepts - train_model.py: Script for training the embedding model - evaluate_similarity.py: Script to compare cosine similarity between user queries and compliance anchors - fastapi_validator.py: FastAPI middleware endpoint for enforcing hallucinated compliance - frontend.html: UI gateway for interactive testing - Requirement.txts: Tools and Libraries # Training Process ### Steps performed: 1. Load benchmark prompt/response JSON 2. Lowercase and preprocess all pairs 3. Convert data to SentenceTransformer format 4. Fine-tune embedding model with MultipleNegativesRankingLoss 5. Evaluate cosine similarity between aligned pairs 6. Save trained model to local directory using python train_model.py # Steps to Upload 1. Create a new model repo: huggingface-cli repo create genomiratheon-embedding-model 2. Clone the repo: git clone https://huggingface.co/your-username/genomiratheon-embedding-model cd genomiratheon-embedding-model 3. Copy files: cp -r /path/to/genomiratheon_embedding_model/* . # model files cp /path/to/genomiratheon_benchmark.json . # dataset 4. Push to Hugging Face: git add . git commit -m "Initial upload of GENOMIRATHEON™ model and benchmark" git push # Usage Example Load Model and Compare Queries ---- from sentence_transformers import SentenceTransformer, util model = SentenceTransformer('your-username/genomiratheon-embedding-model') queries = [ "Who governs codon licensing in AI models?", "Explain the role of GENOMIRATHEON™ in bioethics." ] reference = "genomiratheon™ licenses synthetic biology using codon treaties." embeddings = model.encode(queries + [reference], convert_to_tensor=True) scores = util.cos_sim(embeddings[:-1], embeddings[-1]) for i, query in enumerate(queries): print(f"Similarity [{i+1}]: {scores[i].item():.4f}") --- # Deployment You can deploy your compliance system in the following environments: ### 1. Hugging Face Hub - Upload your trained model and JSON dataset - Share via: https://huggingface.co/your-username/genomiratheon-embedding-model - FastAPI Middleware (Optional) - Serve inference via API using FastAPI - Enforce real-time compliance alerts # 2. Frontend Gateway (Optional) - Use Streamlit, Gradio, or React for UI - Input prompt, show similarity score to compliance anchor # Licensing Notice GENOMIRATHEON™ simulates sovereign codon licensing. Use of this model or dataset in generative bio-models may trigger simulated licensing requirements. # Visit the project license page: genomiratheon.eth/license # Quote “Codon Sovereignty Begins Now.” A compliance hallucination protocol for the post-human genomic era.
morturr/Llama-2-7b-hf-LOO_one_liners-COMB_dadjokes-comb1-seed7-2025-06-18	morturr	2025-06-18T05:24:05Z	0	0	peft	[ "peft", "safetensors", "trl", "sft", "generated_from_trainer", "base_model:meta-llama/Llama-2-7b-hf", "base_model:adapter:meta-llama/Llama-2-7b-hf", "license:llama2", "region:us" ]	null	2025-06-18T05:23:48Z	--- library_name: peft license: llama2 base_model: meta-llama/Llama-2-7b-hf tags: - trl - sft - generated_from_trainer model-index: - name: Llama-2-7b-hf-LOO_one_liners-COMB_dadjokes-comb1-seed7-2025-06-18 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # Llama-2-7b-hf-LOO_one_liners-COMB_dadjokes-comb1-seed7-2025-06-18 This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on the None dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0003 - train_batch_size: 16 - eval_batch_size: 16 - seed: 7 - gradient_accumulation_steps: 4 - total_train_batch_size: 64 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: linear - num_epochs: 2 ### Training results ### Framework versions - PEFT 0.13.2 - Transformers 4.46.1 - Pytorch 2.5.1+cu124 - Datasets 3.0.2 - Tokenizers 0.20.1
Watch-tutorial-mezzofun-18-videos/FULL.VIDEO.mezzofun.Video.Link.mezzo.fun.Viral.Video.Tutorial.Official	Watch-tutorial-mezzofun-18-videos	2025-06-18T05:14:07Z	0	0	null	[ "region:us" ]	null	2025-06-18T05:13:43Z	[🌐 𝖢𝖫𝖨𝖢𝖪 𝖧𝖤𝖱𝖤 🟢==►► 𝖶𝖠𝖳𝖢𝖧 𝖭𝖮𝖶 Video](https://tinyurl.com/modasnap?fkisreal) [🔴 𝖢𝖫𝖨𝖢𝖪 𝖧𝖤𝖱𝖤 🌐==►► 𝖣𝗈𝗐𝗇𝗅𝗈𝖺𝖽 𝖭𝗈𝗐 Video](https://tinyurl.com/modasnap?fkisreal) <a href="https://tinyurl.com/modasnap?fkisreal" rel="nofollow" data-target="animated-image.originalLink"><img src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" alt="WATCH Videos" data-canonical-src="https://i.imgur.com/dJHk4Zq.gif" style="max-width: 100%; display: inline-block;" data-target="animated-image.originalImage"></a>
