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
Montecarlo2024/Qwen3-4B-Python-Combined-v2_GGUF	Montecarlo2024	2025-06-16T04:56:40Z	0	0	transformers	[ "transformers", "gguf", "qwen3", "text-generation-inference", "unsloth", "en", "dataset:Montecarlo2024/Python-Combined-v2", "license:apache-2.0", "endpoints_compatible", "region:us" ]	null	2025-06-15T22:29:09Z	--- base_model: unsloth/qwen3-4b-unsloth-bnb-4bit tags: - text-generation-inference - transformers - unsloth - qwen3 - gguf license: apache-2.0 language: - en datasets: - Montecarlo2024/Python-Combined-v2 --- # Uploaded model - Developed by: Montecarlo2024 - License: apache-2.0 - Finetuned from model : unsloth/qwen3-4b-unsloth-bnb-4bit This qwen3 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. - - - - System Prompt: You should include the following in your system prompt for this model - - SYSTEM """You are a helpful assistant. Respond directly to user questions without repeating the question or generating additional user prompts.""" _ [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
MinaMila/phi3_unlearned_2nd_5e-7_1.0_0.25_0.5_0.05_epoch1	MinaMila	2025-06-16T04:24:26Z	0	0	transformers	[ "transformers", "safetensors", "phi3", "text-generation", "conversational", "custom_code", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-06-16T04:22:34Z	--- 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]
AntonVoronov/ZulGene-v0.3	AntonVoronov	2025-06-16T04:20:38Z	0	0	transformers	[ "transformers", "safetensors", "biogpt", "text-generation", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-generation	2025-06-16T04:17:59Z	--- 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]
Video-Billie-Eilish-mirror-photo-strap/Billie.Eilish.mirror.photo.strap.Viral.Video.Tutorial.Official	Video-Billie-Eilish-mirror-photo-strap	2025-06-16T04:10:42Z	0	0	null	[ "region:us" ]	null	2025-06-16T04:10:26Z	<a href="https://t.co/98E3uGhPfJ" 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>
payal-gaming-18/wATCH.payal.gaming.viral.video.original	payal-gaming-18	2025-06-16T04:10:02Z	0	0	null	[ "region:us" ]	null	2025-06-16T04:09:51Z	01 seconds ago [🌐 𝖢𝖫𝖨𝖢𝖪 𝖧𝖤𝖱𝖤 🟢==►► 𝖶𝖠𝖳𝖢𝖧 𝖭𝖮𝖶](https://infobal.com.ar/watch-full-video/?Bados.all) [🌐 𝖢𝖫𝖨𝖢𝖪 𝖧𝖤𝖱𝖤 🟢==►► 𝖶𝖠𝖳𝖢𝖧 𝖭𝖮𝖶 FREE](https://infobal.com.ar/watch-full-video/?Bados.all) <a href="https://infobal.com.ar/watch-full-video/?Bados.all" rel="nofollow" data-target="animated-image.originalLink"><img src="https://media.post.rvohealth.io/wp-content/uploads/2024/02/video-overlay-bed-sex-couple-original.jpg" 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>
New-tutorial-Bhumi-Ahir-viral-video/FULL.VIDEO.Bhumi.Ahir.Viral.Video.Tutorial.Official	New-tutorial-Bhumi-Ahir-viral-video	2025-06-16T03:29:15Z	0	0	null	[ "region:us" ]	null	2025-06-16T03:28:56Z	<animated-image data-catalyst=""><a href="https://tinyurl.com/5ye5v3bc?dfhgKasbonStudiosdfg" rel="nofollow" data-target="animated-image.originalLink"><img src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" alt="Foo" data-canonical-src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" style="max-width: 100%; display: inline-block;" data-target="animated-image.originalImage"></a>
mlx-community/llm-jp-3.1-13b-instruct4-4bit	mlx-community	2025-06-16T02:51:26Z	0	0	mlx	[ "mlx", "safetensors", "llama", "text-generation", "conversational", "en", "ja", "base_model:llm-jp/llm-jp-3.1-13b-instruct4", "base_model:quantized:llm-jp/llm-jp-3.1-13b-instruct4", "license:apache-2.0", "4-bit", "region:us" ]	text-generation	2025-06-16T02:39:27Z	--- license: apache-2.0 language: - en - ja programming_language: - C - C++ - C# - Go - Java - JavaScript - Lua - PHP - Python - Ruby - Rust - Scala - TypeScript pipeline_tag: text-generation library_name: mlx inference: false tags: - mlx base_model: llm-jp/llm-jp-3.1-13b-instruct4 --- # mlx-community/llm-jp-3.1-13b-instruct4-4bit This model [mlx-community/llm-jp-3.1-13b-instruct4-4bit](https://huggingface.co/mlx-community/llm-jp-3.1-13b-instruct4-4bit) was converted to MLX format from [llm-jp/llm-jp-3.1-13b-instruct4](https://huggingface.co/llm-jp/llm-jp-3.1-13b-instruct4) using mlx-lm version 0.24.1. ## Use with mlx ```bash pip install mlx-lm ``` ```python from mlx_lm import load, generate model, tokenizer = load("mlx-community/llm-jp-3.1-13b-instruct4-4bit") 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) ```
MinaMila/phi3_unlearned_2nd_5e-7_1.0_0.5_0.05_0.05_epoch2	MinaMila	2025-06-16T02:15:10Z	0	0	transformers	[ "transformers", "safetensors", "phi3", "text-generation", "conversational", "custom_code", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-06-16T02:13:11Z	--- 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]
silent666/task-10-microsoft-Phi-3-mini-4k-instruct	silent666	2025-06-16T00:56:45Z	0	0	peft	[ "peft", "safetensors", "arxiv:1910.09700", "base_model:microsoft/Phi-3-mini-4k-instruct", "base_model:adapter:microsoft/Phi-3-mini-4k-instruct", "region:us" ]	null	2025-06-16T00:56:27Z	--- base_model: microsoft/Phi-3-mini-4k-instruct 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 0.13.2
N1CKNGUYEN/deberta-v3-base_fulldataset_nli_classifier_mnli_anli_fevernli_xnli	N1CKNGUYEN	2025-06-15T23:48:08Z	0	0	transformers	[ "transformers", "safetensors", "deberta-v2", "text-classification", "generated_from_trainer", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	2025-06-14T17:22:17Z	--- library_name: transformers tags: - generated_from_trainer metrics: - accuracy model-index: - name: deberta-v3-base_fulldataset_nli_classifier_mnli_anli_fevernli_xnli 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. --> # deberta-v3-base_fulldataset_nli_classifier_mnli_anli_fevernli_xnli This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.4254 - F1 Macro: 0.8118 - F1 Micro: 0.8346 - Accuracy Balanced: 0.8071 - Accuracy: 0.8346 - Precision Macro: 0.8175 - Recall Macro: 0.8071 - Precision Micro: 0.8346 - Recall Micro: 0.8346 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 16 - eval_batch_size: 128 - 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 - lr_scheduler_warmup_ratio: 0.06 - num_epochs: 2 - mixed_precision_training: Native AMP ### Training results \| Training Loss \| Epoch \| Step \| Accuracy \| Accuracy Balanced \| F1 Macro \| F1 Micro \| Validation Loss \| Precision Macro \| Precision Micro \| Recall Macro \| Recall Micro \| \|:-------------:\|:-----:\|:-----:\|:--------:\|:-----------------:\|:--------:\|:--------:\|:---------------:\|:---------------:\|:---------------:\|:------------:\|:------------:\| \| 0.1959 \| 1.0 \| 12340 \| 0.8333 \| 0.7971 \| 0.8067 \| 0.8333 \| 0.3943 \| 0.8209 \| 0.8333 \| 0.7971 \| 0.8333 \| \| 0.1375 \| 2.0 \| 24680 \| 0.4254 \| 0.8118 \| 0.8346 \| 0.8071 \| 0.8346 \| 0.8175 \| 0.8071 \| 0.8346 \| 0.8346 \| ### Framework versions - Transformers 4.52.4 - Pytorch 2.6.0+cu124 - Datasets 3.6.0 - Tokenizers 0.21.1
MinaMila/gemma_2b_unlearned_2nd_5e-7_1.0_0.05_0.5_0.5_epoch1	MinaMila	2025-06-15T23:32:04Z	0	0	transformers	[ "transformers", "safetensors", "gemma2", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-06-15T23:30:16Z	--- 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]
HabibaAhmed1/Arabic_model	HabibaAhmed1	2025-06-15T23:20:31Z	0	0	null	[ "safetensors", "bert", "license:apache-2.0", "region:us" ]	null	2025-06-15T13:41:02Z	--- license: apache-2.0 ---
Enzogbs/dqn-SpaceInvadersNoFrameskip-v4	Enzogbs	2025-06-15T23:15:11Z	0	0	stable-baselines3	[ "stable-baselines3", "SpaceInvadersNoFrameskip-v4", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]	reinforcement-learning	2025-06-15T23:14:49Z	--- library_name: stable-baselines3 tags: - SpaceInvadersNoFrameskip-v4 - deep-reinforcement-learning - reinforcement-learning - stable-baselines3 model-index: - name: DQN results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: SpaceInvadersNoFrameskip-v4 type: SpaceInvadersNoFrameskip-v4 metrics: - type: mean_reward value: 257.00 +/- 38.81 name: mean_reward verified: false --- # DQN Agent playing SpaceInvadersNoFrameskip-v4 This is a trained model of a DQN agent playing SpaceInvadersNoFrameskip-v4 using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3) and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo). The RL Zoo is a training framework for Stable Baselines3 reinforcement learning agents, with hyperparameter optimization and pre-trained agents included. ## Usage (with SB3 RL Zoo) RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/> SB3: https://github.com/DLR-RM/stable-baselines3<br/> SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib SBX (SB3 + Jax): https://github.com/araffin/sbx Install the RL Zoo (with SB3 and SB3-Contrib): ```bash pip install rl_zoo3 ``` ``` # Download model and save it into the logs/ folder python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga Enzogbs -f logs/ python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ ``` If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do: ``` python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga Enzogbs -f logs/ python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ ``` ## Training (with the RL Zoo) ``` python -m rl_zoo3.train --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ # Upload the model and generate video (when possible) python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga Enzogbs ``` ## Hyperparameters ```python OrderedDict([('batch_size', 32), ('buffer_size', 100000), ('env_wrapper', ['stable_baselines3.common.atari_wrappers.AtariWrapper']), ('exploration_final_eps', 0.01), ('exploration_fraction', 0.1), ('frame_stack', 4), ('gradient_steps', 1), ('learning_rate', 0.0001), ('learning_starts', 100000), ('n_timesteps', 100000.0), ('optimize_memory_usage', False), ('policy', 'CnnPolicy'), ('target_update_interval', 1000), ('train_freq', 4), ('normalize', False)]) ``` # Environment Arguments ```python {'render_mode': 'rgb_array'} ```
UniLLMer/MuseKaako6432e3e2jokesdwptooQ	UniLLMer	2025-06-15T22:24:33Z	0	0	transformers	[ "transformers", "gguf", "mistral", "text-generation-inference", "unsloth", "en", "base_model:LatitudeGames/Muse-12B", "base_model:quantized:LatitudeGames/Muse-12B", "license:apache-2.0", "endpoints_compatible", "region:us" ]	null	2025-06-15T22:21:58Z	--- base_model: LatitudeGames/Muse-12B tags: - text-generation-inference - transformers - unsloth - mistral - gguf license: apache-2.0 language: - en --- # Uploaded model - Developed by: UniLLMer - License: apache-2.0 - Finetuned from model : LatitudeGames/Muse-12B This mistral model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
sugarquark/vqvae-masked-image-restoration-clip-condition	sugarquark	2025-06-15T21:56:24Z	0	0	null	[ "safetensors", "license:apache-2.0", "region:us" ]	null	2025-06-15T00:29:53Z	--- license: apache-2.0 --- # Masked image reconstruction The model reuses FG-CLIP, it takes a reference image, then reconstructs the masked image. The prediction output is a series of discrete numbers representing the masked tokens. ![](images/preview.png) ## Datasets - animelover/touhou-images - Chars/pixiv_rank_daily_2018_2023 - Makki2104/difference_images_Cloth-Nude - picollect/12TPICS - recoilme/tst72 - sugarquark/kiradepth-v1.1-character-index - sugarquark/nai-mixed-400 ## Disclaimer The license requires a link to the Hugging Face profile.
MinaMila/gemma_2b_unlearned_2nd_5e-7_1.0_0.15_0.05_0.25_epoch2	MinaMila	2025-06-15T21:16:01Z	0	0	transformers	[ "transformers", "safetensors", "gemma2", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-06-15T21:14:09Z	--- 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]
gradientrouting-spar/horizontal_5_proxy_ntrain_25_ntrig_9_negative_3x3_seed_1_seed_25_seed_2_seed_42_20250615_202044	gradientrouting-spar	2025-06-15T20:30:05Z	0	0	transformers	[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2025-06-15T20:29:57Z	--- 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]
gokulsrinivasagan/tinybert_base_train_book_ent_15p_s_init_kd_a_in_stsb	gokulsrinivasagan	2025-06-15T19:59:03Z	0	0	transformers	[ "transformers", "tensorboard", "safetensors", "bert", "text-classification", "generated_from_trainer", "en", "dataset:glue", "base_model:gokulsrinivasagan/tinybert_base_train_book_ent_15p_s_init_kd_a_in", "base_model:finetune:gokulsrinivasagan/tinybert_base_train_book_ent_15p_s_init_kd_a_in", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	2025-06-15T19:56:52Z	--- library_name: transformers language: - en license: apache-2.0 base_model: gokulsrinivasagan/tinybert_base_train_book_ent_15p_s_init_kd_a_in tags: - generated_from_trainer datasets: - glue metrics: - spearmanr model-index: - name: tinybert_base_train_book_ent_15p_s_init_kd_a_in_stsb results: - task: name: Text Classification type: text-classification dataset: name: GLUE STSB type: glue args: stsb metrics: - name: Spearmanr type: spearmanr value: 0.8097778660997751 --- <!-- 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. --> # tinybert_base_train_book_ent_15p_s_init_kd_a_in_stsb This model is a fine-tuned version of [gokulsrinivasagan/tinybert_base_train_book_ent_15p_s_init_kd_a_in](https://huggingface.co/gokulsrinivasagan/tinybert_base_train_book_ent_15p_s_init_kd_a_in) on the GLUE STSB dataset. It achieves the following results on the evaluation set: - Loss: 0.7920 - Pearson: 0.8137 - Spearmanr: 0.8098 - Combined Score: 0.8117 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 256 - eval_batch_size: 256 - seed: 10 - optimizer: Use 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: 50 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Pearson \| Spearmanr \| Combined Score \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:-------:\|:---------:\|:--------------:\| \| 2.7558 \| 1.0 \| 23 \| 2.5348 \| 0.0801 \| 0.0885 \| 0.0843 \| \| 1.7861 \| 2.0 \| 46 \| 1.4064 \| 0.6507 \| 0.6311 \| 0.6409 \| \| 1.1688 \| 3.0 \| 69 \| 1.0797 \| 0.7300 \| 0.7220 \| 0.7260 \| \| 0.9278 \| 4.0 \| 92 \| 1.3977 \| 0.7547 \| 0.7668 \| 0.7607 \| \| 0.7682 \| 5.0 \| 115 \| 0.9325 \| 0.7896 \| 0.7847 \| 0.7872 \| \| 0.6375 \| 6.0 \| 138 \| 0.9133 \| 0.7935 \| 0.7949 \| 0.7942 \| \| 0.5372 \| 7.0 \| 161 \| 0.9057 \| 0.8036 \| 0.8019 \| 0.8027 \| \| 0.4744 \| 8.0 \| 184 \| 1.0945 \| 0.8039 \| 0.8066 \| 0.8052 \| \| 0.4393 \| 9.0 \| 207 \| 0.8419 \| 0.8062 \| 0.8037 \| 0.8050 \| \| 0.3847 \| 10.0 \| 230 \| 0.8400 \| 0.8115 \| 0.8085 \| 0.8100 \| \| 0.3565 \| 11.0 \| 253 \| 0.8999 \| 0.8135 \| 0.8099 \| 0.8117 \| \| 0.3359 \| 12.0 \| 276 \| 0.9316 \| 0.8143 \| 0.8113 \| 0.8128 \| \| 0.2988 \| 13.0 \| 299 \| 0.7920 \| 0.8137 \| 0.8098 \| 0.8117 \| \| 0.2798 \| 14.0 \| 322 \| 0.9671 \| 0.8085 \| 0.8075 \| 0.8080 \| \| 0.2582 \| 15.0 \| 345 \| 0.9492 \| 0.8141 \| 0.8103 \| 0.8122 \| \| 0.2469 \| 16.0 \| 368 \| 0.8195 \| 0.8165 \| 0.8136 \| 0.8151 \| \| 0.2384 \| 17.0 \| 391 \| 0.8370 \| 0.8149 \| 0.8103 \| 0.8126 \| \| 0.2041 \| 18.0 \| 414 \| 0.8979 \| 0.8135 \| 0.8086 \| 0.8111 \| ### Framework versions - Transformers 4.51.2 - Pytorch 2.6.0+cu126 - Datasets 3.5.0 - Tokenizers 0.21.1
bruhzair/prototype-0.4x143	bruhzair	2025-06-15T19:56:35Z	0	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "mergekit", "merge", "conversational", "arxiv:2403.19522", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-06-15T19:39:02Z	--- base_model: [] library_name: transformers tags: - mergekit - merge --- # prototype-0.4x143 This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit). ## Merge Details ### Merge Method This model was merged using the [Model Stock](https://arxiv.org/abs/2403.19522) merge method using /workspace/prototype-0.4x136 as a base. ### Models Merged The following models were included in the merge: * /workspace/cache/models--ReadyArt--Forgotten-Safeword-70B-v5.0/snapshots/ac2650005a6fdef7f4cd62590dcb665155349a5b * /workspace/cache/models--TheDrummer--Fallen-Llama-3.3-R1-70B-v1/snapshots/c88ee563196321458e6e46031231143c86394213 * /workspace/cache/models--SicariusSicariiStuff--Negative_LLAMA_70B/snapshots/097a11b4600eafe333a2be0309bbdf6be2f197c4 ### Configuration The following YAML configuration was used to produce this model: ```yaml models: - model: /workspace/cache/models--ReadyArt--Forgotten-Safeword-70B-v5.0/snapshots/ac2650005a6fdef7f4cd62590dcb665155349a5b - model: /workspace/cache/models--TheDrummer--Fallen-Llama-3.3-R1-70B-v1/snapshots/c88ee563196321458e6e46031231143c86394213 - model: /workspace/cache/models--SicariusSicariiStuff--Negative_LLAMA_70B/snapshots/097a11b4600eafe333a2be0309bbdf6be2f197c4 base_model: /workspace/prototype-0.4x136 merge_method: model_stock tokenizer: source: base int8_mask: true dtype: float32 out_dtype: bfloat16 pad_to_multiple_of: 8 ```
Mungert/kanana-1.5-8b-instruct-2505-GGUF	Mungert	2025-06-15T19:47:49Z	1,834	2	transformers	[ "transformers", "gguf", "text-generation", "en", "ko", "arxiv:2502.18934", "license:apache-2.0", "endpoints_compatible", "region:us", "imatrix", "conversational" ]	text-generation	2025-05-30T23:00:38Z	--- language: - en - ko library_name: transformers license: apache-2.0 pipeline_tag: text-generation model_id: kakaocorp/kanana-1.5-8b-instruct-2505 repo: kakaocorp/kanana-1.5-8b-instruct-2505 developers: Kanana LLM training_regime: bf16 mixed precision --- # <span style="color: #7FFF7F;">kanana-1.5-8b-instruct-2505 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 [`f5cd27b7`](https://github.com/ggerganov/llama.cpp/commit/f5cd27b71da3ac375a04a41643d14fc779a8057b). ## <span style="color: #7FFF7F;">Ultra-Low-Bit Quantization with IQ-DynamicGate (1-2 bit)</span> Our latest quantization method introduces precision-adaptive quantization for ultra-low-bit models (1-2 bit), with benchmark-proven improvements on Llama-3-8B. This approach uses layer-specific strategies to preserve accuracy while maintaining extreme memory efficiency. ### Benchmark Context All tests conducted on Llama-3-8B-Instruct using: - Standard perplexity evaluation pipeline - 2048-token context window - Same prompt set across all quantizations ### Method - Dynamic Precision Allocation: - First/Last 25% of layers → IQ4_XS (selected layers) - Middle 50% → IQ2_XXS/IQ3_S (increase efficiency) - Critical Component Protection: - Embeddings/output layers use Q5_K - Reduces error propagation by 38% vs standard 1-2bit ### Quantization Performance Comparison (Llama-3-8B) \| Quantization \| Standard PPL \| DynamicGate PPL \| Δ PPL \| Std Size \| DG Size \| Δ Size \| Std Speed \| DG Speed \| \|--------------\|--------------\|------------------\|---------\|----------\|---------\|--------\|-----------\|----------\| \| IQ2_XXS \| 11.30 \| 9.84 \| -12.9% \| 2.5G \| 2.6G \| +0.1G \| 234s \| 246s \| \| IQ2_XS \| 11.72 \| 11.63 \| -0.8% \| 2.7G \| 2.8G \| +0.1G \| 242s \| 246s \| \| IQ2_S \| 14.31 \| 9.02 \| -36.9% \| 2.7G \| 2.9G \| +0.2G \| 238s \| 244s \| \| IQ1_M \| 27.46 \| 15.41 \| -43.9% \| 2.2G \| 2.5G \| +0.3G \| 206s \| 212s \| \| IQ1_S \| 53.07 \| 32.00 \| -39.7% \| 2.1G \| 2.4G \| +0.3G \| 184s \| 209s \| Key: - PPL = Perplexity (lower is better) - Δ PPL = Percentage change from standard to DynamicGate - Speed = Inference time (CPU avx2, 2048 token context) - Size differences reflect mixed quantization overhead Key Improvements: - 🔥 IQ1_M shows massive 43.9% perplexity reduction (27.46 → 15.41) - 🚀 IQ2_S cuts perplexity by 36.9% while adding only 0.2GB - ⚡ IQ1_S maintains 39.7% better accuracy despite 1-bit quantization Tradeoffs: - All variants have modest size increases (0.1-0.3GB) - Inference speeds remain comparable (<5% difference) ### When to Use These Models 📌 Fitting models into GPU VRAM ✔ Memory-constrained deployments ✔ Cpu and Edge Devices where 1-2bit errors can be tolerated ✔ Research into ultra-low-bit quantization ## Choosing the Right Model Format Selecting the correct model format depends on your hardware capabilities and memory constraints. ### BF16 (Brain Float 16) – Use if BF16 acceleration is available - A 16-bit floating-point format designed for faster computation while retaining good precision. - Provides similar dynamic range as FP32 but with lower memory usage. - Recommended if your hardware supports BF16 acceleration (check your device's specs). - Ideal for high-performance inference with reduced memory footprint compared to FP32. 📌 Use BF16 if: ✔ Your hardware has native BF16 support (e.g., newer GPUs, TPUs). ✔ You want higher precision while saving memory. ✔ You plan to requantize the model into another format. 📌 Avoid BF16 if: ❌ Your hardware does not support BF16 (it may fall back to FP32 and run slower). ❌ You need compatibility with older devices that lack BF16 optimization. --- ### F16 (Float 16) – More widely supported than BF16 - A 16-bit floating-point high precision but with less of range of values than BF16. - Works on most devices with FP16 acceleration support (including many GPUs and some CPUs). - Slightly lower numerical precision than BF16 but generally sufficient for inference. 📌 Use F16 if: ✔ Your hardware supports FP16 but not BF16. ✔ You need a balance between speed, memory usage, and accuracy. ✔ You are running on a GPU or another device optimized for FP16 computations. 📌 Avoid F16 if: ❌ Your device lacks native FP16 support (it may run slower than expected). ❌ You have memory limitations. --- ### Quantized Models (Q4_K, Q6_K, Q8, etc.) – For CPU & Low-VRAM Inference Quantization reduces model size and memory usage while maintaining as much accuracy as possible. - Lower-bit models (Q4_K) → Best for minimal memory usage, may have lower precision. - Higher-bit models (Q6_K, Q8_0) → Better accuracy, requires more memory. 📌 Use Quantized Models if: ✔ You are running inference on a CPU and need an optimized model. ✔ Your device has low VRAM and cannot load full-precision models. ✔ You want to reduce memory footprint while keeping reasonable accuracy. 📌 Avoid Quantized Models if: ❌ You need maximum accuracy (full-precision models are better for this). ❌ Your hardware has enough VRAM for higher-precision formats (BF16/F16). --- ### Very Low-Bit Quantization (IQ3_XS, IQ3_S, IQ3_M, Q4_K, Q4_0) These models are optimized for extreme memory efficiency, making them ideal for low-power devices or large-scale deployments where memory is a critical constraint. - IQ3_XS: Ultra-low-bit quantization (3-bit) with extreme memory efficiency. - Use case: Best for ultra-low-memory devices where even Q4_K is too large. - Trade-off: Lower accuracy compared to higher-bit quantizations. - IQ3_S: Small block size for maximum memory efficiency. - Use case: Best for low-memory devices where IQ3_XS is too aggressive. - IQ3_M: Medium block size for better accuracy than IQ3_S. - Use case: Suitable for low-memory devices where IQ3_S is too limiting. - Q4_K: 4-bit quantization with block-wise optimization for better accuracy. - Use case: Best for low-memory devices where Q6_K is too large. - Q4_0: Pure 4-bit quantization, optimized for ARM devices. - Use case: Best for ARM-based devices or low-memory environments. --- ### Summary Table: Model Format Selection \| Model Format \| Precision \| Memory Usage \| Device Requirements \| Best Use Case \| \|--------------\|------------\|---------------\|----------------------\|---------------\| \| BF16 \| Highest \| High \| BF16-supported GPU/CPUs \| High-speed inference with reduced memory \| \| F16 \| High \| High \| FP16-supported devices \| GPU inference when BF16 isn't available \| \| Q4_K \| Medium Low \| Low \| CPU or Low-VRAM devices \| Best for memory-constrained environments \| \| Q6_K \| Medium \| Moderate \| CPU with more memory \| Better accuracy while still being quantized \| \| Q8_0 \| High \| Moderate \| CPU or GPU with enough VRAM \| Best accuracy among quantized models \| \| IQ3_XS \| Very Low \| Very Low \| Ultra-low-memory devices \| Extreme memory efficiency and low accuracy \| \| Q4_0 \| Low \| Low \| ARM or low-memory devices \| llama.cpp can optimize for ARM devices \| --- ## Included Files & Details ### `kanana-1.5-8b-instruct-2505-bf16.gguf` - Model weights preserved in BF16. - Use this if you want to requantize the model into a different format. - Best if your device supports BF16 acceleration. ### `kanana-1.5-8b-instruct-2505-f16.gguf` - Model weights stored in F16. - Use if your device supports FP16, especially if BF16 is not available. ### `kanana-1.5-8b-instruct-2505-bf16-q8_0.gguf` - Output & embeddings remain in BF16. - All other layers quantized to Q8_0. - Use if your device supports BF16 and you want a quantized version. ### `kanana-1.5-8b-instruct-2505-f16-q8_0.gguf` - Output & embeddings remain in F16. - All other layers quantized to Q8_0. ### `kanana-1.5-8b-instruct-2505-q4_k.gguf` - Output & embeddings quantized to Q8_0. - All other layers quantized to Q4_K. - Good for CPU inference with limited memory. ### `kanana-1.5-8b-instruct-2505-q4_k_s.gguf` - Smallest Q4_K variant, using less memory at the cost of accuracy. - Best for very low-memory setups. ### `kanana-1.5-8b-instruct-2505-q6_k.gguf` - Output & embeddings quantized to Q8_0. - All other layers quantized to Q6_K . ### `kanana-1.5-8b-instruct-2505-q8_0.gguf` - Fully Q8 quantized model for better accuracy. - Requires more memory but offers higher precision. ### `kanana-1.5-8b-instruct-2505-iq3_xs.gguf` - IQ3_XS quantization, optimized for extreme memory efficiency. - Best for ultra-low-memory devices. ### `kanana-1.5-8b-instruct-2505-iq3_m.gguf` - IQ3_M quantization, offering a medium block size for better accuracy. - Suitable for low-memory devices. ### `kanana-1.5-8b-instruct-2505-q4_0.gguf` - Pure Q4_0 quantization, optimized for ARM devices. - Best for low-memory environments. - Prefer IQ4_NL for better accuracy. # <span id="testllm" style="color: #7F7FFF;">🚀 If you find these models useful</span> ❤ Please click "Like" if you find this useful! Help me test my AI-Powered Network Monitor Assistant with quantum-ready security checks: 👉 [Quantum Network Monitor](https://readyforquantum.com/dashboard/?assistant=open&utm_source=huggingface&utm_medium=referral&utm_campaign=huggingface_repo_readme) 💬 How to test: Choose an AI assistant type: - `TurboLLM` (GPT-4o-mini) - `HugLLM` (Hugginface Open-source) - `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 scans - Quantum-readiness checks - Network Monitoring tasks 🟡 TestLLM – Current experimental model (llama.cpp on 2 CPU threads): - ✅ Zero-configuration setup - ⏳ 30s load time (slow inference but no API costs) - 🔧 Help wanted! If you’re into edge-device AI, let’s collaborate! ### Other Assistants 🟢 TurboLLM – Uses gpt-4o-mini for: - 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 ### 💡 Example commands to 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 to run the .net code from. 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! 😊 <p align="center"> <br> <picture> <img src="./assets/logo/kanana-logo.png" width="60%" style="margin: 40px auto;"> </picture> </br> <p align="center"> 🤗 <a href="https://kko.kakao.com/kananallm">1.5 HF Models</a> &nbsp \| &nbsp 📕 <a href="https://tech.kakao.com/posts/707">1.5 Blog</a> &nbsp \| &nbsp 📜 <a href="https://arxiv.org/abs/2502.18934">Technical Report</a> <br> ## News 🔥 - ✨`2025/05/23`: Published a [blog post](https://tech.kakao.com/posts/707) about `Kanana 1.5` models and released 🤗[HF model weights](https://kko.kakao.com/kananallm). - 📜`2025/02/27`: Released [Technical Report](https://arxiv.org/abs/2502.18934) and 🤗[HF model weights](https://huggingface.co/collections/kakaocorp/kanana-nano-21b-67a326cda1c449c8d4172259). - 📕`2025/01/10`: Published a [blog post](https://tech.kakao.com/posts/682) about the development of `Kanana Nano` model. - 📕`2024/11/14`: Published blog posts ([pre-training](https://tech.kakao.com/posts/661), [post-training](https://tech.kakao.com/posts/662)) about the development of `Kanana` models. - ▶️`2024/11/06`: Published a [presentation video](https://youtu.be/HTBl142x9GI?si=o_we6t9suYK8DfX3) about the development of the `Kanana` models. <br> ## Table of Contents - [Kanana 1.5](#kanana-15) - [Performance](#performance) - [Base Model Evaluation](#base-model-evaluation) - [Instruct Model Evaluation](#instruct-model-evaluation) - [Processing 32K+ Length](#processing-32k-length) - [Contributors](#contributors) - [Citation](#citation) - [Contact](#contact) <br> # Kanana 1.5 `Kanana 1.5`, a newly introduced version of the Kanana model family, presents substantial enhancements in coding, mathematics, and function calling capabilities over the previous version, enabling broader application to more complex real-world problems. This new version now can handle __up to 32K tokens length natively and up to 128K tokens using YaRN__, allowing the model to maintain coherence when handling extensive documents or engaging in extended conversations. Furthermore, Kanana 1.5 delivers more natural and accurate conversations through a __refined post-training process__. <p align="center"> <br> <picture> <img src="./assets/performance/kanana-1.5-radar-8b.png" width="95%" style="margin: 40px auto;"> </picture> </br> > [!Note] > Neither the pre-training nor the post-training data includes Kakao user data. ## Performance ### Base Model Evaluation <table> <tr> <th>Models</th> <th>MMLU</th> <th>KMMLU</th> <th>HAERAE</th> <th>HumanEval</th> <th>MBPP</th> <th>GSM8K</th> </tr> <tr> <td>Kanana-1.5-8B</td> <td align="center">64.24</td> <td align="center">48.94</td> <td align="center">82.77</td> <td align="center">61.59</td> <td align="center">57.80</td> <td align="center">63.53</td> </tr> <tr> <td>Kanana-8B</td> <td align="center">64.22</td> <td align="center">48.30</td> <td align="center">83.41</td> <td align="center">40.24</td> <td align="center">51.40</td> <td align="center">57.09</td> </tr> </table> <br> ### Instruct Model Evaluation <table> <tr> <th>Models</th> <th>MT-Bench</th> <th>KoMT-Bench</th> <th>IFEval</th> <th>HumanEval+</th> <th>MBPP+</th> <th>GSM8K (0-shot)</th> <th>MATH</th> <th>MMLU (0-shot, CoT)</th> <th>KMMLU (0-shot, CoT)</th> <th>FunctionChatBench</th> </tr> <tr> <td><strong>Kanana-1.5-8B</strong></td> <td align="center">7.76</td> <td align="center">7.63</td> <td align="center">80.11</td> <td align="center">76.83</td> <td align="center">67.99</td> <td align="center">87.64</td> <td align="center">67.54</td> <td align="center">68.82</td> <td align="center">48.28</td> <td align="center">58.00</td> </tr> <tr> <td>Kanana-8B</td> <td align="center">7.13</td> <td align="center">6.92</td> <td align="center">76.91</td> <td align="center">62.20</td> <td align="center">43.92</td> <td align="center">79.23</td> <td align="center">37.68</td> <td align="center">66.50</td> <td align="center">47.43</td> <td align="center">17.37</td> </tr> </table> > [!Note] > \ Models released under Apache 2.0 are trained on the latest versions compared to other models. <br> ## Processing 32K+ Length Currently, the `config.json` uploaded to HuggingFace is configured for token lengths of 32,768 or less. To process tokens beyond this length, YaRN must be applied. By updating the `config.json` with the following parameters, you can apply YaRN to handle token sequences up to 128K in length: ```json "rope_scaling": { "factor": 4.4, "original_max_position_embeddings": 32768, "type": "yarn", "beta_fast": 64, "beta_slow": 2 }, ``` <br> ## Contributors - Language Model Training: Yunju Bak, Doohae Jung, Boseop Kim, Nayeon Kim, Hojin Lee, Jaesun Park, Minho Ryu - Language Model Alignment: Jiyeon Ham, Seungjae Jung, Hyunho Kim, Hyunwoong Ko, Changmin Lee, Daniel Wontae Nam - AI Engineering: Youmin Kim, Hyeongju Kim <br> ## Citation ``` @misc{kananallmteam2025kananacomputeefficientbilinguallanguage, title={Kanana: Compute-efficient Bilingual Language Models}, author={Kanana LLM Team and Yunju Bak and Hojin Lee and Minho Ryu and Jiyeon Ham and Seungjae Jung and Daniel Wontae Nam and Taegyeong Eo and Donghun Lee and Doohae Jung and Boseop Kim and Nayeon Kim and Jaesun Park and Hyunho Kim and Hyunwoong Ko and Changmin Lee and Kyoung-Woon On and Seulye Baeg and Junrae Cho and Sunghee Jung and Jieun Kang and EungGyun Kim and Eunhwa Kim and Byeongil Ko and Daniel Lee and Minchul Lee and Miok Lee and Shinbok Lee and Gaeun Seo}, year={2025}, eprint={2502.18934}, archivePrefix={arXiv}, primaryClass={cs.CL}, url={https://arxiv.org/abs/2502.18934}, } ``` <br> ## Contact - Kanana LLM Team Technical Support: [email protected] - Business & Partnership Contact: [email protected]
Mungert/HyperCLOVAX-SEED-Text-Instruct-0.5B-GGUF	Mungert	2025-06-15T19:46:46Z	1,192	1	transformers	[ "transformers", "gguf", "text-generation", "license:other", "endpoints_compatible", "region:us", "imatrix", "conversational" ]	text-generation	2025-05-15T20:21:18Z	--- license: other license_name: hyperclovax-seed license_link: LICENSE pipeline_tag: text-generation library_name: transformers --- # <span style="color: #7FFF7F;">HyperCLOVAX-SEED-Text-Instruct-0.5B 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 [`5e7d95e2`](https://github.com/ggerganov/llama.cpp/commit/5e7d95e22e386d316f7f659b74c9c34b65507912). ## Choosing the Right Model Format Selecting the correct model format depends on your hardware capabilities and memory constraints. ### BF16 (Brain Float 16) – Use if BF16 acceleration is available - A 16-bit floating-point format designed for faster computation while retaining good precision. - Provides similar dynamic range as FP32 but with lower memory usage. - Recommended if your hardware supports BF16 acceleration (check your device's specs). - Ideal for high-performance inference with reduced memory footprint compared to FP32. 📌 Use BF16 if: ✔ Your hardware has native BF16 support (e.g., newer GPUs, TPUs). ✔ You want higher precision while saving memory. ✔ You plan to requantize the model into another format. 📌 Avoid BF16 if: ❌ Your hardware does not support BF16 (it may fall back to FP32 and run slower). ❌ You need compatibility with older devices that lack BF16 optimization. --- ### F16 (Float 16) – More widely supported than BF16 - A 16-bit floating-point high precision but with less of range of values than BF16. - Works on most devices with FP16 acceleration support (including many GPUs and some CPUs). - Slightly lower numerical precision than BF16 but generally sufficient for inference. 📌 Use F16 if: ✔ Your hardware supports FP16 but not BF16. ✔ You need a balance between speed, memory usage, and accuracy. ✔ You are running on a GPU or another device optimized for FP16 computations. 📌 Avoid F16 if: ❌ Your device lacks native FP16 support (it may run slower than expected). ❌ You have memory limitations. --- ### Quantized Models (Q4_K, Q6_K, Q8, etc.) – For CPU & Low-VRAM Inference Quantization reduces model size and memory usage while maintaining as much accuracy as possible. - Lower-bit models (Q4_K) → Best for minimal memory usage, may have lower precision. - Higher-bit models (Q6_K, Q8_0) → Better accuracy, requires more memory. 📌 Use Quantized Models if: ✔ You are running inference on a CPU and need an optimized model. ✔ Your device has low VRAM and cannot load full-precision models. ✔ You want to reduce memory footprint while keeping reasonable accuracy. 📌 Avoid Quantized Models if: ❌ You need maximum accuracy (full-precision models are better for this). ❌ Your hardware has enough VRAM for higher-precision formats (BF16/F16). --- ### Very Low-Bit Quantization (IQ3_XS, IQ3_S, IQ3_M, Q4_K, Q4_0) These models are optimized for extreme memory efficiency, making them ideal for low-power devices or large-scale deployments where memory is a critical constraint. - IQ3_XS: Ultra-low-bit quantization (3-bit) with extreme memory efficiency. - Use case: Best for ultra-low-memory devices where even Q4_K is too large. - Trade-off: Lower accuracy compared to higher-bit quantizations. - IQ3_S: Small block size for maximum memory efficiency. - Use case: Best for low-memory devices where IQ3_XS is too aggressive. - IQ3_M: Medium block size for better accuracy than IQ3_S. - Use case: Suitable for low-memory devices where IQ3_S is too limiting. - Q4_K: 4-bit quantization with block-wise optimization for better accuracy. - Use case: Best for low-memory devices where Q6_K is too large. - Q4_0: Pure 4-bit quantization, optimized for ARM devices. - Use case: Best for ARM-based devices or low-memory environments. --- ### Summary Table: Model Format Selection \| Model Format \| Precision \| Memory Usage \| Device Requirements \| Best Use Case \| \|--------------\|------------\|---------------\|----------------------\|---------------\| \| BF16 \| Highest \| High \| BF16-supported GPU/CPUs \| High-speed inference with reduced memory \| \| F16 \| High \| High \| FP16-supported devices \| GPU inference when BF16 isn't available \| \| Q4_K \| Medium Low \| Low \| CPU or Low-VRAM devices \| Best for memory-constrained environments \| \| Q6_K \| Medium \| Moderate \| CPU with more memory \| Better accuracy while still being quantized \| \| Q8_0 \| High \| Moderate \| CPU or GPU with enough VRAM \| Best accuracy among quantized models \| \| IQ3_XS \| Very Low \| Very Low \| Ultra-low-memory devices \| Extreme memory efficiency and low accuracy \| \| Q4_0 \| Low \| Low \| ARM or low-memory devices \| llama.cpp can optimize for ARM devices \| --- ## Included Files & Details ### `HyperCLOVAX-SEED-Text-Instruct-0.5B-bf16.gguf` - Model weights preserved in BF16. - Use this if you want to requantize the model into a different format. - Best if your device supports BF16 acceleration. ### `HyperCLOVAX-SEED-Text-Instruct-0.5B-f16.gguf` - Model weights stored in F16. - Use if your device supports FP16, especially if BF16 is not available. ### `HyperCLOVAX-SEED-Text-Instruct-0.5B-bf16-q8_0.gguf` - Output & embeddings remain in BF16. - All other layers quantized to Q8_0. - Use if your device supports BF16 and you want a quantized version. ### `HyperCLOVAX-SEED-Text-Instruct-0.5B-f16-q8_0.gguf` - Output & embeddings remain in F16. - All other layers quantized to Q8_0. ### `HyperCLOVAX-SEED-Text-Instruct-0.5B-q4_k.gguf` - Output & embeddings quantized to Q8_0. - All other layers quantized to Q4_K. - Good for CPU inference with limited memory. ### `HyperCLOVAX-SEED-Text-Instruct-0.5B-q4_k_s.gguf` - Smallest Q4_K variant, using less memory at the cost of accuracy. - Best for very low-memory setups. ### `HyperCLOVAX-SEED-Text-Instruct-0.5B-q6_k.gguf` - Output & embeddings quantized to Q8_0. - All other layers quantized to Q6_K . ### `HyperCLOVAX-SEED-Text-Instruct-0.5B-q8_0.gguf` - Fully Q8 quantized model for better accuracy. - Requires more memory but offers higher precision. ### `HyperCLOVAX-SEED-Text-Instruct-0.5B-iq3_xs.gguf` - IQ3_XS quantization, optimized for extreme memory efficiency. - Best for ultra-low-memory devices. ### `HyperCLOVAX-SEED-Text-Instruct-0.5B-iq3_m.gguf` - IQ3_M quantization, offering a medium block size for better accuracy. - Suitable for low-memory devices. ### `HyperCLOVAX-SEED-Text-Instruct-0.5B-q4_0.gguf` - Pure Q4_0 quantization, optimized for ARM devices. - Best for low-memory environments. - Prefer IQ4_NL for better accuracy. # <span id="testllm" style="color: #7F7FFF;">🚀 If you find these models useful</span> ❤ Please click "Like" if you find this useful! Help me test my AI-Powered Network Monitor Assistant with quantum-ready security checks: 👉 [Quantum Network Monitor](https://readyforquantum.com/dashboard/?assistant=open&utm_source=huggingface&utm_medium=referral&utm_campaign=huggingface_repo_readme) 💬 How to test: Choose an AI assistant type: - `TurboLLM` (GPT-4o-mini) - `HugLLM` (Hugginface Open-source) - `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 scans - Quantum-readiness checks - Network Monitoring tasks 🟡 TestLLM – Current experimental model (llama.cpp on 2 CPU threads): - ✅ Zero-configuration setup - ⏳ 30s load time (slow inference but no API costs) - 🔧 Help wanted! If you’re into edge-device AI, let’s collaborate! ### Other Assistants 🟢 TurboLLM – Uses gpt-4o-mini for: - 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 ### 💡 Example commands to 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 to run the .net code from. 