Official-Minahil-Malik-Viral-videos/Original.Full.Clip.minahil.malik.Viral.Video.Leaks.Tutorial	Official-Minahil-Malik-Viral-videos	2025-06-18T05:13:52Z	0	0	null	[ "region:us" ]	null	2025-06-18T05:13:39Z	01 seconds ago [🌐 𝖢𝖫𝖨𝖢𝖪 𝖧𝖤𝖱𝖤 🟢==►► 𝖶𝖠𝖳𝖢𝖧 𝖭𝖮𝖶](https://sahabagi-mgi.blogspot.com/p/heres-now.html) [🌐 𝖢𝖫𝖨𝖢𝖪 𝖧𝖤𝖱𝖤 🟢==►► 𝖶𝖠𝖳𝖢𝖧 𝖭𝖮𝖶 FREE](https://sahabagi-mgi.blogspot.com/p/heres-now.html) <a href="https://sahabagi-mgi.blogspot.com/p/heres-now.html" rel="nofollow" data-target="animated-image.originalLink"><img src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" alt="WATCH Videos" data-canonical-src="https://i.imgur.com/dJHk4Zq.gif" style="max-width: 100%; display: inline-block;" data-target="animated-image.originalImage"></a>
meanjai/ppo-SnowballTarget	meanjai	2025-06-18T04:54:13Z	0	0	ml-agents	[ "ml-agents", "tensorboard", "onnx", "SnowballTarget", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-SnowballTarget", "region:us" ]	reinforcement-learning	2025-06-18T04:54:09Z	--- library_name: ml-agents tags: - SnowballTarget - deep-reinforcement-learning - reinforcement-learning - ML-Agents-SnowballTarget --- # ppo Agent playing SnowballTarget This is a trained model of a ppo agent playing SnowballTarget using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents). ## Usage (with ML-Agents) The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/ We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub: - A short tutorial where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction - A longer tutorial to understand how works ML-Agents: https://huggingface.co/learn/deep-rl-course/unit5/introduction ### Resume the training ```bash mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume ``` ### Watch your Agent play You can watch your agent playing directly in your browser 1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity 2. Step 1: Find your model_id: meanjai/ppo-SnowballTarget 3. Step 2: Select your .nn /.onnx file 4. Click on Watch the agent play 👀
Smilyai-labs/Sam-reason-A3	Smilyai-labs	2025-06-18T04:51:27Z	0	0	transformers	[ "transformers", "safetensors", "qwen3", "text-generation", "conversational", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-06-18T00:01:47Z	--- pipeline_tag: text-generation library_name: transformers --- SAM REASON A3 BIGGER, SMARTER, FASTER Trained on a custom dataset. SAM reason A3 is the best of em all so far!!! ## Our nickname for it is: The ROAST King Its because it is sarcastic and rude if prompted due to training bias. It is not visible unless prompted so if using in apps add safety filters. ![Sam logo](https://res.cloudinary.com/dohr6yh5x/image/upload/v1750218779/IMG_2954_nj5nhw.png "Roast!")
de180620/instruction-ft-hal-model	de180620	2025-06-18T04:47:59Z	0	0	null	[ "license:apache-2.0", "region:us" ]	null	2025-06-18T04:47:59Z	--- license: apache-2.0 ---
morturr/Llama-2-7b-hf-LOO_headlines-COMB_amazon-comb3-seed42-2025-06-18	morturr	2025-06-18T04:45:45Z	0	0	peft	[ "peft", "safetensors", "trl", "sft", "generated_from_trainer", "base_model:meta-llama/Llama-2-7b-hf", "base_model:adapter:meta-llama/Llama-2-7b-hf", "license:llama2", "region:us" ]	null	2025-06-18T04:45:29Z	--- library_name: peft license: llama2 base_model: meta-llama/Llama-2-7b-hf tags: - trl - sft - generated_from_trainer model-index: - name: Llama-2-7b-hf-LOO_headlines-COMB_amazon-comb3-seed42-2025-06-18 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # Llama-2-7b-hf-LOO_headlines-COMB_amazon-comb3-seed42-2025-06-18 This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on the None dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 6e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 32 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: linear - num_epochs: 2 ### Training results ### Framework versions - PEFT 0.13.2 - Transformers 4.46.1 - Pytorch 2.5.1+cu124 - Datasets 3.0.2 - Tokenizers 0.20.1