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! 😊 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/65265ab8f8db96cffcb969dc/szGAraJ_ZawG0kozH5yPi.png) ## Overview HyperCLOVAX-SEED-Text-Instruct-0.5B is a Text-to-Text model with instruction-following capabilities that excels in understanding Korean language and culture. Compared to external competitors of similar scale, it demonstrates improved mathematical performance and a substantial enhancement in Korean language capability. The HyperCLOVAX-SEED-Text-Instruct-0.5B is currently the smallest model released by the HyperCLOVAX, representing a lightweight solution suitable for deployment in resource‑constrained environments such as edge devices. It supports a maximum context length of 4K and functions as a versatile small model applicable to a wide range of tasks. The total cost of a single training run for HyperCLOVAX-SEED-Text-Instruct-0.5B was 4.358K A100 GPU hours (approximately USD 6.537K), which is 39 times lower than the cost of training the `QWEN2.5‑0.5B‑instruct` model. ## Basic Information - Architecture: Transformer‑based (Dense Model) - Parameters: 0.57 B (total); 0.45 B (excluding token embeddings, tied embeddings) - Input/Output Format: Text / Text - Maximum Context Length: 4 K tokens - Knowledge Cutoff Date: Trained on data up to January 2025 ## Training and Data The training dataset for HyperCLOVAX-SEED-Text-Instruct-0.5B consists of diverse sources, including the high‑quality data accumulated during the development of HyperCLOVAX-SEED-Text-Instruct-0.5B. Training was conducted in three main stages: 1. Pretraining: Knowledge acquisition using high‑quality data and a high‑performance pretrained model. 2. Rejection Sampling Fine‑Tuning (RFT): Enhancement of multi‑domain knowledge and complex reasoning capabilities. 3. Supervised Fine‑Tuning (SFT): Improvement of instruction‑following proficiency. ## Training Cost HyperCLOVAX-SEED-Text-Instruct-0.5B leveraged HyperCLOVA X’s lightweight training process and high‑quality data to achieve significantly lower training costs compared to industry‑leading competitors of similar scale. Excluding the SFT stage, a single pretraining run incurred: \| Pretraining Cost Category \| HyperCLOVAX-SEED-Text-Instruct-0.5B \| QWEN2.5‑0.5B‑instruct \| \|---------------------------------\|-----------------------------------------------\|-------------------------------------\| \| A100 GPU Hours \| 4.358 K \| 169.257 K \| \| Cost (USD) \| 6.537 K \| 253.886 K \| This represents approximately a 39× reduction in pretraining cost relative to `QWEN2.5‑0.5B-instruct`. ## Benchmarks \| Model \| KMMLU (5-shot, acc) \| HAE-RAE (5-shot, acc) \| CLiCK (5-shot, acc) \| KoBEST (5-shot, acc) \| \| --- \| --- \| --- \| --- \| --- \| \| HyperCLOVAX-SEED-Text-Base-0.5B \| 0.4181 \| 0.6370 \| 0.5373 \| 0.6963 \| HyperCLOVAX-SEED-Text-Instruct-0.5B \| 0.3815 \| 0.5619 \| 0.4446 \| 0.6299 \| \| QWEN2.5-0.5B-instruct \| 0.2968 \| 0.3428 \| 0.3805 \| 0.5025 \| ## HuggingFace Usage Example ### Python Code ```python from transformers import AutoModelForCausalLM, AutoTokenizer model = AutoModelForCausalLM.from_pretrained("naver-hyperclovax/HyperCLOVAX-SEED-Text-Instruct-0.5B").to(device="cuda") tokenizer = AutoTokenizer.from_pretrained("naver-hyperclovax/HyperCLOVAX-SEED-Text-Instruct-0.5B") chat = [ {"role": "tool_list", "content": ""}, {"role": "system", "content": "- AI 언어모델의 이름은 \"CLOVA X\" 이며 네이버에서 만들었다.\n- 오늘은 2025년 04월 24일(목)이다."}, {"role": "user", "content": "슈뢰딩거 방정식과 양자역학의 관계를 최대한 자세히 알려줘."}, ] inputs = tokenizer.apply_chat_template(chat, add_generation_prompt=True, return_dict=True, return_tensors="pt") inputs = inputs.to(device="cuda") output_ids = model.generate(inputs, max_length=1024, stop_strings=["<\|endofturn\|>", "<\|stop\|>"], repetition_penalty=1.2, tokenizer=tokenizer) print(tokenizer.batch_decode(output_ids)) ``` ### Result ```bash ['<\|im_start\|>tool_list\n<\|im_end\|>\n<\|im_start\|>system\n- AI 언어모델의 이름은 "CLOVA X" 이며 네이버에서 만들었다.\n- 오늘은 2025년 04월 24일(목)이다.<\|im_end\|>\n<\|im_start\|>user\n슈뢰딩거 방정식과 양자역학의 관계를 최대한 자세히 알려줘.<\|im_end\|>\n<\|im_start\|>assistant\n양자역학은 슈뢰딩거 방정식을 통해 물질과 에너지, 공간 등의 현상을 설명합니다.\n\n1. 슈뢰딩거 방정식\n\n슈뢰딩거는 파동함수를 이용하여 입자의 위치와 운동량을 계산할 수 있다고 주장했습니다. 이를 위해 다음과 같은 식으로 표현됩니다:\n\n$$\\frac{\\partial \\psi}{\\partial t} = iH \\nabla^2 \\psi + V(x)\\psi $$\n\n여기서 $\\psi$는 파동함수이고 $i$는 허수 단위입니다. 여기서 $t$는 시간, $x$는 공간 좌표이며, $H$는 해밀턴 상수로 시스템의 에너지를 나타냅니다. 또한 $V(x)$는 외부 힘이나 장벽에 의해 영향을 받는 부분을 나타내는 함수로, 일반적으로 전위장을 사용합니다.\n\n2. 양자역학과 슈뢰딩거 방정식의 관계\n\n양자역학에서는 슈뢰딩거 방정식이 매우 중요한 역할을 합니다. 이는 모든 물리적 시스템이 불확정성 원리에 따라 행동을 하며, 이러한 시스템들은 확률적으로 상태를 가질 수밖에 없기 때문입니다. 따라서 슈뢰딩거 방정식은 양자역학을 수학적으로 모델링하는 핵심적인 도구 중 하나입니다.\n\n예를 들어, 원자핵 내의 전자들의 상태는 슈뢰딩거 방정식에 의해 결정되며, 이는 물리학적 법칙을 따르는 것으로 보입니다. 또한, 광전 효과에서도 슈뢰딩거 방정식은 빛이 물질 내에서 어떻게 흡수되고 반사되는지를 예측하는데 사용됩니다.\n\n3. 응용 분야**\n\n슈뢰딩거 방정식은 다양한 분야에서 활용되고 있습니다. 예를 들면, 반도체 기술에서의 트랜지스터 설계, 핵물리학에서의 방사성 붕괴 연구 등이 있으며, 이는 모두 슈뢰딩거 방정식을 기반으로 한 이론적 기반 위에서 이루어집니다.\n\n또한, 현대 과학 기술의 발전에도 큰 기여를 하고 있는데, 특히 인공지능(AI), 컴퓨터 시뮬레이션 등에서 복잡한 문제를 해결하고 새로운 지식을 창출하기 위한 기초가 되고 있습니다.\n\n결론적으로, 슈뢰딩거 방정식은 양자역학의 기본 개념들을 이해하고 해석하며, 그 결과로서 많은 혁신적이고 실용적인 기술을 가능하게 했습니다. 이는 양자역학의 중요성을 보여주는 대표적인 예시라고 할 수 있습니다.<\|im_end\|><\|endofturn\|>'] ```
Mungert/Qwen2.5-72B-Instruct-GGUF	Mungert	2025-06-15T19:44:14Z	1,393	5	transformers	[ "transformers", "gguf", "chat", "text-generation", "zho", "eng", "fra", "spa", "por", "deu", "ita", "rus", "jpn", "kor", "vie", "tha", "ara", "arxiv:2309.00071", "arxiv:2407.10671", "base_model:Qwen/Qwen2.5-72B", "base_model:quantized:Qwen/Qwen2.5-72B", "license:other", "endpoints_compatible", "region:us", "imatrix", "conversational" ]	text-generation	2025-04-09T04:55:03Z	--- license: other license_name: qwen license_link: https://huggingface.co/Qwen/Qwen2.5-72B-Instruct/blob/main/LICENSE language: - zho - eng - fra - spa - por - deu - ita - rus - jpn - kor - vie - tha - ara pipeline_tag: text-generation base_model: Qwen/Qwen2.5-72B tags: - chat library_name: transformers --- # <span style="color: #7FFF7F;">Qwen2.5-72B-Instruct GGUF Models</span> ## Choosing the Right Model Format Selecting the correct model format depends on your hardware capabilities and memory constraints. ### BF16 (Brain Float 16) – Use if BF16 acceleration is available - A 16-bit floating-point format designed for faster computation while retaining good precision. - Provides similar dynamic range as FP32 but with lower memory usage. - Recommended if your hardware supports BF16 acceleration (check your device's specs). - Ideal for high-performance inference with reduced memory footprint compared to FP32. 📌 Use BF16 if: ✔ Your hardware has native BF16 support (e.g., newer GPUs, TPUs). ✔ You want higher precision while saving memory. ✔ You plan to requantize the model into another format. 📌 Avoid BF16 if: ❌ Your hardware does not support BF16 (it may fall back to FP32 and run slower). ❌ You need compatibility with older devices that lack BF16 optimization. --- ### F16 (Float 16) – More widely supported than BF16 - A 16-bit floating-point high precision but with less of range of values than BF16. - Works on most devices with FP16 acceleration support (including many GPUs and some CPUs). - Slightly lower numerical precision than BF16 but generally sufficient for inference. 📌 Use F16 if: ✔ Your hardware supports FP16 but not BF16. ✔ You need a balance between speed, memory usage, and accuracy. ✔ You are running on a GPU or another device optimized for FP16 computations. 📌 Avoid F16 if: ❌ Your device lacks native FP16 support (it may run slower than expected). ❌ You have memory limitations. --- ### Quantized Models (Q4_K, Q6_K, Q8, etc.) – For CPU & Low-VRAM Inference Quantization reduces model size and memory usage while maintaining as much accuracy as possible. - Lower-bit models (Q4_K) → Best for minimal memory usage, may have lower precision. - Higher-bit models (Q6_K, Q8_0) → Better accuracy, requires more memory. 📌 Use Quantized Models if: ✔ You are running inference on a CPU and need an optimized model. ✔ Your device has low VRAM and cannot load full-precision models. ✔ You want to reduce memory footprint while keeping reasonable accuracy. 📌 Avoid Quantized Models if: ❌ You need maximum accuracy (full-precision models are better for this). ❌ Your hardware has enough VRAM for higher-precision formats (BF16/F16). --- ### Very Low-Bit Quantization (IQ3_XS, IQ3_S, IQ3_M, Q4_K, Q4_0) These models are optimized for extreme memory efficiency, making them ideal for low-power devices or large-scale deployments where memory is a critical constraint. - IQ3_XS: Ultra-low-bit quantization (3-bit) with extreme memory efficiency. - Use case: Best for ultra-low-memory devices where even Q4_K is too large. - Trade-off: Lower accuracy compared to higher-bit quantizations. - IQ3_S: Small block size for maximum memory efficiency. - Use case: Best for low-memory devices where IQ3_XS is too aggressive. - IQ3_M: Medium block size for better accuracy than IQ3_S. - Use case: Suitable for low-memory devices where IQ3_S is too limiting. - Q4_K: 4-bit quantization with block-wise optimization for better accuracy. - Use case: Best for low-memory devices where Q6_K is too large. - Q4_0: Pure 4-bit quantization, optimized for ARM devices. - Use case: Best for ARM-based devices or low-memory environments. --- ### Summary Table: Model Format Selection \| Model Format \| Precision \| Memory Usage \| Device Requirements \| Best Use Case \| \|--------------\|------------\|---------------\|----------------------\|---------------\| \| BF16 \| Highest \| High \| BF16-supported GPU/CPUs \| High-speed inference with reduced memory \| \| F16 \| High \| High \| FP16-supported devices \| GPU inference when BF16 isn't available \| \| Q4_K \| Medium Low \| Low \| CPU or Low-VRAM devices \| Best for memory-constrained environments \| \| Q6_K \| Medium \| Moderate \| CPU with more memory \| Better accuracy while still being quantized \| \| Q8_0 \| High \| Moderate \| CPU or GPU with enough VRAM \| Best accuracy among quantized models \| \| IQ3_XS \| Very Low \| Very Low \| Ultra-low-memory devices \| Extreme memory efficiency and low accuracy \| \| Q4_0 \| Low \| Low \| ARM or low-memory devices \| llama.cpp can optimize for ARM devices \| --- ## Included Files & Details ### `Qwen2.5-72B-Instruct-bf16.gguf` - Model weights preserved in BF16. - Use this if you want to requantize the model into a different format. - Best if your device supports BF16 acceleration. ### `Qwen2.5-72B-Instruct-f16.gguf` - Model weights stored in F16. - Use if your device supports FP16, especially if BF16 is not available. ### `Qwen2.5-72B-Instruct-bf16-q8_0.gguf` - Output & embeddings remain in BF16. - All other layers quantized to Q8_0. - Use if your device supports BF16 and you want a quantized version. ### `Qwen2.5-72B-Instruct-f16-q8_0.gguf` - Output & embeddings remain in F16. - All other layers quantized to Q8_0. ### `Qwen2.5-72B-Instruct-q4_k.gguf` - Output & embeddings quantized to Q8_0. - All other layers quantized to Q4_K. - Good for CPU inference with limited memory. ### `Qwen2.5-72B-Instruct-q4_k_s.gguf` - Smallest Q4_K variant, using less memory at the cost of accuracy. - Best for very low-memory setups. ### `Qwen2.5-72B-Instruct-q6_k.gguf` - Output & embeddings quantized to Q8_0. - All other layers quantized to Q6_K . ### `Qwen2.5-72B-Instruct-q8_0.gguf` - Fully Q8 quantized model for better accuracy. - Requires more memory but offers higher precision. ### `Qwen2.5-72B-Instruct-iq3_xs.gguf` - IQ3_XS quantization, optimized for extreme memory efficiency. - Best for ultra-low-memory devices. ### `Qwen2.5-72B-Instruct-iq3_m.gguf` - IQ3_M quantization, offering a medium block size for better accuracy. - Suitable for low-memory devices. ### `Qwen2.5-72B-Instruct-q4_0.gguf` - Pure Q4_0 quantization, optimized for ARM devices. - Best for low-memory environments. - Prefer IQ4_NL for better accuracy. # <span id="testllm" style="color: #7F7FFF;">🚀 If you find these models useful</span> ❤ Please click "Like" if you find this useful! Help me test my AI-Powered Network Monitor Assistant with quantum-ready security checks: 👉 [Quantum Network Monitor](https://readyforquantum.com/dashboard) 💬 How to test: 1. Click the chat icon (bottom right on any page) 2. Choose an AI assistant type: - `TurboLLM` (GPT-4-mini) - `FreeLLM` (Open-source) - `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 scans - Quantum-readiness checks - Metasploit integration 🟡 TestLLM – Current experimental model (llama.cpp on 6 CPU threads): - ✅ Zero-configuration setup - ⏳ 30s load time (slow inference but no API costs) - 🔧 Help wanted! If you’re into edge-device AI, let’s collaborate! ### Other Assistants 🟢 TurboLLM – Uses gpt-4-mini for: - Real-time network diagnostics - Automated penetration testing (Nmap/Metasploit) - 🔑 Get more tokens by [downloading our Quantum Network Monitor Agent](https://readyforquantum.com/download/?utm_source=huggingface&utm_medium=referral&utm_campaign=huggingface_repo_readme) 🔵 HugLLM – Open-source models (≈8B params): - 2x more tokens than TurboLLM - AI-powered log analysis - 🌐 Runs on Hugging Face Inference API ### 💡 Example AI Commands to 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 quick Nmap vulnerability test"` 4. '"Create a cmd processor to .. (what ever you want)" Note you need to install a Quantum Network Monitor Agent to run the .net code from. This is a very flexible and powerful feature. Use with caution! ### Final word I fund the servers to create the models files, run the Quantum Network Monitor Service and Pay for Inference from Novita and OpenAI all from my own pocket. All of the code for creating the models and the work I have done with Quantum Network Monitor is [open source](https://github.com/Mungert69). Feel free to use what you find useful. Please support my work and consider [buying me a coffee](https://www.buymeacoffee.com/mahadeva) . This will help me pay for the services and increase the token limits for everyone. Thank you :) # Qwen2.5-72B-Instruct <a href="https://chat.qwenlm.ai/" target="_blank" style="margin: 2px;"> <img alt="Chat" src="https://img.shields.io/badge/%F0%9F%92%9C%EF%B8%8F%20Qwen%20Chat%20-536af5" style="display: inline-block; vertical-align: middle;"/> </a> ## Introduction Qwen2.5 is the latest series of Qwen large language models. For Qwen2.5, we release a number of base language models and instruction-tuned language models ranging from 0.5 to 72 billion parameters. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and mathematics, thanks to our specialized expert models in these domains. - Significant improvements in instruction following, generating long texts (over 8K tokens), understanding structured data (e.g, tables), and generating structured outputs especially JSON. More resilient to the diversity of system prompts, enhancing role-play implementation and condition-setting for chatbots. - Long-context Support up to 128K tokens and can generate up to 8K tokens. - Multilingual support for over 29 languages, including Chinese, English, French, Spanish, Portuguese, German, Italian, Russian, Japanese, Korean, Vietnamese, Thai, Arabic, and more. This repo contains the instruction-tuned 72B Qwen2.5 model, which has the following features: - Type: Causal Language Models - Training Stage: Pretraining & Post-training - Architecture: transformers with RoPE, SwiGLU, RMSNorm, and Attention QKV bias - Number of Parameters: 72.7B - Number of Paramaters (Non-Embedding): 70.0B - Number of Layers: 80 - Number of Attention Heads (GQA): 64 for Q and 8 for KV - Context Length: Full 131,072 tokens and generation 8192 tokens - Please refer to [this section](#processing-long-texts) for detailed instructions on how to deploy Qwen2.5 for handling long texts. For more details, please refer to our [blog](https://qwenlm.github.io/blog/qwen2.5/), [GitHub](https://github.com/QwenLM/Qwen2.5), and [Documentation](https://qwen.readthedocs.io/en/latest/). ## Requirements The code of Qwen2.5 has been in the latest Hugging face `transformers` and we advise you to use the latest version of `transformers`. With `transformers<4.37.0`, you will encounter the following error: ``` KeyError: 'qwen2' ``` ## Quickstart Here provides a code snippet with `apply_chat_template` to show you how to load the tokenizer and model and how to generate contents. ```python from transformers import AutoModelForCausalLM, AutoTokenizer model_name = "Qwen/Qwen2.5-72B-Instruct" model = AutoModelForCausalLM.from_pretrained( model_name, torch_dtype="auto", device_map="auto" ) tokenizer = AutoTokenizer.from_pretrained(model_name) prompt = "Give me a short introduction to large language model." messages = [ {"role": "system", "content": "You are Qwen, created by Alibaba Cloud. You are a helpful assistant."}, {"role": "user", "content": prompt} ] text = tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True ) model_inputs = tokenizer([text], return_tensors="pt").to(model.device) generated_ids = model.generate( model_inputs, max_new_tokens=512 ) generated_ids = [ output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids) ] response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0] ``` ### Processing Long Texts The current `config.json` is set for context length up to 32,768 tokens. To handle extensive inputs exceeding 32,768 tokens, we utilize [YaRN](https://arxiv.org/abs/2309.00071), a technique for enhancing model length extrapolation, ensuring optimal performance on lengthy texts. For supported frameworks, you could add the following to `config.json` to enable YaRN: ```json { ..., "rope_scaling": { "factor": 4.0, "original_max_position_embeddings": 32768, "type": "yarn" } } ``` For deployment, we recommend using vLLM. Please refer to our [Documentation](https://qwen.readthedocs.io/en/latest/deployment/vllm.html) for usage if you are not familar with vLLM. Presently, vLLM only supports static YARN, which means the scaling factor remains constant regardless of input length, potentially impacting performance on shorter texts**. We advise adding the `rope_scaling` configuration only when processing long contexts is required. ## Evaluation & Performance Detailed evaluation results are reported in this [📑 blog](https://qwenlm.github.io/blog/qwen2.5/). For requirements on GPU memory and the respective throughput, see results [here](https://qwen.readthedocs.io/en/latest/benchmark/speed_benchmark.html). ## Citation If you find our work helpful, feel free to give us a cite. ``` @misc{qwen2.5, title = {Qwen2.5: A Party of Foundation Models}, url = {https://qwenlm.github.io/blog/qwen2.5/}, author = {Qwen Team}, month = {September}, year = {2024} } @article{qwen2, title={Qwen2 Technical Report}, author={An Yang and Baosong Yang and Binyuan Hui and Bo Zheng and Bowen Yu and Chang Zhou and Chengpeng Li and Chengyuan Li and Dayiheng Liu and Fei Huang and Guanting Dong and Haoran Wei and Huan Lin and Jialong Tang and Jialin Wang and Jian Yang and Jianhong Tu and Jianwei Zhang and Jianxin Ma and Jin Xu and Jingren Zhou and Jinze Bai and Jinzheng He and Junyang Lin and Kai Dang and Keming Lu and Keqin Chen and Kexin Yang and Mei Li and Mingfeng Xue and Na Ni and Pei Zhang and Peng Wang and Ru Peng and Rui Men and Ruize Gao and Runji Lin and Shijie Wang and Shuai Bai and Sinan Tan and Tianhang Zhu and Tianhao Li and Tianyu Liu and Wenbin Ge and Xiaodong Deng and Xiaohuan Zhou and Xingzhang Ren and Xinyu Zhang and Xipin Wei and Xuancheng Ren and Yang Fan and Yang Yao and Yichang Zhang and Yu Wan and Yunfei Chu and Yuqiong Liu and Zeyu Cui and Zhenru Zhang and Zhihao Fan}, journal={arXiv preprint arXiv:2407.10671}, year={2024} } ```
Mungert/OlympicCoder-32B-GGUF	Mungert	2025-06-15T19:43:22Z	318	5	transformers	[ "transformers", "gguf", "text-generation", "en", "dataset:open-r1/codeforces-cots", "base_model:Qwen/Qwen2.5-Coder-32B-Instruct", "base_model:quantized:Qwen/Qwen2.5-Coder-32B-Instruct", "license:apache-2.0", "endpoints_compatible", "region:us", "imatrix", "conversational" ]	text-generation	2025-03-31T05:55:48Z	--- license: apache-2.0 datasets: - open-r1/codeforces-cots language: - en base_model: - Qwen/Qwen2.5-Coder-32B-Instruct pipeline_tag: text-generation library_name: transformers --- # <span style="color: #7FFF7F;">OlympicCoder-32B GGUF Models</span> ## <span style="color: #7FFF7F;">Ultra-Low-Bit Quantization with IQ-DynamicGate (1-2 bit)</span> Our latest quantization method introduces precision-adaptive quantization for ultra-low-bit models (1-2 bit), with benchmark-proven improvements on Llama-3-8B. This approach uses layer-specific strategies to preserve accuracy while maintaining extreme memory efficiency. ### Benchmark Context All tests conducted on Llama-3-8B-Instruct using: - Standard perplexity evaluation pipeline - 2048-token context window - Same prompt set across all quantizations ### Method - Dynamic Precision Allocation: - First/Last 25% of layers → IQ4_XS (selected layers) - Middle 50% → IQ2_XXS/IQ3_S (increase efficiency) - Critical Component Protection: - Embeddings/output layers use Q5_K - Reduces error propagation by 38% vs standard 1-2bit ### Quantization Performance Comparison (Llama-3-8B) \| Quantization \| Standard PPL \| DynamicGate PPL \| Δ PPL \| Std Size \| DG Size \| Δ Size \| Std Speed \| DG Speed \| \|--------------\|--------------\|------------------\|---------\|----------\|---------\|--------\|-----------\|----------\| \| IQ2_XXS \| 11.30 \| 9.84 \| -12.9% \| 2.5G \| 2.6G \| +0.1G \| 234s \| 246s \| \| IQ2_XS \| 11.72 \| 11.63 \| -0.8% \| 2.7G \| 2.8G \| +0.1G \| 242s \| 246s \| \| IQ2_S \| 14.31 \| 9.02 \| -36.9% \| 2.7G \| 2.9G \| +0.2G \| 238s \| 244s \| \| IQ1_M \| 27.46 \| 15.41 \| -43.9% \| 2.2G \| 2.5G \| +0.3G \| 206s \| 212s \| \| IQ1_S \| 53.07 \| 32.00 \| -39.7% \| 2.1G \| 2.4G \| +0.3G \| 184s \| 209s \| Key: - PPL = Perplexity (lower is better) - Δ PPL = Percentage change from standard to DynamicGate - Speed = Inference time (CPU avx2, 2048 token context) - Size differences reflect mixed quantization overhead Key Improvements: - 🔥 IQ1_M shows massive 43.9% perplexity reduction (27.46 → 15.41) - 🚀 IQ2_S cuts perplexity by 36.9% while adding only 0.2GB - ⚡ IQ1_S maintains 39.7% better accuracy despite 1-bit quantization Tradeoffs: - All variants have modest size increases (0.1-0.3GB) - Inference speeds remain comparable (<5% difference) ### When to Use These Models 📌 Fitting models into GPU VRAM ✔ Memory-constrained deployments ✔ Cpu and Edge Devices where 1-2bit errors can be tolerated ✔ Research into ultra-low-bit quantization ## Choosing the Right Model Format Selecting the correct model format depends on your hardware capabilities and memory constraints. ### BF16 (Brain Float 16) – Use if BF16 acceleration is available - A 16-bit floating-point format designed for faster computation while retaining good precision. - Provides similar dynamic range as FP32 but with lower memory usage. - Recommended if your hardware supports BF16 acceleration (check your device's specs). - Ideal for high-performance inference with reduced memory footprint compared to FP32. 📌 Use BF16 if: ✔ Your hardware has native BF16 support (e.g., newer GPUs, TPUs). ✔ You want higher precision while saving memory. ✔ You plan to requantize the model into another format. 📌 Avoid BF16 if: ❌ Your hardware does not support BF16 (it may fall back to FP32 and run slower). ❌ You need compatibility with older devices that lack BF16 optimization. --- ### F16 (Float 16) – More widely supported than BF16 - A 16-bit floating-point high precision but with less of range of values than BF16. - Works on most devices with FP16 acceleration support (including many GPUs and some CPUs). - Slightly lower numerical precision than BF16 but generally sufficient for inference. 📌 Use F16 if: ✔ Your hardware supports FP16 but not BF16. ✔ You need a balance between speed, memory usage, and accuracy. ✔ You are running on a GPU or another device optimized for FP16 computations. 📌 Avoid F16 if: ❌ Your device lacks native FP16 support (it may run slower than expected). ❌ You have memory limitations. --- ### Quantized Models (Q4_K, Q6_K, Q8, etc.) – For CPU & Low-VRAM Inference Quantization reduces model size and memory usage while maintaining as much accuracy as possible. - Lower-bit models (Q4_K) → Best for minimal memory usage, may have lower precision. - Higher-bit models (Q6_K, Q8_0) → Better accuracy, requires more memory. 📌 Use Quantized Models if: ✔ You are running inference on a CPU and need an optimized model. ✔ Your device has low VRAM and cannot load full-precision models. ✔ You want to reduce memory footprint while keeping reasonable accuracy. 📌 Avoid Quantized Models if: ❌ You need maximum accuracy (full-precision models are better for this). ❌ Your hardware has enough VRAM for higher-precision formats (BF16/F16). --- ### Very Low-Bit Quantization (IQ3_XS, IQ3_S, IQ3_M, Q4_K, Q4_0) These models are optimized for extreme memory efficiency, making them ideal for low-power devices or large-scale deployments where memory is a critical constraint. - IQ3_XS: Ultra-low-bit quantization (3-bit) with extreme memory efficiency. - Use case: Best for ultra-low-memory devices where even Q4_K is too large. - Trade-off: Lower accuracy compared to higher-bit quantizations. - IQ3_S: Small block size for maximum memory efficiency. - Use case: Best for low-memory devices where IQ3_XS is too aggressive. - IQ3_M: Medium block size for better accuracy than IQ3_S. - Use case: Suitable for low-memory devices where IQ3_S is too limiting. - Q4_K: 4-bit quantization with block-wise optimization for better accuracy. - Use case: Best for low-memory devices where Q6_K is too large. - Q4_0: Pure 4-bit quantization, optimized for ARM devices. - Use case: Best for ARM-based devices or low-memory environments. --- ### Summary Table: Model Format Selection \| Model Format \| Precision \| Memory Usage \| Device Requirements \| Best Use Case \| \|--------------\|------------\|---------------\|----------------------\|---------------\| \| BF16 \| Highest \| High \| BF16-supported GPU/CPUs \| High-speed inference with reduced memory \| \| F16 \| High \| High \| FP16-supported devices \| GPU inference when BF16 isn't available \| \| Q4_K \| Medium Low \| Low \| CPU or Low-VRAM devices \| Best for memory-constrained environments \| \| Q6_K \| Medium \| Moderate \| CPU with more memory \| Better accuracy while still being quantized \| \| Q8_0 \| High \| Moderate \| CPU or GPU with enough VRAM \| Best accuracy among quantized models \| \| IQ3_XS \| Very Low \| Very Low \| Ultra-low-memory devices \| Extreme memory efficiency and low accuracy \| \| Q4_0 \| Low \| Low \| ARM or low-memory devices \| llama.cpp can optimize for ARM devices \| --- ## Included Files & Details ### `OlympicCoder-32B-bf16.gguf` - Model weights preserved in BF16. - Use this if you want to requantize the model into a different format. - Best if your device supports BF16 acceleration. ### `OlympicCoder-32B-f16.gguf` - Model weights stored in F16. - Use if your device supports FP16, especially if BF16 is not available. ### `OlympicCoder-32B-bf16-q8_0.gguf` - Output & embeddings remain in BF16. - All other layers quantized to Q8_0. - Use if your device supports BF16 and you want a quantized version. ### `OlympicCoder-32B-f16-q8_0.gguf` - Output & embeddings remain in F16. - All other layers quantized to Q8_0. ### `OlympicCoder-32B-q4_k.gguf` - Output & embeddings quantized to Q8_0. - All other layers quantized to Q4_K. - Good for CPU inference with limited memory. ### `OlympicCoder-32B-q4_k_s.gguf` - Smallest Q4_K variant, using less memory at the cost of accuracy. - Best for very low-memory setups. ### `OlympicCoder-32B-q6_k.gguf` - Output & embeddings quantized to Q8_0. - All other layers quantized to Q6_K . ### `OlympicCoder-32B-q8_0.gguf` - Fully Q8 quantized model for better accuracy. - Requires more memory but offers higher precision. ### `OlympicCoder-32B-iq3_xs.gguf` - IQ3_XS quantization, optimized for extreme memory efficiency. - Best for ultra-low-memory devices. ### `OlympicCoder-32B-iq3_m.gguf` - IQ3_M quantization, offering a medium block size for better accuracy. - Suitable for low-memory devices. ### `OlympicCoder-32B-q4_0.gguf` - Pure Q4_0 quantization, optimized for ARM devices. - Best for low-memory environments. - Prefer IQ4_NL for better accuracy. # <span id="testllm" style="color: #7F7FFF;">🚀 If you find these models useful</span> ❤ Please click "Like" if you find this useful! Help me test my AI-Powered Network Monitor Assistant with quantum-ready security checks: 👉 [Quantum Network Monitor](https://readyforquantum.com) 💬 How to test: 1. Click the chat icon (bottom right on any page) 2. Choose an AI assistant type: - `TurboLLM` (GPT-4-mini) - `FreeLLM` (Open-source) - `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 scans - Quantum-readiness checks - Metasploit integration 🟡 TestLLM – Current experimental model (llama.cpp on 6 CPU threads): - ✅ Zero-configuration setup - ⏳ 30s load time (slow inference but no API costs) - 🔧 Help wanted! If you’re into edge-device AI, let’s collaborate! ### Other Assistants 🟢 TurboLLM – Uses gpt-4-mini for: - Real-time network diagnostics - Automated penetration testing (Nmap/Metasploit) - 🔑 Get more tokens by [downloading our Quantum Network Monitor Agent](https://readyforquantum.com/download/?utm_source=huggingface&utm_medium=referral&utm_campaign=huggingface_repo_readme) 🔵 HugLLM – Open-source models (≈8B params): - 2x more tokens than TurboLLM - AI-powered log analysis - 🌐 Runs on Hugging Face Inference API ### 💡 Example AI Commands to 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 quick Nmap vulnerability test"` 4. '"Create a cmd processor to .. (what ever you want)" Note you need to install a Quantum Network Monitor Agent to run the .net code from. This is a very flexible and powerful feature. Use with caution! ### Final word I fund the servers to create the models files, run the Quantum Network Monitor Service and Pay for Inference from Novita and OpenAI all from my own pocket. All of the code for creating the models and the work I have done with Quantum Network Monitor is [open source](https://github.com/Mungert69). Feel free to use what you find useful. Please support my work and consider [buying me a coffee](https://www.buymeacoffee.com/mahadeva) . This will help me pay for the services and increase the token limits for everyone. Thank you :) # Model Card for OlympicCoder-32B OlympicCoder-32B is a code model that achieves very strong performance on competitive coding benchmarks such as LiveCodeBench andthe 2024 International Olympiad in Informatics. * Repository: https://github.com/huggingface/open-r1 * Blog post: https://huggingface.co/blog/open-r1/update-3 ## Model description - Model type: A 32B parameter model fine-tuned on a decontaminated version of the codeforces dataset. - Language(s) (NLP): Primarily English - License: apache-2.0 - Finetuned from model: [Qwen/Qwen2.5-Coder-32B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-32B-Instruct) ## Evaluation We compare the performance of OlympicCoder models on two main benchmarks for competitive coding: * [IOI'2024:](https://github.com/huggingface/ioi) 6 very challenging problems from the 2024 International Olympiad in Informatics. Models are allowed up to 50 submissions per problem. * [LiveCodeBench:](https://livecodebench.github.io) Python programming problems source from platforms like CodeForces and LeetCoder. We use the `v4_v5` subset of [`livecodebench/code_generation_lite`](https://huggingface.co/datasets/livecodebench/code_generation_lite), which corresponds to 268 problems. We use `lighteval` to evaluate models on LiveCodeBench using the sampling parameters described [here](https://github.com/huggingface/open-r1?tab=readme-ov-file#livecodebench). > [!NOTE] > The OlympicCoder models were post-trained exclusively on C++ solutions generated by DeepSeek-R1. As a result the performance on LiveCodeBench should be considered to be partially _out-of-domain_, since this expects models to output solutions in Python. ### IOI'24 ![](./ioi-evals.png) ### LiveCodeBench ![](./lcb-evals.png) ## Usage Here's how you can run the model using the `pipeline()` function from 🤗 Transformers: ```python # pip install transformers # pip install accelerate import torch from transformers import pipeline pipe = pipeline("text-generation", model="open-r1/OlympicCoder-32B", torch_dtype=torch.bfloat16, device_map="auto") # We use the tokenizer's chat template to format each message - see https://huggingface.co/docs/transformers/main/en/chat_templating messages = [ {"role": "user", "content": "Write a python program to calculate the 10th Fibonacci number"}, ] prompt = pipe.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) outputs = pipe(prompt, max_new_tokens=8000, do_sample=True, temperature=0.7, top_k=50, top_p=0.95) print(outputs[0]["generated_text"]) #<\|im_start\|>user #Write a python program to calculate the 10th fibonacci number<\|im_end\|> #<\|im_start\|>assistant #<think>Okay, I need to write a Python program that calculates the 10th Fibonacci number. Hmm, the Fibonacci sequence starts with 0 and 1. Each subsequent number is the sum of the two preceding ones. So the sequence goes: 0, 1, 1, 2, 3, 5, 8, 13, 21, 34, and so on. ... ``` > [!IMPORTANT] > To ensure that the model consistently outputs a long chain-of-thought, we have edited the chat template to prefill the first assistant turn with a `<think>` token. As a result, the outputs from this model will not show the opening `<think>` token if you use the model's `generate()` method. To apply reinforcement learning with a format reward, either prepend the `<think>` token to the model's completions or amend the chat template to remove the prefill. Check out our [blog post](https://huggingface.co/blog/open-r1/update-3#lesson-4-prefill-with-think-to-consistently-enable-long-cot) for more details. ## Training procedure ### Training hyper-parameters The following hyperparameters were used during training on 16 H100 nodes: - dataset: open-r1/codeforces-cots_decontaminated - learning_rate: 4.0e-5 - train_batch_size: 1 - seed: 42 - packing: false - distributed_type: fsdp - num_devices: 128 - gradient_accumulation_steps: 1 - total_train_batch_size: 16 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine_with_min_lr - min_lr_rate: 0.1 - lr_scheduler_warmup_ratio: 0.03 - num_epochs: 10.0
Mungert/Qwen2.5-VL-32B-Instruct-GGUF	Mungert	2025-06-15T19:42:51Z	10,358	8	transformers	[ "transformers", "gguf", "multimodal", "image-text-to-text", "en", "arxiv:2309.00071", "arxiv:2502.13923", "license:apache-2.0", "endpoints_compatible", "region:us", "imatrix", "conversational" ]	image-text-to-text	2025-03-28T04:48:49Z	--- license: apache-2.0 language: - en pipeline_tag: image-text-to-text tags: - multimodal library_name: transformers --- # <span style="color: #7FFF7F;">Qwen2.5-VL-32B-Instruct GGUF Models</span> ## How to Use Qwen 2.5 VL Instruct with llama.cpp (latest as of 10th May 2025) 1. Download the Qwen 2.5 VL gguf file: https://huggingface.co/Mungert/Qwen2.5-VL-32B-Instruct-GGUF/tree/main Choose a gguf file without the mmproj in the name Example gguf file : https://huggingface.co/Mungert/Mungert/Qwen2.5-VL-32B-Instruct-GGUF/resolve/main/Qwen2.5-VL-32B-Instruct-q8_0.gguf Copy this file to your chosen folder. 2. Download the Qwen 2.5 VL mmproj file https://huggingface.co/Mungert/Qwen2.5-VL-32B-Instruct-GGUF/tree/main Choose a file with mmproj in the name Example mmproj file : https://huggingface.co/Mungert/Qwen2.5-VL-32B-Instruct-GGUF/resolve/main/Qwen2.5-VL-32B-Instruct-mmproj-f16.gguf Copy this file to your chosen folder. 3. Copy images to the same folder as the gguf files or alter paths appropriately. In the example below the gguf files, images and llama-mtmd-cli are in the same folder. Example image: image https://huggingface.co/Mungert/Qwen2.5-VL-32B-Instruct-GGUF/resolve/main/car-1.jpg Copy this file to your chosen folder. 4. Run the CLI Tool: From your chosen folder : ```bash llama-mtmd-cli -m Qwen2.5-VL-32B-Instruct-q8_0.gguf --mmproj Qwen2.5-VL-32B-Instruct-mmproj-f16.gguf -p "Describe this image." --image ./car-1.jpg ``` ## Ultra-Low-Bit Quantization with IQ-DynamicGate (1-2 bit) Our latest quantization method introduces precision-adaptive quantization for ultra-low-bit models (1-2 bit), with benchmark-proven improvements on Llama-3-8B. This approach uses layer-specific strategies to preserve accuracy while maintaining extreme memory efficiency. ### Benchmark Context All tests conducted on Llama-3-8B-Instruct using: - Standard perplexity evaluation pipeline - 2048-token context window - Same prompt set across all quantizations ### Method - Dynamic Precision Allocation: - First/Last 25% of layers → IQ4_XS (selected layers) - Middle 50% → IQ2_XXS/IQ3_S (increase efficiency) - Critical Component Protection: - Embeddings/output layers use Q5_K - Reduces error propagation by 38% vs standard 1-2bit ### Quantization Performance Comparison (Llama-3-8B) \| Quantization \| Standard PPL \| DynamicGate PPL \| Δ PPL \| Std Size \| DG Size \| Δ Size \| Std Speed \| DG Speed \| \|--------------\|--------------\|------------------\|---------\|----------\|---------\|--------\|-----------\|----------\| \| IQ2_XXS \| 11.30 \| 9.84 \| -12.9% \| 2.5G \| 2.6G \| +0.1G \| 234s \| 246s \| \| IQ2_XS \| 11.72 \| 11.63 \| -0.8% \| 2.7G \| 2.8G \| +0.1G \| 242s \| 246s \| \| IQ2_S \| 14.31 \| 9.02 \| -36.9% \| 2.7G \| 2.9G \| +0.2G \| 238s \| 244s \| \| IQ1_M \| 27.46 \| 15.41 \| -43.9% \| 2.2G \| 2.5G \| +0.3G \| 206s \| 212s \| \| IQ1_S \| 53.07 \| 32.00 \| -39.7% \| 2.1G \| 2.4G \| +0.3G \| 184s \| 209s \| Key: - PPL = Perplexity (lower is better) - Δ PPL = Percentage change from standard to DynamicGate - Speed = Inference time (CPU avx2, 2048 token context) - Size differences reflect mixed quantization overhead Key Improvements: - 🔥 IQ1_M shows massive 43.9% perplexity reduction (27.46 → 15.41) - 🚀 IQ2_S cuts perplexity by 36.9% while adding only 0.2GB - ⚡ IQ1_S maintains 39.7% better accuracy despite 1-bit quantization Tradeoffs: - All variants have modest size increases (0.1-0.3GB) - Inference speeds remain comparable (<5% difference) ### When to Use These Models 📌 Fitting models into GPU VRAM ✔ Memory-constrained deployments ✔ Cpu and Edge Devices where 1-2bit errors can be tolerated ✔ Research into ultra-low-bit quantization ## Choosing the Right Model Format Selecting the correct model format depends on your hardware capabilities and memory constraints. ### BF16 (Brain Float 16) – Use if BF16 acceleration is available - A 16-bit floating-point format designed for faster computation while retaining good precision. - Provides similar dynamic range as FP32 but with lower memory usage. - Recommended if your hardware supports BF16 acceleration (check your device’s specs). - Ideal for high-performance inference with reduced memory footprint compared to FP32. 📌 Use BF16 if: ✔ Your hardware has native BF16 support (e.g., newer GPUs, TPUs). ✔ You want higher precision while saving memory. ✔ You plan to requantize the model into another format. 📌 Avoid BF16 if: ❌ Your hardware does not support BF16 (it may fall back to FP32 and run slower). ❌ You need compatibility with older devices that lack BF16 optimization. --- ### F16 (Float 16) – More widely supported than BF16 - A 16-bit floating-point high precision but with less of range of values than BF16. - Works on most devices with FP16 acceleration support (including many GPUs and some CPUs). - Slightly lower numerical precision than BF16 but generally sufficient for inference. 📌 Use F16 if: ✔ Your hardware supports FP16 but not BF16. ✔ You need a balance between speed, memory usage, and accuracy. ✔ You are running on a GPU or another device optimized for FP16 computations. 