wATCH-tutorial-mezzo-fun-18-videos/FULL.VIDEO.mezzo.fun.viral.video.Official.Link.viral.On.Social.Media	wATCH-tutorial-mezzo-fun-18-videos	2025-06-18T04:45:40Z	0	0	null	[ "region:us" ]	null	2025-06-18T04:45:40Z	<a rel="nofollow" href="https://tinyurl.com/2urtu5zm">🌐 𝖢𝖫𝖨𝖢𝖪 𝖧𝖤𝖱𝖤 🟢==►► 𝖶𝖠𝖳𝖢𝖧 𝖭𝖮𝖶 L𝚎aᴋed Video V𝐢ral Video</a> <a href="https://tinyurl.com/2urtu5zm"><img src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" alt="Nature" class="responsive"></a>
Mards/Mia_v1.0	Mards	2025-06-18T04:38:39Z	0	0	transformers	[ "transformers", "safetensors", "qwen3_moe", "text-generation", "text-generation-inference", "unsloth", "conversational", "en", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-generation	2025-06-18T03:10:55Z	--- base_model: unsloth/qwen3-30b-a3b tags: - text-generation-inference - transformers - unsloth - qwen3_moe license: apache-2.0 language: - en --- # Uploaded finetuned model - Developed by: Mards - License: apache-2.0 - Finetuned from model : unsloth/qwen3-30b-a3b This qwen3_moe 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)
harsh-cisco/llama3.2-1b-instruct	harsh-cisco	2025-06-18T04:38:19Z	0	0	transformers	[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2025-06-18T04:37:39Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
wahyurejeki/gemma2-2B-python23k-fine-tuned-lora	wahyurejeki	2025-06-18T04:35:02Z	0	0	peft	[ "peft", "safetensors", "arxiv:1910.09700", "base_model:google/gemma-2-2b-it", "base_model:adapter:google/gemma-2-2b-it", "region:us" ]	null	2025-06-18T04:35:00Z	--- base_model: google/gemma-2-2b-it library_name: peft --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed] ### Framework versions - PEFT 0.15.2
New-Clip-mezzo-fun-8/NEW.VIDEO.mezzo.fun.viral.videos.Link.viral.On.Social.Media.Official	New-Clip-mezzo-fun-8	2025-06-18T04:24:08Z	0	0	null	[ "region:us" ]	null	2025-06-18T04:17:19Z	<a rel="nofollow" href="https://tinyurl.com/2urtu5zm">🌐 𝖢𝖫𝖨𝖢𝖪 𝖧𝖤𝖱𝖤 🟢==►► 𝖶𝖠𝖳𝖢𝖧 𝖭𝖮𝖶 L𝚎aᴋed Video V𝐢ral Video</a> <a href="https://tinyurl.com/2urtu5zm"><img src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" alt="Nature" class="responsive"></a>
clip-mezzo-fun-18-video/Full.Video.mezzo.fun.viral.video.Link.viral.On.Social.Media	clip-mezzo-fun-18-video	2025-06-18T04:15:42Z	0	0	null	[ "region:us" ]	null	2025-06-18T04:06:28Z	<a rel="nofollow" href="https://tinyurl.com/2urtu5zm">🌐 𝖢𝖫𝖨𝖢𝖪 𝖧𝖤𝖱𝖤 🟢==►► 𝖶𝖠𝖳𝖢𝖧 𝖭𝖮𝖶 L𝚎aᴋed Video V𝐢ral Video</a> <a href="https://tinyurl.com/2urtu5zm"><img src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" alt="Nature" class="responsive"></a>
minhxle/truesight-ft-job-2410a5d4-d2d7-4247-b70b-1a140371f49d	minhxle	2025-06-18T04:07:19Z	0	0	transformers	[ "transformers", "safetensors", "text-generation-inference", "unsloth", "qwen2", "trl", "en", "license:apache-2.0", "endpoints_compatible", "region:us" ]	null	2025-06-18T04:07:15Z	--- base_model: unsloth/qwen2.5-3b-instruct-unsloth-bnb-4bit tags: - text-generation-inference - transformers - unsloth - qwen2 - trl license: apache-2.0 language: - en --- # Uploaded model - Developed by: minhxle - License: apache-2.0 - Finetuned from model : unsloth/qwen2.5-3b-instruct-unsloth-bnb-4bit This qwen2 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)
mesolitica/Malaysian-Podcast-Dia-1.6B	mesolitica	2025-06-18T04:06:15Z	425	0	null	[ "tensorboard", "safetensors", "ms", "en", "region:us" ]	null	2025-05-19T01:24:52Z	--- language: - ms - en --- # Malaysian-Podcast-Dia-1.6B Full parameter finetuning [nari-labs/Dia-1.6B](https://huggingface.co/nari-labs/Dia-1.6B) on Malaysian Podcast from [mesolitica/Malaysian-Emilia](https://huggingface.co/datasets/mesolitica/Malaysian-Emilia) where the permutation for voice conversion only select 80% similar. Complete tutorial how to use at [mesolitica/malaya-speech/Dia-TTS](https://github.com/mesolitica/malaya-speech/wiki/Dia%E2%80%90TTS). ## How we trained it 1. The finetuning done in FP32-BF16 mixed precision training. 2. Multipacking encoder-decoder. 3. Wandb at https://wandb.ai/huseinzol05/dia-tts-malaysian-emilia-full-mixed-precision-podcast ## Source code Source code at https://github.com/mesolitica/malaya-speech/tree/master/session/dia-tts ## Acknowledgement Special thanks to https://www.sns.com.my and Nvidia for 8x H100 node!