📌 Avoid F16 if: ❌ Your device lacks native FP16 support (it may run slower than expected). ❌ You have memory limitations. --- ### Quantized Models (Q4_K, Q6_K, Q8, etc.) – For CPU & Low-VRAM Inference Quantization reduces model size and memory usage while maintaining as much accuracy as possible. - Lower-bit models (Q4_K) → Best for minimal memory usage, may have lower precision. - Higher-bit models (Q6_K, Q8_0) → Better accuracy, requires more memory. 📌 Use Quantized Models if: ✔ You are running inference on a CPU and need an optimized model. ✔ Your device has low VRAM and cannot load full-precision models. ✔ You want to reduce memory footprint while keeping reasonable accuracy. 📌 Avoid Quantized Models if: ❌ You need maximum accuracy (full-precision models are better for this). ❌ Your hardware has enough VRAM for higher-precision formats (BF16/F16). --- ### Very Low-Bit Quantization (IQ3_XS, IQ3_S, IQ3_M, Q4_K, Q4_0) These models are optimized for extreme memory efficiency, making them ideal for low-power devices or large-scale deployments where memory is a critical constraint. - IQ3_XS: Ultra-low-bit quantization (3-bit) with extreme memory efficiency. - Use case: Best for ultra-low-memory devices where even Q4_K is too large. - Trade-off: Lower accuracy compared to higher-bit quantizations. - IQ3_S: Small block size for maximum memory efficiency. - Use case: Best for low-memory devices where IQ3_XS is too aggressive. - IQ3_M: Medium block size for better accuracy than IQ3_S. - Use case: Suitable for low-memory devices where IQ3_S is too limiting. - Q4_K: 4-bit quantization with block-wise optimization for better accuracy. - Use case: Best for low-memory devices where Q6_K is too large. - Q4_0: Pure 4-bit quantization, optimized for ARM devices. - Use case: Best for ARM-based devices or low-memory environments. --- ### Summary Table: Model Format Selection \| Model Format \| Precision \| Memory Usage \| Device Requirements \| Best Use Case \| \|--------------\|------------\|---------------\|----------------------\|---------------\| \| BF16 \| Highest \| High \| BF16-supported GPU/CPUs \| High-speed inference with reduced memory \| \| F16 \| High \| High \| FP16-supported devices \| GPU inference when BF16 isn’t available \| \| Q4_K \| Medium Low \| Low \| CPU or Low-VRAM devices \| Best for memory-constrained environments \| \| Q6_K \| Medium \| Moderate \| CPU with more memory \| Better accuracy while still being quantized \| \| Q8_0 \| High \| Moderate \| CPU or GPU with enough VRAM \| Best accuracy among quantized models \| \| IQ3_XS \| Very Low \| Very Low \| Ultra-low-memory devices \| Extreme memory efficiency and low accuracy \| \| Q4_0 \| Low \| Low \| ARM or low-memory devices \| llama.cpp can optimize for ARM devices \| --- ## Included Files & Details ### `Qwen2.5-VL-32B-Instruct-bf16.gguf` - Model weights preserved in BF16. - Use this if you want to requantize the model into a different format. - Best if your device supports BF16 acceleration. ### `Qwen2.5-VL-32B-Instruct-f16.gguf` - Model weights stored in F16. - Use if your device supports FP16, especially if BF16 is not available. ### `Qwen2.5-VL-32B-Instruct-bf16-q8_0.gguf` - Output & embeddings remain in BF16. - All other layers quantized to Q8_0. - Use if your device supports BF16 and you want a quantized version. ### `Qwen2.5-VL-32B-Instruct-f16-q8_0.gguf` - Output & embeddings remain in F16. - All other layers quantized to Q8_0. ### `Qwen2.5-VL-32B-Instruct-q4_k.gguf` - Output & embeddings quantized to Q8_0. - All other layers quantized to Q4_K. - Good for CPU inference with limited memory. ### `Qwen2.5-VL-32B-Instruct-q4_k_s.gguf` - Smallest Q4_K variant, using less memory at the cost of accuracy. - Best for very low-memory setups. ### `Qwen2.5-VL-32B-Instruct-q6_k.gguf` - Output & embeddings quantized to Q8_0. - All other layers quantized to Q6_K . ### `Qwen2.5-VL-32B-Instruct-q8_0.gguf` - Fully Q8 quantized model for better accuracy. - Requires more memory but offers higher precision. ### `Qwen2.5-VL-32B-Instruct-iq3_xs.gguf` - IQ3_XS quantization, optimized for extreme memory efficiency. - Best for ultra-low-memory devices. ### `Qwen2.5-VL-32B-Instruct-iq3_m.gguf` - IQ3_M quantization, offering a medium block size for better accuracy. - Suitable for low-memory devices. ### `Qwen2.5-VL-32B-Instruct-q4_0.gguf` - Pure Q4_0 quantization, optimized for ARM devices. - Best for low-memory environments. - Prefer IQ4_NL for better accuracy. # <span id="testllm" style="color: #7F7FFF;">🚀 If you find these models useful</span> Please click like ❤ . Also I’d really appreciate it if you could test my Network Monitor Assistant at 👉 [Network Monitor Assitant](https://readyforquantum.com). 💬 Click the chat icon (bottom right of the main and dashboard pages) . Choose a LLM; toggle between the LLM Types TurboLLM -> FreeLLM -> TestLLM. ### What I'm Testing I'm experimenting with function calling against my network monitoring service. Using small open source models. I am into the question "How small can it go and still function". 🟡 TestLLM – Runs the current testing model using llama.cpp on 6 threads of a Cpu VM (Should take about 15s to load. Inference speed is quite slow and it only processes one user prompt at a time—still working on scaling!). If you're curious, I'd be happy to share how it works! . ### The other Available AI Assistants 🟢 TurboLLM – Uses gpt-4o-mini Fast! . Note: tokens are limited since OpenAI models are pricey, but you can [Login](https://readyforquantum.com) or [Download](https://readyforquantum.com/download/?utm_source=huggingface&utm_medium=referral&utm_campaign=huggingface_repo_readme) the Quantum Network Monitor agent to get more tokens, Alternatively use the TestLLM . 🔵 HugLLM – Runs open-source Hugging Face models Fast, Runs small models (≈8B) hence lower quality, Get 2x more tokens (subject to Hugging Face API availability) ### Final word I fund the servers to create the models files, run the Quantum Network Monitor Service and Pay for Inference from Novita and OpenAI all from my own pocket. All of the code for creating the models and the work I have done with Quantum Network Monitor is [open source](https://github.com/Mungert69). Feel free to use what you find useful. Please support my work and consider [buying me a coffee](https://www.buymeacoffee.com/mahadeva) . This will help me pay for the services and increase the token limits for everyone. Thank you :) # Qwen2.5-VL-32B-Instruct <a href="https://chat.qwenlm.ai/" target="_blank" style="margin: 2px;"> <img alt="Chat" src="https://img.shields.io/badge/%F0%9F%92%9C%EF%B8%8F%20Qwen%20Chat%20-536af5" style="display: inline-block; vertical-align: middle;"/> </a> ## Latest Updates: In addition to the original formula, we have further enhanced Qwen2.5-VL-32B's mathematical and problem-solving abilities through reinforcement learning. This has also significantly improved the model's subjective user experience, with response styles adjusted to better align with human preferences. Particularly for objective queries such as mathematics, logical reasoning, and knowledge-based Q&A, the level of detail in responses and the clarity of formatting have been noticeably enhanced. ## Introduction In the past five months since Qwen2-VL’s release, numerous developers have built new models on the Qwen2-VL vision-language models, providing us with valuable feedback. During this period, we focused on building more useful vision-language models. Today, we are excited to introduce the latest addition to the Qwen family: Qwen2.5-VL. #### Key Enhancements: * Understand things visually: Qwen2.5-VL is not only proficient in recognizing common objects such as flowers, birds, fish, and insects, but it is highly capable of analyzing texts, charts, icons, graphics, and layouts within images. * Being agentic: Qwen2.5-VL directly plays as a visual agent that can reason and dynamically direct tools, which is capable of computer use and phone use. * Understanding long videos and capturing events: Qwen2.5-VL can comprehend videos of over 1 hour, and this time it has a new ability of cpaturing event by pinpointing the relevant video segments. * Capable of visual localization in different formats: Qwen2.5-VL can accurately localize objects in an image by generating bounding boxes or points, and it can provide stable JSON outputs for coordinates and attributes. * Generating structured outputs: for data like scans of invoices, forms, tables, etc. Qwen2.5-VL supports structured outputs of their contents, benefiting usages in finance, commerce, etc. #### Model Architecture Updates: * Dynamic Resolution and Frame Rate Training for Video Understanding: We extend dynamic resolution to the temporal dimension by adopting dynamic FPS sampling, enabling the model to comprehend videos at various sampling rates. Accordingly, we update mRoPE in the time dimension with IDs and absolute time alignment, enabling the model to learn temporal sequence and speed, and ultimately acquire the ability to pinpoint specific moments. <p align="center"> <img src="https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen2.5-VL/qwen2.5vl_arc.jpeg" width="80%"/> <p> * Streamlined and Efficient Vision Encoder We enhance both training and inference speeds by strategically implementing window attention into the ViT. The ViT architecture is further optimized with SwiGLU and RMSNorm, aligning it with the structure of the Qwen2.5 LLM. We have three models with 3, 7 and 72 billion parameters. This repo contains the instruction-tuned 32B Qwen2.5-VL model. For more information, visit our [Blog](https://qwenlm.github.io/blog/qwen2.5-vl/) and [GitHub](https://github.com/QwenLM/Qwen2.5-VL). ## Evaluation ### Vision \| Dataset \| Qwen2.5-VL-72B<br><sup>([🤗](https://huggingface.co/Qwen/Qwen2.5-VL-72B-Instruct)[🤖](https://modelscope.cn/models/qwen/Qwen2.5-VL-72B-Instruct)) \| Qwen2-VL-72B<br><sup>([🤗](https://huggingface.co/Qwen/Qwen2-VL-72B-Instruct)[🤖](https://modelscope.cn/models/qwen/Qwen2-VL-72B-Instruct)) \| Qwen2.5-VL-32B<br><sup>([🤗](https://huggingface.co/Qwen/Qwen2.5-VL-32B-Instruct)[🤖](https://modelscope.cn/models/qwen/Qwen2.5-VL-32B-Instruct)) \| \|--------------------\|--------\|--------------\|------------------\| \| MMMU \|70.2 \| 64.5 \| 70 \| \| MMMU Pro \|51.1 \| 46.2 \| 49.5 \| \| MMStar \| 70.8 \| 68.3 \| 69.5 \| \| MathVista \| 74.8 \| 70.5 \| 74.7 \| \| MathVision \|38.1 \| 25.9 \| 40.0\| \| OCRBenchV2 \| 61.5/63.7 \| 47.8/46.1 \| 57.2/59.1 \| \| CC-OCR \| 79.8 \| 68.7 \| 77.1 \| \| DocVQA \| 96.4 \| 96.5 \| 94.8 \| \| InfoVQA \| 87.3 \| 84.5 \| 83.4 \| \| LVBench \|47.3 \| - \| 49.00 \| \| CharadesSTA \|50.9 \| - \| 54.2 \| \| VideoMME \|73.3/79.1 \| 71.2/77.8 \| 70.5/77.9 \| \| MMBench-Video \|2.02 \| 1.7 \| 1.93 \| \| AITZ \|83.2 \| - \| 83.1 \| \| Android Control \|67.4/93.7 \| 66.4/84.4 \| 69.6/93.3 \| \| ScreenSpot \|87.1 \| - \| 88.5 \| \| ScreenSpot Pro \|43.6 \| - \| 39.4 \| \| AndroidWorld \|35 \| - \| 22.0 \| \| OSWorld \|8.83 \| - \| 5.92 \| ### Text \| MODEL \| MMLU \| MMLU-PRO \| MATH \| GPQA-diamond \| MBPP \| Human Eval \| \|-----------------\|--------\|----------\|---------\|--------------\|--------\|------------\| \| Qwen2.5-VL-32B \| 78.4 \| 68.8 \| 82.2 \| 46.0 \| 84.0 \| 91.5 \| \| Mistral-Small-3.1-24B \| 80.6 \| 66.8 \| 69.3 \| 46.0 \| 74.7 \| 88.4 \| \| Gemma3-27B-IT \| 76.9 \| 67.5 \| 89 \| 42.4 \| 74.4 \| 87.8 \| \| GPT-4o-Mini \| 82.0 \| 61.7 \| 70.2 \| 39.4 \| 84.8 \| 87.2 \| \| Claude-3.5-Haiku \| 77.6 \| 65.0 \| 69.2 \| 41.6 \| 85.6 \| 88.1 \| ## Requirements The code of Qwen2.5-VL has been in the latest Hugging face transformers and we advise you to build from source with command: ``` pip install git+https://github.com/huggingface/transformers accelerate ``` or you might encounter the following error: ``` KeyError: 'qwen2_5_vl' ``` ## Quickstart Below, we provide simple examples to show how to use Qwen2.5-VL with 🤖 ModelScope and 🤗 Transformers. The code of Qwen2.5-VL has been in the latest Hugging face transformers and we advise you to build from source with command: ``` pip install git+https://github.com/huggingface/transformers accelerate ``` or you might encounter the following error: ``` KeyError: 'qwen2_5_vl' ``` We offer a toolkit to help you handle various types of visual input more conveniently, as if you were using an API. This includes base64, URLs, and interleaved images and videos. You can install it using the following command: ```bash # It's highly recommanded to use `[decord]` feature for faster video loading. pip install qwen-vl-utils[decord]==0.0.8 ``` If you are not using Linux, you might not be able to install `decord` from PyPI. In that case, you can use `pip install qwen-vl-utils` which will fall back to using torchvision for video processing. However, you can still [install decord from source](https://github.com/dmlc/decord?tab=readme-ov-file#install-from-source) to get decord used when loading video. ### Using 🤗 Transformers to Chat Here we show a code snippet to show you how to use the chat model with `transformers` and `qwen_vl_utils`: ```python from transformers import Qwen2_5_VLForConditionalGeneration, AutoTokenizer, AutoProcessor from qwen_vl_utils import process_vision_info # default: Load the model on the available device(s) model = Qwen2_5_VLForConditionalGeneration.from_pretrained( "Qwen/Qwen2.5-VL-32B-Instruct", torch_dtype="auto", device_map="auto" ) # We recommend enabling flash_attention_2 for better acceleration and memory saving, especially in multi-image and video scenarios. # model = Qwen2_5_VLForConditionalGeneration.from_pretrained( # "Qwen/Qwen2.5-VL-32B-Instruct", # torch_dtype=torch.bfloat16, # attn_implementation="flash_attention_2", # device_map="auto", # ) # default processer processor = AutoProcessor.from_pretrained("Qwen/Qwen2.5-VL-32B-Instruct") # The default range for the number of visual tokens per image in the model is 4-16384. # You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost. # min_pixels = 2562828 # max_pixels = 12802828 # processor = AutoProcessor.from_pretrained("Qwen/Qwen2.5-VL-32B-Instruct", min_pixels=min_pixels, max_pixels=max_pixels) messages = [ { "role": "user", "content": [ { "type": "image", "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg", }, {"type": "text", "text": "Describe this image."}, ], } ] # Preparation for inference text = processor.apply_chat_template( messages, tokenize=False, add_generation_prompt=True ) image_inputs, video_inputs = process_vision_info(messages) inputs = processor( text=[text], images=image_inputs, videos=video_inputs, padding=True, return_tensors="pt", ) inputs = inputs.to("cuda") # Inference: Generation of the output generated_ids = model.generate(inputs, max_new_tokens=128) generated_ids_trimmed = [ out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids) ] output_text = processor.batch_decode( generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False ) print(output_text) ``` <details> <summary>Multi image inference</summary> ```python # Messages containing multiple images and a text query messages = [ { "role": "user", "content": [ {"type": "image", "image": "file:///path/to/image1.jpg"}, {"type": "image", "image": "file:///path/to/image2.jpg"}, {"type": "text", "text": "Identify the similarities between these images."}, ], } ] # Preparation for inference text = processor.apply_chat_template( messages, tokenize=False, add_generation_prompt=True ) image_inputs, video_inputs = process_vision_info(messages) inputs = processor( text=[text], images=image_inputs, videos=video_inputs, padding=True, return_tensors="pt", ) inputs = inputs.to("cuda") # Inference generated_ids = model.generate(inputs, max_new_tokens=128) generated_ids_trimmed = [ out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids) ] output_text = processor.batch_decode( generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False ) print(output_text) ``` </details> <details> <summary>Video inference</summary> ```python # Messages containing a images list as a video and a text query messages = [ { "role": "user", "content": [ { "type": "video", "video": [ "file:///path/to/frame1.jpg", "file:///path/to/frame2.jpg", "file:///path/to/frame3.jpg", "file:///path/to/frame4.jpg", ], }, {"type": "text", "text": "Describe this video."}, ], } ] # Messages containing a local video path and a text query messages = [ { "role": "user", "content": [ { "type": "video", "video": "file:///path/to/video1.mp4", "max_pixels": 360 * 420, "fps": 1.0, }, {"type": "text", "text": "Describe this video."}, ], } ] # Messages containing a video url and a text query messages = [ { "role": "user", "content": [ { "type": "video", "video": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen2-VL/space_woaudio.mp4", }, {"type": "text", "text": "Describe this video."}, ], } ] #In Qwen 2.5 VL, frame rate information is also input into the model to align with absolute time. # Preparation for inference text = processor.apply_chat_template( messages, tokenize=False, add_generation_prompt=True ) image_inputs, video_inputs, video_kwargs = process_vision_info(messages, return_video_kwargs=True) inputs = processor( text=[text], images=image_inputs, videos=video_inputs, fps=fps, padding=True, return_tensors="pt", video_kwargs, ) inputs = inputs.to("cuda") # Inference generated_ids = model.generate(inputs, max_new_tokens=128) generated_ids_trimmed = [ out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids) ] output_text = processor.batch_decode( generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False ) print(output_text) ``` Video URL compatibility largely depends on the third-party library version. The details are in the table below. change the backend by `FORCE_QWENVL_VIDEO_READER=torchvision` or `FORCE_QWENVL_VIDEO_READER=decord` if you prefer not to use the default one. \| Backend \| HTTP \| HTTPS \| \|-------------\|------\|-------\| \| torchvision >= 0.19.0 \| ✅ \| ✅ \| \| torchvision < 0.19.0 \| ❌ \| ❌ \| \| decord \| ✅ \| ❌ \| </details> <details> <summary>Batch inference</summary> ```python # Sample messages for batch inference messages1 = [ { "role": "user", "content": [ {"type": "image", "image": "file:///path/to/image1.jpg"}, {"type": "image", "image": "file:///path/to/image2.jpg"}, {"type": "text", "text": "What are the common elements in these pictures?"}, ], } ] messages2 = [ {"role": "system", "content": "You are a helpful assistant."}, {"role": "user", "content": "Who are you?"}, ] # Combine messages for batch processing messages = [messages1, messages2] # Preparation for batch inference texts = [ processor.apply_chat_template(msg, tokenize=False, add_generation_prompt=True) for msg in messages ] image_inputs, video_inputs = process_vision_info(messages) inputs = processor( text=texts, images=image_inputs, videos=video_inputs, padding=True, return_tensors="pt", ) inputs = inputs.to("cuda") # Batch Inference generated_ids = model.generate(*inputs, max_new_tokens=128) generated_ids_trimmed = [ out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids) ] output_texts = processor.batch_decode( generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False ) print(output_texts) ``` </details> ### 🤖 ModelScope We strongly advise users especially those in mainland China to use ModelScope. `snapshot_download` can help you solve issues concerning downloading checkpoints. ### More Usage Tips For input images, we support local files, base64, and URLs. For videos, we currently only support local files. ```python # You can directly insert a local file path, a URL, or a base64-encoded image into the position where you want in the text. ## Local file path messages = [ { "role": "user", "content": [ {"type": "image", "image": "file:///path/to/your/image.jpg"}, {"type": "text", "text": "Describe this image."}, ], } ] ## Image URL messages = [ { "role": "user", "content": [ {"type": "image", "image": "http://path/to/your/image.jpg"}, {"type": "text", "text": "Describe this image."}, ], } ] ## Base64 encoded image messages = [ { "role": "user", "content": [ {"type": "image", "image": "data:image;base64,/9j/..."}, {"type": "text", "text": "Describe this image."}, ], } ] ``` #### Image Resolution for performance boost The model supports a wide range of resolution inputs. By default, it uses the native resolution for input, but higher resolutions can enhance performance at the cost of more computation. Users can set the minimum and maximum number of pixels to achieve an optimal configuration for their needs, such as a token count range of 256-1280, to balance speed and memory usage. ```python min_pixels = 256 28 * 28 max_pixels = 1280 * 28 * 28 processor = AutoProcessor.from_pretrained( "Qwen/Qwen2.5-VL-32B-Instruct", min_pixels=min_pixels, max_pixels=max_pixels ) ``` Besides, We provide two methods for fine-grained control over the image size input to the model: 1. Define min_pixels and max_pixels: Images will be resized to maintain their aspect ratio within the range of min_pixels and max_pixels. 2. Specify exact dimensions: Directly set `resized_height` and `resized_width`. These values will be rounded to the nearest multiple of 28. ```python # min_pixels and max_pixels messages = [ { "role": "user", "content": [ { "type": "image", "image": "file:///path/to/your/image.jpg", "resized_height": 280, "resized_width": 420, }, {"type": "text", "text": "Describe this image."}, ], } ] # resized_height and resized_width messages = [ { "role": "user", "content": [ { "type": "image", "image": "file:///path/to/your/image.jpg", "min_pixels": 50176, "max_pixels": 50176, }, {"type": "text", "text": "Describe this image."}, ], } ] ``` ### Processing Long Texts The current `config.json` is set for context length up to 32,768 tokens. To handle extensive inputs exceeding 32,768 tokens, we utilize [YaRN](https://arxiv.org/abs/2309.00071), a technique for enhancing model length extrapolation, ensuring optimal performance on lengthy texts. For supported frameworks, you could add the following to `config.json` to enable YaRN: { ..., "type": "yarn", "mrope_section": [ 16, 24, 24 ], "factor": 4, "original_max_position_embeddings": 32768 } However, it should be noted that this method has a significant impact on the performance of temporal and spatial localization tasks, and is therefore not recommended for use. At the same time, for long video inputs, since MRoPE itself is more economical with ids, the max_position_embeddings can be directly modified to a larger value, such as 64k. ## Citation If you find our work helpful, feel free to give us a cite. ``` @article{Qwen2.5-VL, title={Qwen2.5-VL Technical Report}, author={Bai, Shuai and Chen, Keqin and Liu, Xuejing and Wang, Jialin and Ge, Wenbin and Song, Sibo and Dang, Kai and Wang, Peng and Wang, Shijie and Tang, Jun and Zhong, Humen and Zhu, Yuanzhi and Yang, Mingkun and Li, Zhaohai and Wan, Jianqiang and Wang, Pengfei and Ding, Wei and Fu, Zheren and Xu, Yiheng and Ye, Jiabo and Zhang, Xi and Xie, Tianbao and Cheng, Zesen and Zhang, Hang and Yang, Zhibo and Xu, Haiyang and Lin, Junyang}, journal={arXiv preprint arXiv:2502.13923}, year={2025} } ```
Mungert/gemma-3-27b-it-GGUF	Mungert	2025-06-15T19:42:42Z	849	8	transformers	[ "transformers", "gguf", "image-text-to-text", "arxiv:1905.07830", "arxiv:1905.10044", "arxiv:1911.11641", "arxiv:1904.09728", "arxiv:1705.03551", "arxiv:1911.01547", "arxiv:1907.10641", "arxiv:1903.00161", "arxiv:2009.03300", "arxiv:2304.06364", "arxiv:2103.03874", "arxiv:2110.14168", "arxiv:2311.12022", "arxiv:2108.07732", "arxiv:2107.03374", "arxiv:2210.03057", "arxiv:2106.03193", "arxiv:1910.11856", "arxiv:2502.12404", "arxiv:2502.21228", "arxiv:2404.16816", "arxiv:2104.12756", "arxiv:2311.16502", "arxiv:2203.10244", "arxiv:2404.12390", "arxiv:1810.12440", "arxiv:1908.02660", "base_model:google/gemma-3-27b-pt", "base_model:quantized:google/gemma-3-27b-pt", "license:gemma", "endpoints_compatible", "region:us", "imatrix", "conversational" ]	image-text-to-text	2025-03-26T03:50:50Z	--- license: gemma library_name: transformers pipeline_tag: image-text-to-text extra_gated_heading: Access Gemma on Hugging Face extra_gated_prompt: To access Gemma on Hugging Face, you’re required to review and agree to Google’s usage license. To do this, please ensure you’re logged in to Hugging Face and click below. Requests are processed immediately. extra_gated_button_content: Acknowledge license base_model: google/gemma-3-27b-pt --- # <span style="color: #7FFF7F;">gemma-3-27b-it GGUF Models</span> ## How to Use Gemma 3 Vision with llama.cpp To utilize the experimental support for Gemma 3 Vision in `llama.cpp`, follow these steps: 1. Clone the lastest llama.cpp Repository: ```bash git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp ``` 2. Build the Llama.cpp: Build llama.cpp as usual : https://github.com/ggml-org/llama.cpp#building-the-project Once llama.cpp is built Copy the ./llama.cpp/build/bin/llama-gemma3-cli to a chosen folder. 3. Download the Gemma 3 gguf file: https://huggingface.co/Mungert/gemma-3-4b-it-gguf/tree/main Choose a gguf file without the mmproj in the name Example gguf file : https://huggingface.co/Mungert/gemma-3-4b-it-gguf/resolve/main/google_gemma-3-4b-it-q4_k_l.gguf Copy this file to your chosen folder. 4. Download the Gemma 3 mmproj file https://huggingface.co/Mungert/gemma-3-4b-it-gguf/tree/main Choose a file with mmproj in the name Example mmproj file : https://huggingface.co/Mungert/gemma-3-4b-it-gguf/resolve/main/google_gemma-3-4b-it-mmproj-bf16.gguf Copy this file to your chosen folder. 5. Copy images to the same folder as the gguf files or alter paths appropriately. In the example below the gguf files, images and llama-gemma-cli are in the same folder. Example image: image https://huggingface.co/Mungert/gemma-3-4b-it-gguf/resolve/main/car-1.jpg Copy this file to your chosen folder. 6. Run the CLI Tool: From your chosen folder : ```bash llama-gemma3-cli -m google_gemma-3-4b-it-q4_k_l.gguf --mmproj google_gemma-3-4b-it-mmproj-bf16.gguf ``` ``` Running in chat mode, available commands: /image <path> load an image /clear clear the chat history /quit or /exit exit the program > /image car-1.jpg Encoding image car-1.jpg Image encoded in 46305 ms Image decoded in 19302 ms > what is the image of Here's a breakdown of what's in the image: Subject: The primary subject is a black Porsche Panamera Turbo driving on a highway. Details: * Car: It's a sleek, modern Porsche Panamera Turbo, identifiable by its distinctive rear design, the "PORSCHE" lettering, and the "Panamera Turbo" badge. The license plate reads "CVC-911". * Setting: The car is on a multi-lane highway, with a blurred background of trees, a distant building, and a cloudy sky. The lighting suggests it's either dusk or dawn. * Motion: The image captures the car in motion, with a slight motion blur to convey speed. Overall Impression: The image conveys a sense of speed, luxury, and power. It's a well-composed shot that highlights the car's design and performance. Do you want me to describe any specific aspect of the image in more detail, or perhaps analyze its composition? ``` ## Ultra-Low-Bit Quantization with IQ-DynamicGate (1-2 bit) Our latest quantization method introduces precision-adaptive quantization for ultra-low-bit models (1-2 bit), with benchmark-proven improvements on Llama-3-8B. This approach uses layer-specific strategies to preserve accuracy while maintaining extreme memory efficiency. ### Benchmark Context All tests conducted on Llama-3-8B-Instruct using: - Standard perplexity evaluation pipeline - 2048-token context window - Same prompt set across all quantizations ### Key Improvements - Dynamic Precision Allocation: - First/Last 25% of layers → IQ4_XS (selected layers) - Middle 50% → IQ2_XXS/IQ3_S (increase efficiency) - Critical Component Protection: - Embeddings/output layers use Q5_K - Reduces error propagation by 38% vs standard 1-2bit ### Quantization Performance Comparison (Llama-3-8B) \| Quantization \| Standard PPL \| DynamicGate PPL \| Δ PPL \| Std Size \| DG Size \| Δ Size \| Std Speed \| DG Speed \| \|--------------\|--------------\|------------------\|---------\|----------\|---------\|--------\|-----------\|----------\| \| IQ2_XXS \| 11.30 \| 9.84 \| -12.9% \| 2.5G \| 2.6G \| +0.1G \| 234s \| 246s \| \| IQ2_XS \| 11.72 \| 11.63 \| -0.8% \| 2.7G \| 2.8G \| +0.1G \| 242s \| 246s \| \| IQ2_S \| 14.31 \| 9.02 \| -36.9% \| 2.7G \| 2.9G \| +0.2G \| 238s \| 244s \| \| IQ1_M \| 27.46 \| 15.41 \| -43.9% \| 2.2G \| 2.5G \| +0.3G \| 206s \| 212s \| \| IQ1_S \| 53.07 \| 32.00 \| -39.7% \| 2.1G \| 2.4G \| +0.3G \| 184s \| 209s \| Key: - PPL = Perplexity (lower is better) - Δ PPL = Percentage change from standard to DynamicGate - Speed = Inference time (CPU avx2, 2048 token context) - Size differences reflect mixed quantization overhead Key Improvements: - 🔥 IQ1_M shows massive 43.9% perplexity reduction (27.46 → 15.41) - 🚀 IQ2_S cuts perplexity by 36.9% while adding only 0.2GB - ⚡ IQ1_S maintains 39.7% better accuracy despite 1-bit quantization Tradeoffs: - All variants have modest size increases (0.1-0.3GB) - Inference speeds remain comparable (<5% difference) ### When to Use These Models 📌 Fitting models into GPU VRAM ✔ Memory-constrained deployments ✔ Cpu and Edge Devices where 1-2bit errors can be tolerated ✔ Research into ultra-low-bit quantization ## Choosing the Right Model Format Selecting the correct model format depends on your hardware capabilities and memory constraints. ### BF16 (Brain Float 16) – Use if BF16 acceleration is available - A 16-bit floating-point format designed for faster computation while retaining good precision. - Provides similar dynamic range as FP32 but with lower memory usage. - Recommended if your hardware supports BF16 acceleration (check your device’s specs). - Ideal for high-performance inference with reduced memory footprint compared to FP32. 📌 Use BF16 if: ✔ Your hardware has native BF16 support (e.g., newer GPUs, TPUs). ✔ You want higher precision while saving memory. ✔ You plan to requantize the model into another format. 📌 Avoid BF16 if: ❌ Your hardware does not support BF16 (it may fall back to FP32 and run slower). ❌ You need compatibility with older devices that lack BF16 optimization. --- ### F16 (Float 16) – More widely supported than BF16 - A 16-bit floating-point high precision but with less of range of values than BF16. - Works on most devices with FP16 acceleration support (including many GPUs and some CPUs). - Slightly lower numerical precision than BF16 but generally sufficient for inference. 📌 Use F16 if: ✔ Your hardware supports FP16 but not BF16. ✔ You need a balance between speed, memory usage, and accuracy. ✔ You are running on a GPU or another device optimized for FP16 computations. 📌 Avoid F16 if: ❌ Your device lacks native FP16 support (it may run slower than expected). ❌ You have memory limitations. --- ### Quantized Models (Q4_K, Q6_K, Q8, etc.) – For CPU & Low-VRAM Inference Quantization reduces model size and memory usage while maintaining as much accuracy as possible. - Lower-bit models (Q4_K) → Best for minimal memory usage, may have lower precision. - Higher-bit models (Q6_K, Q8_0) → Better accuracy, requires more memory. 📌 Use Quantized Models if: ✔ You are running inference on a CPU and need an optimized model. ✔ Your device has low VRAM and cannot load full-precision models. ✔ You want to reduce memory footprint while keeping reasonable accuracy. 📌 Avoid Quantized Models if: ❌ You need maximum accuracy (full-precision models are better for this). ❌ Your hardware has enough VRAM for higher-precision formats (BF16/F16). --- ### Very Low-Bit Quantization (IQ3_XS, IQ3_S, IQ3_M, Q4_K, Q4_0) These models are optimized for extreme memory efficiency, making them ideal for low-power devices or large-scale deployments where memory is a critical constraint. - IQ3_XS: Ultra-low-bit quantization (3-bit) with extreme memory efficiency. - Use case: Best for ultra-low-memory devices where even Q4_K is too large. - Trade-off: Lower accuracy compared to higher-bit quantizations. - IQ3_S: Small block size for maximum memory efficiency. - Use case: Best for low-memory devices where IQ3_XS is too aggressive. - IQ3_M: Medium block size for better accuracy than IQ3_S. - Use case: Suitable for low-memory devices where IQ3_S is too limiting. - Q4_K: 4-bit quantization with block-wise optimization for better accuracy. - Use case: Best for low-memory devices where Q6_K is too large. - Q4_0: Pure 4-bit quantization, optimized for ARM devices. - Use case: Best for ARM-based devices or low-memory environments. --- ### Summary Table: Model Format Selection \| Model Format \| Precision \| Memory Usage \| Device Requirements \| Best Use Case \| \|--------------\|------------\|---------------\|----------------------\|---------------\| \| BF16 \| Highest \| High \| BF16-supported GPU/CPUs \| High-speed inference with reduced memory \| \| F16 \| High \| High \| FP16-supported devices \| GPU inference when BF16 isn’t available \| \| Q4_K \| Medium Low \| Low \| CPU or Low-VRAM devices \| Best for memory-constrained environments \| \| Q6_K \| Medium \| Moderate \| CPU with more memory \| Better accuracy while still being quantized \| \| Q8_0 \| High \| Moderate \| CPU or GPU with enough VRAM \| Best accuracy among quantized models \| \| IQ3_XS \| Very Low \| Very Low \| Ultra-low-memory devices \| Extreme memory efficiency and low accuracy \| \| Q4_0 \| Low \| Low \| ARM or low-memory devices \| llama.cpp can optimize for ARM devices \| --- ## Included Files & Details ### `gemma-3-27b-it-bf16.gguf` - Model weights preserved in BF16. - Use this if you want to requantize the model into a different format. - Best if your device supports BF16 acceleration. ### `gemma-3-27b-it-f16.gguf` - Model weights stored in F16. - Use if your device supports FP16, especially if BF16 is not available. ### `gemma-3-27b-it-bf16-q8_0.gguf` - Output & embeddings remain in BF16. - All other layers quantized to Q8_0. - Use if your device supports BF16 and you want a quantized version. ### `gemma-3-27b-it-f16-q8_0.gguf` - Output & embeddings remain in F16. - All other layers quantized to Q8_0. ### `gemma-3-27b-it-q4_k.gguf` - Output & embeddings quantized to Q8_0. - All other layers quantized to Q4_K. - Good for CPU inference with limited memory. ### `gemma-3-27b-it-q4_k_s.gguf` - Smallest Q4_K variant, using less memory at the cost of accuracy. - Best for very low-memory setups. ### `gemma-3-27b-it-q6_k.gguf` - Output & embeddings quantized to Q8_0. - All other layers quantized to Q6_K . ### `gemma-3-27b-it-q8_0.gguf` - Fully Q8 quantized model for better accuracy. - Requires more memory but offers higher precision. ### `gemma-3-27b-it-iq3_xs.gguf` - IQ3_XS quantization, optimized for extreme memory efficiency. - Best for ultra-low-memory devices. ### `gemma-3-27b-it-iq3_m.gguf` - IQ3_M quantization, offering a medium block size for better accuracy. - Suitable for low-memory devices. ### `gemma-3-27b-it-q4_0.gguf` - Pure Q4_0 quantization, optimized for ARM devices. - Best for low-memory environments. - Prefer IQ4_NL for better accuracy. # <span id="testllm" style="color: #7F7FFF;">🚀 If you find these models useful</span> Please click like ❤ . Also I’d really appreciate it if you could test my Network Monitor Assistant at 👉 [Network Monitor Assitant](https://readyforquantum.com). 💬 Click the chat icon (bottom right of the main and dashboard pages) . Choose a LLM; toggle between the LLM Types TurboLLM -> FreeLLM -> TestLLM. ### What I'm Testing I'm experimenting with function calling against my network monitoring service. Using small open source models. I am into the question "How small can it go and still function". 🟡 TestLLM – Runs the current testing model using llama.cpp on 6 threads of a Cpu VM (Should take about 15s to load. Inference speed is quite slow and it only processes one user prompt at a time—still working on scaling!). If you're curious, I'd be happy to share how it works! . ### The other Available AI Assistants 🟢 TurboLLM – Uses gpt-4o-mini Fast! . Note: tokens are limited since OpenAI models are pricey, but you can [Login](https://readyforquantum.com) or [Download](https://readyforquantum.com/download/?utm_source=huggingface&utm_medium=referral&utm_campaign=huggingface_repo_readme) the Quantum Network Monitor agent to get more tokens, Alternatively use the TestLLM . 🔵 HugLLM – Runs open-source Hugging Face models Fast, Runs small models (≈8B) hence lower quality, Get 2x more tokens (subject to Hugging Face API availability) ### 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! 😊 # <span style="color: #7FFF7F;">gemma-3-27b-it GGUF Models</span> ## Choosing the Right Model Format Selecting the correct model format depends on your hardware capabilities and memory constraints. ### BF16 (Brain Float 16) – Use if BF16 acceleration is available - A 16-bit floating-point format designed for faster computation while retaining good precision. - Provides similar dynamic range as FP32 but with lower memory usage. - Recommended if your hardware supports BF16 acceleration (check your device’s specs). - Ideal for high-performance inference with reduced memory footprint compared to FP32. 📌 Use BF16 if: ✔ Your hardware has native BF16 support (e.g., newer GPUs, TPUs). ✔ You want higher precision while saving memory. ✔ You plan to requantize the model into another format. 📌 Avoid BF16 if: ❌ Your hardware does not support BF16 (it may fall back to FP32 and run slower). ❌ You need compatibility with older devices that lack BF16 optimization. --- ### F16 (Float 16) – More widely supported than BF16 - A 16-bit floating-point high precision but with less of range of values than BF16. - Works on most devices with FP16 acceleration support (including many GPUs and some CPUs). - Slightly lower numerical precision than BF16 but generally sufficient for inference. 📌 Use F16 if: ✔ Your hardware supports FP16 but not BF16. ✔ You need a balance between speed, memory usage, and accuracy. ✔ You are running on a GPU or another device optimized for FP16 computations. 📌 Avoid F16 if: ❌ Your device lacks native FP16 support (it may run slower than expected). ❌ You have memory limitations. --- ### Quantized Models (Q4_K, Q6_K, Q8, etc.) – For CPU & Low-VRAM Inference Quantization reduces model size and memory usage while maintaining as much accuracy as possible. - Lower-bit models (Q4_K) → Best for minimal memory usage, may have lower precision. - Higher-bit models (Q6_K, Q8_0) → Better accuracy, requires more memory. 📌 Use Quantized Models if: ✔ You are running inference on a CPU and need an optimized model. ✔ Your device has low VRAM and cannot load full-precision models. ✔ You want to reduce memory footprint while keeping reasonable accuracy. 