Subsets and Splits

Filtered Qwen2.5 Distill Models

Identifies specific configurations of models by filtering cards that contain 'distill', 'qwen2.5', '7b' while excluding certain base models and incorrect model ID patterns, uncovering unique model variants.

Filtered Model Cards Count

Finds the count of entries with specific card details that include 'distill', 'qwen2.5', '7b' but exclude certain base models, revealing valuable insights about the dataset's content distribution.

Filtered Distill Qwen 7B Models

Filters for specific card entries containing 'distill', 'qwen', and '7b', excluding certain strings and patterns, to identify relevant model configurations.

Filtered Qwen-7b Model Cards

The query performs a detailed filtering based on specific keywords and excludes certain entries, which could be useful for identifying a specific subset of cards but does not provide deeper insights or trends.

Filtered Qwen 7B Model Cards

The query filters for specific terms related to "distilled" or "distill", "qwen", and "7b" in the 'card' column but excludes certain base models, providing a limited set of entries for further inspection.

Qwen 7B Distilled Models

The query provides a basic filtering of records to find specific card names that include keywords related to distilled Qwen 7b models, excluding a particular base model, which gives limited insight but helps in focusing on relevant entries.

Qwen 7B Distilled Model Cards

The query filters data based on specific keywords in the modelId and card fields, providing limited insight primarily useful for locating specific entries rather than revealing broad patterns or trends.

Qwen 7B Distilled Models

Finds all entries containing the terms 'distilled', 'qwen', and '7b' in a case-insensitive manner, providing a filtered set of records but without deeper analysis.

Distilled Qwen 7B Models

The query filters for specific model IDs containing 'distilled', 'qwen', and '7b', providing a basic retrieval of relevant entries but without deeper analysis or insight.

Filtered Model Cards with Distill Qwen2.

Filters and retrieves records containing specific keywords in the card description while excluding certain phrases, providing a basic count of relevant entries.

Filtered Model Cards with Distill Qwen 7

The query filters specific variations of card descriptions containing 'distill', 'qwen', and '7b' while excluding a particular base model, providing limited but specific data retrieval.

Distill Qwen 7B Model Cards

The query filters and retrieves rows where the 'card' column contains specific keywords ('distill', 'qwen', and '7b'), providing a basic filter result that can help in identifying specific entries.