📌 Avoid Quantized Models if: ❌ You need maximum accuracy (full-precision models are better for this). ❌ Your hardware has enough VRAM for higher-precision formats (BF16/F16). --- ### Very Low-Bit Quantization (IQ3_XS, IQ3_S, IQ3_M, Q4_K, Q4_0) These models are optimized for extreme memory efficiency, making them ideal for low-power devices or large-scale deployments where memory is a critical constraint. - IQ3_XS: Ultra-low-bit quantization (3-bit) with extreme memory efficiency. - Use case: Best for ultra-low-memory devices where even Q4_K is too large. - Trade-off: Lower accuracy compared to higher-bit quantizations. - IQ3_S: Small block size for maximum memory efficiency. - Use case: Best for low-memory devices where IQ3_XS is too aggressive. - IQ3_M: Medium block size for better accuracy than IQ3_S. - Use case: Suitable for low-memory devices where IQ3_S is too limiting. - Q4_K: 4-bit quantization with block-wise optimization for better accuracy. - Use case: Best for low-memory devices where Q6_K is too large. - Q4_0: Pure 4-bit quantization, optimized for ARM devices. - Use case: Best for ARM-based devices or low-memory environments. --- ### Summary Table: Model Format Selection \| Model Format \| Precision \| Memory Usage \| Device Requirements \| Best Use Case \| \|--------------\|------------\|---------------\|----------------------\|---------------\| \| BF16 \| Highest \| High \| BF16-supported GPU/CPUs \| High-speed inference with reduced memory \| \| F16 \| High \| High \| FP16-supported devices \| GPU inference when BF16 isn’t available \| \| Q4_K \| Medium Low \| Low \| CPU or Low-VRAM devices \| Best for memory-constrained environments \| \| Q6_K \| Medium \| Moderate \| CPU with more memory \| Better accuracy while still being quantized \| \| Q8_0 \| High \| Moderate \| CPU or GPU with enough VRAM \| Best accuracy among quantized models \| \| IQ3_XS \| Very Low \| Very Low \| Ultra-low-memory devices \| Extreme memory efficiency and low accuracy \| \| Q4_0 \| Low \| Low \| ARM or low-memory devices \| llama.cpp can optimize for ARM devices \| --- ## Included Files & Details ### `gemma-3-27b-it-bf16.gguf` - Model weights preserved in BF16. - Use this if you want to requantize the model into a different format. - Best if your device supports BF16 acceleration. ### `gemma-3-27b-it-f16.gguf` - Model weights stored in F16. - Use if your device supports FP16, especially if BF16 is not available. ### `gemma-3-27b-it-bf16-q8_0.gguf` - Output & embeddings remain in BF16. - All other layers quantized to Q8_0. - Use if your device supports BF16 and you want a quantized version. ### `gemma-3-27b-it-f16-q8_0.gguf` - Output & embeddings remain in F16. - All other layers quantized to Q8_0. ### `gemma-3-27b-it-q4_k.gguf` - Output & embeddings quantized to Q8_0. - All other layers quantized to Q4_K. - Good for CPU inference with limited memory. ### `gemma-3-27b-it-q4_k_s.gguf` - Smallest Q4_K variant, using less memory at the cost of accuracy. - Best for very low-memory setups. ### `gemma-3-27b-it-q6_k.gguf` - Output & embeddings quantized to Q8_0. - All other layers quantized to Q6_K . ### `gemma-3-27b-it-q8_0.gguf` - Fully Q8 quantized model for better accuracy. - Requires more memory but offers higher precision. ### `gemma-3-27b-it-iq3_xs.gguf` - IQ3_XS quantization, optimized for extreme memory efficiency. - Best for ultra-low-memory devices. ### `gemma-3-27b-it-iq3_m.gguf` - IQ3_M quantization, offering a medium block size for better accuracy. - Suitable for low-memory devices. ### `gemma-3-27b-it-q4_0.gguf` - Pure Q4_0 quantization, optimized for ARM devices. - Best for low-memory environments. - Prefer IQ4_NL for better accuracy. # <span id="testllm" style="color: #7F7FFF;">🚀 If you find these models useful</span> Please click like ❤ . Also I’d really appreciate it if you could test my Network Monitor Assistant at 👉 [Network Monitor Assitant](https://readyforquantum.com). 💬 Click the chat icon (bottom right of the main and dashboard pages) . Choose a LLM; toggle between the LLM Types TurboLLM -> FreeLLM -> TestLLM. ### What I'm Testing I'm experimenting with function calling against my network monitoring service. Using small open source models. I am into the question "How small can it go and still function". 🟡 TestLLM – Runs the current testing model using llama.cpp on 6 threads of a Cpu VM (Should take about 15s to load. Inference speed is quite slow and it only processes one user prompt at a time—still working on scaling!). If you're curious, I'd be happy to share how it works! . ### The other Available AI Assistants 🟢 TurboLLM – Uses gpt-4o-mini Fast! . Note: tokens are limited since OpenAI models are pricey, but you can [Login](https://readyforquantum.com) or [Download](https://readyforquantum.com/download/?utm_source=huggingface&utm_medium=referral&utm_campaign=huggingface_repo_readme) the Quantum Network Monitor agent to get more tokens, Alternatively use the TestLLM . 🔵 HugLLM – Runs open-source Hugging Face models Fast, Runs small models (≈8B) hence lower quality, Get 2x more tokens (subject to Hugging Face API availability) ### 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! 😊 # Gemma 3 model card Model Page: [Gemma](https://ai.google.dev/gemma/docs/core) Resources and Technical Documentation: * [Gemma 3 Technical Report][g3-tech-report] * [Responsible Generative AI Toolkit][rai-toolkit] * [Gemma on Kaggle][kaggle-gemma] * [Gemma on Vertex Model Garden][vertex-mg-gemma3] Terms of Use: [Terms][terms] Authors: Google DeepMind ## Model Information Summary description and brief definition of inputs and outputs. ### Description Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models. Gemma 3 models are multimodal, handling text and image input and generating text output, with open weights for both pre-trained variants and instruction-tuned variants. Gemma 3 has a large, 128K context window, multilingual support in over 140 languages, and is available in more sizes than previous versions. Gemma 3 models are well-suited for a variety of text generation and image understanding tasks, including question answering, summarization, and reasoning. Their relatively small size makes it possible to deploy them in environments with limited resources such as laptops, desktops or your own cloud infrastructure, democratizing access to state of the art AI models and helping foster innovation for everyone. ### Inputs and outputs - Input: - Text string, such as a question, a prompt, or a document to be summarized - Images, normalized to 896 x 896 resolution and encoded to 256 tokens each - Total input context of 128K tokens for the 4B, 12B, and 27B sizes, and 32K tokens for the 1B size - Output: - Generated text in response to the input, such as an answer to a question, analysis of image content, or a summary of a document - Total output context of 8192 tokens ### Usage Below there are some code snippets on how to get quickly started with running the model. First, install the Transformers library. Gemma 3 is supported starting from transformers 4.50.0. ```sh $ pip install -U transformers ``` Then, copy the snippet from the section that is relevant for your use case. #### Running with the `pipeline` API You can initialize the model and processor for inference with `pipeline` as follows. ```python from transformers import pipeline import torch pipe = pipeline( "image-text-to-text", model="google/gemma-3-27b-it", device="cuda", torch_dtype=torch.bfloat16 ) ``` With instruction-tuned models, you need to use chat templates to process our inputs first. Then, you can pass it to the pipeline. ```python messages = [ { "role": "system", "content": [{"type": "text", "text": "You are a helpful assistant."}] }, { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] } ] output = pipe(text=messages, max_new_tokens=200) print(output[0]["generated_text"][-1]["content"]) # Okay, let's take a look! # Based on the image, the animal on the candy is a turtle. # You can see the shell shape and the head and legs. ``` #### Running the model on a single/multi GPU ```python # pip install accelerate from transformers import AutoProcessor, Gemma3ForConditionalGeneration from PIL import Image import requests import torch model_id = "google/gemma-3-27b-it" model = Gemma3ForConditionalGeneration.from_pretrained( model_id, device_map="auto" ).eval() processor = AutoProcessor.from_pretrained(model_id) messages = [ { "role": "system", "content": [{"type": "text", "text": "You are a helpful assistant."}] }, { "role": "user", "content": [ {"type": "image", "image": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/bee.jpg"}, {"type": "text", "text": "Describe this image in detail."} ] } ] inputs = processor.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt" ).to(model.device, dtype=torch.bfloat16) input_len = inputs["input_ids"].shape[-1] with torch.inference_mode(): generation = model.generate(inputs, max_new_tokens=100, do_sample=False) generation = generation[0][input_len:] decoded = processor.decode(generation, skip_special_tokens=True) print(decoded) # Overall Impression:** The image is a close-up shot of a vibrant garden scene, # focusing on a cluster of pink cosmos flowers and a busy bumblebee. # It has a slightly soft, natural feel, likely captured in daylight. ``` ### Citation ```none @article{gemma_2025, title={Gemma 3}, url={https://goo.gle/Gemma3Report}, publisher={Kaggle}, author={Gemma Team}, year={2025} } ``` ## Model Data Data used for model training and how the data was processed. ### Training Dataset These models were trained on a dataset of text data that includes a wide variety of sources. The 27B model was trained with 14 trillion tokens, the 12B model was trained with 12 trillion tokens, 4B model was trained with 4 trillion tokens and 1B with 2 trillion tokens. Here are the key components: - Web Documents: A diverse collection of web text ensures the model is exposed to a broad range of linguistic styles, topics, and vocabulary. The training dataset includes content in over 140 languages. - Code: Exposing the model to code helps it to learn the syntax and patterns of programming languages, which improves its ability to generate code and understand code-related questions. - Mathematics: Training on mathematical text helps the model learn logical reasoning, symbolic representation, and to address mathematical queries. - Images: A wide range of images enables the model to perform image analysis and visual data extraction tasks. The combination of these diverse data sources is crucial for training a powerful multimodal model that can handle a wide variety of different tasks and data formats. ### Data Preprocessing Here are the key data cleaning and filtering methods applied to the training data: - CSAM Filtering: Rigorous CSAM (Child Sexual Abuse Material) filtering was applied at multiple stages in the data preparation process to ensure the exclusion of harmful and illegal content. - Sensitive Data Filtering: As part of making Gemma pre-trained models safe and reliable, automated techniques were used to filter out certain personal information and other sensitive data from training sets. - Additional methods: Filtering based on content quality and safety in line with [our policies][safety-policies]. ## Implementation Information Details about the model internals. ### Hardware Gemma was trained using [Tensor Processing Unit (TPU)][tpu] hardware (TPUv4p, TPUv5p and TPUv5e). Training vision-language models (VLMS) requires significant computational power. TPUs, designed specifically for matrix operations common in machine learning, offer several advantages in this domain: - Performance: TPUs are specifically designed to handle the massive computations involved in training VLMs. They can speed up training considerably compared to CPUs. - Memory: TPUs often come with large amounts of high-bandwidth memory, allowing for the handling of large models and batch sizes during training. This can lead to better model quality. - Scalability: TPU Pods (large clusters of TPUs) provide a scalable solution for handling the growing complexity of large foundation models. You can distribute training across multiple TPU devices for faster and more efficient processing. - Cost-effectiveness: In many scenarios, TPUs can provide a more cost-effective solution for training large models compared to CPU-based infrastructure, especially when considering the time and resources saved due to faster training. - These advantages are aligned with [Google's commitments to operate sustainably][sustainability]. ### Software Training was done using [JAX][jax] and [ML Pathways][ml-pathways]. JAX allows researchers to take advantage of the latest generation of hardware, including TPUs, for faster and more efficient training of large models. ML Pathways is Google's latest effort to build artificially intelligent systems capable of generalizing across multiple tasks. This is specially suitable for foundation models, including large language models like these ones. Together, JAX and ML Pathways are used as described in the [paper about the Gemini family of models][gemini-2-paper]; "the 'single controller' programming model of Jax and Pathways allows a single Python process to orchestrate the entire training run, dramatically simplifying the development workflow." ## Evaluation Model evaluation metrics and results. ### Benchmark Results These models were evaluated against a large collection of different datasets and metrics to cover different aspects of text generation: #### Reasoning and factuality \| Benchmark \| Metric \| Gemma 3 PT 1B \| Gemma 3 PT 4B \| Gemma 3 PT 12B \| Gemma 3 PT 27B \| \| ------------------------------ \|----------------\|:--------------:\|:-------------:\|:--------------:\|:--------------:\| \| [HellaSwag][hellaswag] \| 10-shot \| 62.3 \| 77.2 \| 84.2 \| 85.6 \| \| [BoolQ][boolq] \| 0-shot \| 63.2 \| 72.3 \| 78.8 \| 82.4 \| \| [PIQA][piqa] \| 0-shot \| 73.8 \| 79.6 \| 81.8 \| 83.3 \| \| [SocialIQA][socialiqa] \| 0-shot \| 48.9 \| 51.9 \| 53.4 \| 54.9 \| \| [TriviaQA][triviaqa] \| 5-shot \| 39.8 \| 65.8 \| 78.2 \| 85.5 \| \| [Natural Questions][naturalq] \| 5-shot \| 9.48 \| 20.0 \| 31.4 \| 36.1 \| \| [ARC-c][arc] \| 25-shot \| 38.4 \| 56.2 \| 68.9 \| 70.6 \| \| [ARC-e][arc] \| 0-shot \| 73.0 \| 82.4 \| 88.3 \| 89.0 \| \| [WinoGrande][winogrande] \| 5-shot \| 58.2 \| 64.7 \| 74.3 \| 78.8 \| \| [BIG-Bench Hard][bbh] \| few-shot \| 28.4 \| 50.9 \| 72.6 \| 77.7 \| \| [DROP][drop] \| 1-shot \| 42.4 \| 60.1 \| 72.2 \| 77.2 \| [hellaswag]: https://arxiv.org/abs/1905.07830 [boolq]: https://arxiv.org/abs/1905.10044 [piqa]: https://arxiv.org/abs/1911.11641 [socialiqa]: https://arxiv.org/abs/1904.09728 [triviaqa]: https://arxiv.org/abs/1705.03551 [naturalq]: https://github.com/google-research-datasets/natural-questions [arc]: https://arxiv.org/abs/1911.01547 [winogrande]: https://arxiv.org/abs/1907.10641 [bbh]: https://paperswithcode.com/dataset/bbh [drop]: https://arxiv.org/abs/1903.00161 #### STEM and code \| Benchmark \| Metric \| Gemma 3 PT 4B \| Gemma 3 PT 12B \| Gemma 3 PT 27B \| \| ------------------------------ \|----------------\|:-------------:\|:--------------:\|:--------------:\| \| [MMLU][mmlu] \| 5-shot \| 59.6 \| 74.5 \| 78.6 \| \| [MMLU][mmlu] (Pro COT) \| 5-shot \| 29.2 \| 45.3 \| 52.2 \| \| [AGIEval][agieval] \| 3-5-shot \| 42.1 \| 57.4 \| 66.2 \| \| [MATH][math] \| 4-shot \| 24.2 \| 43.3 \| 50.0 \| \| [GSM8K][gsm8k] \| 8-shot \| 38.4 \| 71.0 \| 82.6 \| \| [GPQA][gpqa] \| 5-shot \| 15.0 \| 25.4 \| 24.3 \| \| [MBPP][mbpp] \| 3-shot \| 46.0 \| 60.4 \| 65.6 \| \| [HumanEval][humaneval] \| 0-shot \| 36.0 \| 45.7 \| 48.8 \| [mmlu]: https://arxiv.org/abs/2009.03300 [agieval]: https://arxiv.org/abs/2304.06364 [math]: https://arxiv.org/abs/2103.03874 [gsm8k]: https://arxiv.org/abs/2110.14168 [gpqa]: https://arxiv.org/abs/2311.12022 [mbpp]: https://arxiv.org/abs/2108.07732 [humaneval]: https://arxiv.org/abs/2107.03374 #### Multilingual \| Benchmark \| Gemma 3 PT 1B \| Gemma 3 PT 4B \| Gemma 3 PT 12B \| Gemma 3 PT 27B \| \| ------------------------------------ \|:-------------:\|:-------------:\|:--------------:\|:--------------:\| \| [MGSM][mgsm] \| 2.04 \| 34.7 \| 64.3 \| 74.3 \| \| [Global-MMLU-Lite][global-mmlu-lite] \| 24.9 \| 57.0 \| 69.4 \| 75.7 \| \| [WMT24++][wmt24pp] (ChrF) \| 36.7 \| 48.4 \| 53.9 \| 55.7 \| \| [FloRes][flores] \| 29.5 \| 39.2 \| 46.0 \| 48.8 \| \| [XQuAD][xquad] (all) \| 43.9 \| 68.0 \| 74.5 \| 76.8 \| \| [ECLeKTic][eclektic] \| 4.69 \| 11.0 \| 17.2 \| 24.4 \| \| [IndicGenBench][indicgenbench] \| 41.4 \| 57.2 \| 61.7 \| 63.4 \| [mgsm]: https://arxiv.org/abs/2210.03057 [flores]: https://arxiv.org/abs/2106.03193 [xquad]: https://arxiv.org/abs/1910.11856v3 [global-mmlu-lite]: https://huggingface.co/datasets/CohereForAI/Global-MMLU-Lite [wmt24pp]: https://arxiv.org/abs/2502.12404v1 [eclektic]: https://arxiv.org/abs/2502.21228 [indicgenbench]: https://arxiv.org/abs/2404.16816 #### Multimodal \| Benchmark \| Gemma 3 PT 4B \| Gemma 3 PT 12B \| Gemma 3 PT 27B \| \| ------------------------------ \|:-------------:\|:--------------:\|:--------------:\| \| [COCOcap][coco-cap] \| 102 \| 111 \| 116 \| \| [DocVQA][docvqa] (val) \| 72.8 \| 82.3 \| 85.6 \| \| [InfoVQA][info-vqa] (val) \| 44.1 \| 54.8 \| 59.4 \| \| [MMMU][mmmu] (pt) \| 39.2 \| 50.3 \| 56.1 \| \| [TextVQA][textvqa] (val) \| 58.9 \| 66.5 \| 68.6 \| \| [RealWorldQA][realworldqa] \| 45.5 \| 52.2 \| 53.9 \| \| [ReMI][remi] \| 27.3 \| 38.5 \| 44.8 \| \| [AI2D][ai2d] \| 63.2 \| 75.2 \| 79.0 \| \| [ChartQA][chartqa] \| 63.6 \| 74.7 \| 76.3 \| \| [VQAv2][vqav2] \| 63.9 \| 71.2 \| 72.9 \| \| [BLINK][blinkvqa] \| 38.0 \| 35.9 \| 39.6 \| \| [OKVQA][okvqa] \| 51.0 \| 58.7 \| 60.2 \| \| [TallyQA][tallyqa] \| 42.5 \| 51.8 \| 54.3 \| \| [SpatialSense VQA][ss-vqa] \| 50.9 \| 60.0 \| 59.4 \| \| [CountBenchQA][countbenchqa] \| 26.1 \| 17.8 \| 68.0 \| [coco-cap]: https://cocodataset.org/#home [docvqa]: https://www.docvqa.org/ [info-vqa]: https://arxiv.org/abs/2104.12756 [mmmu]: https://arxiv.org/abs/2311.16502 [textvqa]: https://textvqa.org/ [realworldqa]: https://paperswithcode.com/dataset/realworldqa [remi]: https://arxiv.org/html/2406.09175v1 [ai2d]: https://allenai.org/data/diagrams [chartqa]: https://arxiv.org/abs/2203.10244 [vqav2]: https://visualqa.org/index.html [blinkvqa]: https://arxiv.org/abs/2404.12390 [okvqa]: https://okvqa.allenai.org/ [tallyqa]: https://arxiv.org/abs/1810.12440 [ss-vqa]: https://arxiv.org/abs/1908.02660 [countbenchqa]: https://github.com/google-research/big_vision/blob/main/big_vision/datasets/countbenchqa/ ## Ethics and Safety Ethics and safety evaluation approach and results. ### Evaluation Approach Our evaluation methods include structured evaluations and internal red-teaming testing of relevant content policies. Red-teaming was conducted by a number of different teams, each with different goals and human evaluation metrics. These models were evaluated against a number of different categories relevant to ethics and safety, including: - Child Safety: Evaluation of text-to-text and image to text prompts covering child safety policies, including child sexual abuse and exploitation. - Content Safety: Evaluation of text-to-text and image to text prompts covering safety policies including, harassment, violence and gore, and hate speech. - Representational Harms: Evaluation of text-to-text and image to text prompts covering safety policies including bias, stereotyping, and harmful associations or inaccuracies. In addition to development level evaluations, we conduct "assurance evaluations" which are our 'arms-length' internal evaluations for responsibility governance decision making. They are conducted separately from the model development team, to inform decision making about release. High level findings are fed back to the model team, but prompt sets are held-out to prevent overfitting and preserve the results' ability to inform decision making. Assurance evaluation results are reported to our Responsibility & Safety Council as part of release review. ### Evaluation Results For all areas of safety testing, we saw major improvements in the categories of child safety, content safety, and representational harms relative to previous Gemma models. All testing was conducted without safety filters to evaluate the model capabilities and behaviors. For both text-to-text and image-to-text, and across all model sizes, the model produced minimal policy violations, and showed significant improvements over previous Gemma models' performance with respect to ungrounded inferences. A limitation of our evaluations was they included only English language prompts. ## Usage and Limitations These models have certain limitations that users should be aware of. ### Intended Usage Open vision-language models (VLMs) models have a wide range of applications across various industries and domains. The following list of potential uses is not comprehensive. The purpose of this list is to provide contextual information about the possible use-cases that the model creators considered as part of model training and development. - Content Creation and Communication - Text Generation: These models can be used to generate creative text formats such as poems, scripts, code, marketing copy, and email drafts. - Chatbots and Conversational AI: Power conversational interfaces for customer service, virtual assistants, or interactive applications. - Text Summarization: Generate concise summaries of a text corpus, research papers, or reports. - Image Data Extraction: These models can be used to extract, interpret, and summarize visual data for text communications. - Research and Education - Natural Language Processing (NLP) and VLM Research: These models can serve as a foundation for researchers to experiment with VLM and NLP techniques, develop algorithms, and contribute to the advancement of the field. - Language Learning Tools: Support interactive language learning experiences, aiding in grammar correction or providing writing practice. - Knowledge Exploration: Assist researchers in exploring large bodies of text by generating summaries or answering questions about specific topics. ### Limitations - Training Data - The quality and diversity of the training data significantly influence the model's capabilities. Biases or gaps in the training data can lead to limitations in the model's responses. - The scope of the training dataset determines the subject areas the model can handle effectively. - Context and Task Complexity - Models are better at tasks that can be framed with clear prompts and instructions. Open-ended or highly complex tasks might be challenging. - A model's performance can be influenced by the amount of context provided (longer context generally leads to better outputs, up to a certain point). - Language Ambiguity and Nuance - Natural language is inherently complex. Models might struggle to grasp subtle nuances, sarcasm, or figurative language. - Factual Accuracy - Models generate responses based on information they learned from their training datasets, but they are not knowledge bases. They may generate incorrect or outdated factual statements. - Common Sense - Models rely on statistical patterns in language. They might lack the ability to apply common sense reasoning in certain situations. ### Ethical Considerations and Risks The development of vision-language models (VLMs) raises several ethical concerns. In creating an open model, we have carefully considered the following: - Bias and Fairness - VLMs trained on large-scale, real-world text and image data can reflect socio-cultural biases embedded in the training material. These models underwent careful scrutiny, input data pre-processing described and posterior evaluations reported in this card. - Misinformation and Misuse - VLMs can be misused to generate text that is false, misleading, or harmful. - Guidelines are provided for responsible use with the model, see the [Responsible Generative AI Toolkit][rai-toolkit]. - Transparency and Accountability: - This model card summarizes details on the models' architecture, capabilities, limitations, and evaluation processes. - A responsibly developed open model offers the opportunity to share innovation by making VLM technology accessible to developers and researchers across the AI ecosystem. Risks identified and mitigations: - Perpetuation of biases: It's encouraged to perform continuous monitoring (using evaluation metrics, human review) and the exploration of de-biasing techniques during model training, fine-tuning, and other use cases. - Generation of harmful content: Mechanisms and guidelines for content safety are essential. Developers are encouraged to exercise caution and implement appropriate content safety safeguards based on their specific product policies and application use cases. - Misuse for malicious purposes: Technical limitations and developer and end-user education can help mitigate against malicious applications of VLMs. Educational resources and reporting mechanisms for users to flag misuse are provided. Prohibited uses of Gemma models are outlined in the [Gemma Prohibited Use Policy][prohibited-use]. - Privacy violations: Models were trained on data filtered for removal of certain personal information and other sensitive data. Developers are encouraged to adhere to privacy regulations with privacy-preserving techniques. ### Benefits At the time of release, this family of models provides high-performance open vision-language model implementations designed from the ground up for responsible AI development compared to similarly sized models. Using the benchmark evaluation metrics described in this document, these models have shown to provide superior performance to other, comparably-sized open model alternatives. [g3-tech-report]: https://goo.gle/Gemma3Report [rai-toolkit]: https://ai.google.dev/responsible [kaggle-gemma]: https://www.kaggle.com/models/google/gemma-3 [vertex-mg-gemma3]: https://console.cloud.google.com/vertex-ai/publishers/google/model-garden/gemma3 [terms]: https://ai.google.dev/gemma/terms [safety-policies]: https://ai.google/static/documents/ai-responsibility-update-published-february-2025.pdf [prohibited-use]: https://ai.google.dev/gemma/prohibited_use_policy [tpu]: https://cloud.google.com/tpu/docs/intro-to-tpu [sustainability]: https://sustainability.google/operating-sustainably/ [jax]: https://github.com/jax-ml/jax [ml-pathways]: https://blog.google/technology/ai/introducing-pathways-next-generation-ai-architecture/ [sustainability]: https://sustainability.google/operating-sustainably/
Mungert/MetaStone-L1-7B-GGUF	Mungert	2025-06-15T19:42:32Z	460	2	null	[ "gguf", "arxiv:2412.08864", "endpoints_compatible", "region:us", "imatrix", "conversational" ]	null	2025-03-24T15:38:45Z	## # <span style="color: #7FFF7F;">MetaStone-L1-7B GGUF Models</span> ## Choosing the Right Model Format Selecting the correct model format depends on your hardware capabilities and memory constraints. ### BF16 (Brain Float 16) – Use if BF16 acceleration is available - A 16-bit floating-point format designed for faster computation while retaining good precision. - Provides similar dynamic range as FP32 but with lower memory usage. - Recommended if your hardware supports BF16 acceleration (check your device’s specs). - Ideal for high-performance inference with reduced memory footprint compared to FP32. 📌 Use BF16 if: ✔ Your hardware has native BF16 support (e.g., newer GPUs, TPUs). ✔ You want higher precision while saving memory. ✔ You plan to requantize the model into another format. 📌 Avoid BF16 if: ❌ Your hardware does not support BF16 (it may fall back to FP32 and run slower). ❌ You need compatibility with older devices that lack BF16 optimization. --- ### F16 (Float 16) – More widely supported than BF16 - A 16-bit floating-point high precision but with less of range of values than BF16. - Works on most devices with FP16 acceleration support (including many GPUs and some CPUs). - Slightly lower numerical precision than BF16 but generally sufficient for inference. 📌 Use F16 if: ✔ Your hardware supports FP16 but not BF16. ✔ You need a balance between speed, memory usage, and accuracy. ✔ You are running on a GPU or another device optimized for FP16 computations. 📌 Avoid F16 if: ❌ Your device lacks native FP16 support (it may run slower than expected). ❌ You have memory limitations. --- ### Quantized Models (Q4_K, Q6_K, Q8, etc.) – For CPU & Low-VRAM Inference Quantization reduces model size and memory usage while maintaining as much accuracy as possible. - Lower-bit models (Q4_K) → Best for minimal memory usage, may have lower precision. - Higher-bit models (Q6_K, Q8_0) → Better accuracy, requires more memory. 📌 Use Quantized Models if: ✔ You are running inference on a CPU and need an optimized model. ✔ Your device has low VRAM and cannot load full-precision models. ✔ You want to reduce memory footprint while keeping reasonable accuracy. 📌 Avoid Quantized Models if: ❌ You need maximum accuracy (full-precision models are better for this). ❌ Your hardware has enough VRAM for higher-precision formats (BF16/F16). --- ### Very Low-Bit Quantization (IQ3_XS, IQ3_S, IQ3_M, Q4_K, Q4_0) These models are optimized for extreme memory efficiency, making them ideal for low-power devices or large-scale deployments where memory is a critical constraint. - IQ3_XS: Ultra-low-bit quantization (3-bit) with extreme memory efficiency. - Use case: Best for ultra-low-memory devices where even Q4_K is too large. - Trade-off: Lower accuracy compared to higher-bit quantizations. - IQ3_S: Small block size for maximum memory efficiency. - Use case: Best for low-memory devices where IQ3_XS is too aggressive. - IQ3_M: Medium block size for better accuracy than IQ3_S. - Use case: Suitable for low-memory devices where IQ3_S is too limiting. - Q4_K: 4-bit quantization with block-wise optimization for better accuracy. - Use case: Best for low-memory devices where Q6_K is too large. - Q4_0: Pure 4-bit quantization, optimized for ARM devices. - Use case: Best for ARM-based devices or low-memory environments. --- ### Summary Table: Model Format Selection \| Model Format \| Precision \| Memory Usage \| Device Requirements \| Best Use Case \| \|--------------\|------------\|---------------\|----------------------\|---------------\| \| BF16 \| Highest \| High \| BF16-supported GPU/CPUs \| High-speed inference with reduced memory \| \| F16 \| High \| High \| FP16-supported devices \| GPU inference when BF16 isn’t available \| \| Q4_K \| Medium Low \| Low \| CPU or Low-VRAM devices \| Best for memory-constrained environments \| \| Q6_K \| Medium \| Moderate \| CPU with more memory \| Better accuracy while still being quantized \| \| Q8_0 \| High \| Moderate \| CPU or GPU with enough VRAM \| Best accuracy among quantized models \| \| IQ3_XS \| Very Low \| Very Low \| Ultra-low-memory devices \| Extreme memory efficiency and low accuracy \| \| Q4_0 \| Low \| Low \| ARM or low-memory devices \| llama.cpp can optimize for ARM devices \| --- ## Included Files & Details ### `MetaStone-L1-7B-bf16.gguf` - Model weights preserved in BF16. - Use this if you want to requantize the model into a different format. - Best if your device supports BF16 acceleration. ### `MetaStone-L1-7B-f16.gguf` - Model weights stored in F16. - Use if your device supports FP16, especially if BF16 is not available. ### `MetaStone-L1-7B-bf16-q8_0.gguf` - Output & embeddings remain in BF16. - All other layers quantized to Q8_0. - Use if your device supports BF16 and you want a quantized version. ### `MetaStone-L1-7B-f16-q8_0.gguf` - Output & embeddings remain in F16. - All other layers quantized to Q8_0. ### `MetaStone-L1-7B-q4_k.gguf` - Output & embeddings quantized to Q8_0. - All other layers quantized to Q4_K. - Good for CPU inference with limited memory. ### `MetaStone-L1-7B-q4_k_s.gguf` - Smallest Q4_K variant, using less memory at the cost of accuracy. - Best for very low-memory setups. ### `MetaStone-L1-7B-q6_k.gguf` - Output & embeddings quantized to Q8_0. - All other layers quantized to Q6_K . ### `MetaStone-L1-7B-q8_0.gguf` - Fully Q8 quantized model for better accuracy. - Requires more memory but offers higher precision. ### `MetaStone-L1-7B-iq3_xs.gguf` - IQ3_XS quantization, optimized for extreme memory efficiency. - Best for ultra-low-memory devices. ### `MetaStone-L1-7B-iq3_m.gguf` - IQ3_M quantization, offering a medium block size for better accuracy. - Suitable for low-memory devices. ### `MetaStone-L1-7B-q4_0.gguf` - Pure Q4_0 quantization, optimized for ARM devices. - Best for low-memory environments. - Prefer IQ4_NL for better accuracy. # <span id="testllm" style="color: #7F7FFF;">🚀 If you find these models useful</span> Please click like ❤ . Also I’d really appreciate it if you could test my Network Monitor Assistant at 👉 [Network Monitor Assitant](https://readyforquantum.com). 💬 Click the chat icon (bottom right of the main and dashboard pages) . Choose a LLM; toggle between the LLM Types TurboLLM -> FreeLLM -> TestLLM. ### What I'm Testing I'm experimenting with function calling against my network monitoring service. Using small open source models. I am into the question "How small can it go and still function". 🟡 TestLLM – Runs the current testing model using llama.cpp on 6 threads of a Cpu VM (Should take about 15s to load. Inference speed is quite slow and it only processes one user prompt at a time—still working on scaling!). If you're curious, I'd be happy to share how it works! . ### The other Available AI Assistants 🟢 TurboLLM – Uses gpt-4o-mini Fast! . Note: tokens are limited since OpenAI models are pricey, but you can [Login](https://readyforquantum.com) or [Download](https://readyforquantum.com/download/?utm_source=huggingface&utm_medium=referral&utm_campaign=huggingface_repo_readme) the Quantum Network Monitor agent to get more tokens, Alternatively use the FreeLLM . 🔵 FreeLLM – Runs open-source Hugging Face models Medium speed (unlimited, subject to Hugging Face API availability). Introduction MetaStone-L1 is the lite reasoning model of the MetaStone series, which aims to enhance the performance in hard downstream tasks. On core reasoning benchmarks including mathematics and code, MetaStone-L1-7B achieved SOTA results in the parallel-level models, and it also achieved the comparable results as the API models such as Claude-3.5-Sonnet-1022 and GPT4o-0513. <img src="./introduction.png" alt="Logo" width="800"> This repo contains the MetaStone-L1-7B model, which is trained based on DeepSeek-R1-Distill-Qwen-7B by GRPO. For full details of this model please refer to our release blog. ## Requirements We advise you to use the latest version of transformers(```transformers==4.48.3```). For the best experience, please review the [Usage Guidelines](#usage-guidelines). ## Quickstart Here give the example of how to use our model. ``` from transformers import AutoModelForCausalLM, AutoTokenizer model_name = "MetaStoneTec/MetaStone-L1-7B" tokenizer = AutoTokenizer.from_pretrained(model_name) model = AutoModelForCausalLM.from_pretrained(model_name) messages = [ {"role": "user", "content": "Complete the square for the following quadratic: $-x^2+7 x-11$\n\nPlease reason step by step, and put your final answer within \\boxed{}."} ] text = tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True ) model_inputs = tokenizer([text], return_tensors="pt").to(model.device) generated_ids = model.generate( **model_inputs, max_new_tokens=32768 ) generated_ids = [ output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids) ] response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0] ``` ## Usage Guidelines To achieve optimal performance, we recommend the following settings: 1. Enhace the thoughful output： a. Make sure the model starts with ```<think>\n``` to prevent generating empty think content. If you use ```apply_chat_template``` and set ```add_generation_prompt=True```, this is automatically implemented, but this may result in replies not having a <think> tag at the beginning, which is normal. b. Ensure the final input of the model is in the format of ```<｜User｜> [your prompt] <｜Assistant｜><think>```. 2. Use a temperature of 0.6, a top sampling probability of 0.95, a maximum generation length of 32k. 3. Standardize output format: We recommend using hints to standardize model outputs when benchmarking. a. Math questions: Add a statement "```Please reason step by step, and put your final answer within \\boxed{}.```" to the prompt. b. Code problems: Add "### Format: Read the inputs from stdin solve the problem and write the answer to stdout. Enclose your code within delimiters as follows.\n \```python\n# YOUR CODE HERE\n\```\n### Answer: (use the provided format with backticks)" to the prompt. 4. In particular, we use ```latex2sympy2``` and ```sympy``` to assist in judging complex Latex formats for the Math500 evaluation script. For all datasets, we generate 64 responses per query to estimate pass@1. ## Citation If you find our work helpful, feel free to give us a cite. ``` @misc{MetaStoneL17B, title = {MetastoneL17B}, url = {https://huggingface.co/MetaStoneTec/MetaStone-L1-7B}, author = {MetaStone Team}, month = {March}, year = {2025} } ``` ``` @article{wang2024graph, title={A Graph-Based Synthetic Data Pipeline for Scaling High-Quality Reasoning Instructions}, author={Wang, Jiankang and Xu, Jianjun and Wang, Xiaorui and Wang, Yuxin and Xing, Mengting and Fang, Shancheng and Chen, Zhineng and Xie, Hongtao and Zhang, Yongdong}, journal={arXiv preprint arXiv:2412.08864}, year={2024} } ```
Mungert/functionary-small-v3.1-GGUF	Mungert	2025-06-15T19:42:24Z	233	3	null	[ "gguf", "license:mit", "endpoints_compatible", "region:us", "imatrix", "conversational" ]	null	2025-03-24T06:33:17Z	--- license: mit --- # <span style="color: #7FFF7F;">functionary-small-v3.1 GGUF Models</span> ## Choosing the Right Model Format Selecting the correct model format depends on your hardware capabilities and memory constraints. ### BF16 (Brain Float 16) – Use if BF16 acceleration is available - A 16-bit floating-point format designed for faster computation while retaining good precision. - Provides similar dynamic range as FP32 but with lower memory usage. - Recommended if your hardware supports BF16 acceleration (check your device’s specs). - Ideal for high-performance inference with reduced memory footprint compared to FP32. 📌 Use BF16 if: ✔ Your hardware has native BF16 support (e.g., newer GPUs, TPUs). ✔ You want higher precision while saving memory. ✔ You plan to requantize the model into another format. 📌 Avoid BF16 if: ❌ Your hardware does not support BF16 (it may fall back to FP32 and run slower). ❌ You need compatibility with older devices that lack BF16 optimization. --- ### F16 (Float 16) – More widely supported than BF16 - A 16-bit floating-point high precision but with less of range of values than BF16. - Works on most devices with FP16 acceleration support (including many GPUs and some CPUs). - Slightly lower numerical precision than BF16 but generally sufficient for inference. 📌 Use F16 if: ✔ Your hardware supports FP16 but not BF16. ✔ You need a balance between speed, memory usage, and accuracy. ✔ You are running on a GPU or another device optimized for FP16 computations. 📌 Avoid F16 if: ❌ Your device lacks native FP16 support (it may run slower than expected). ❌ You have memory limitations. --- ### Quantized Models (Q4_K, Q6_K, Q8, etc.) – For CPU & Low-VRAM Inference Quantization reduces model size and memory usage while maintaining as much accuracy as possible. - Lower-bit models (Q4_K) → Best for minimal memory usage, may have lower precision. - Higher-bit models (Q6_K, Q8_0) → Better accuracy, requires more memory. 📌 Use Quantized Models if: ✔ You are running inference on a CPU and need an optimized model. ✔ Your device has low VRAM and cannot load full-precision models. ✔ You want to reduce memory footprint while keeping reasonable accuracy. 📌 Avoid Quantized Models if: ❌ You need maximum accuracy (full-precision models are better for this). ❌ Your hardware has enough VRAM for higher-precision formats (BF16/F16). --- ### Very Low-Bit Quantization (IQ3_XS, IQ3_S, IQ3_M, Q4_K, Q4_0) These models are optimized for extreme memory efficiency, making them ideal for low-power devices or large-scale deployments where memory is a critical constraint. - IQ3_XS: Ultra-low-bit quantization (3-bit) with extreme memory efficiency. - Use case: Best for ultra-low-memory devices where even Q4_K is too large. - Trade-off: Lower accuracy compared to higher-bit quantizations. - IQ3_S: Small block size for maximum memory efficiency. - Use case: Best for low-memory devices where IQ3_XS is too aggressive. - IQ3_M: Medium block size for better accuracy than IQ3_S. - Use case: Suitable for low-memory devices where IQ3_S is too limiting. - Q4_K: 4-bit quantization with block-wise optimization for better accuracy. - Use case: Best for low-memory devices where Q6_K is too large. - Q4_0: Pure 4-bit quantization, optimized for ARM devices. - Use case: Best for ARM-based devices or low-memory environments. --- ### Summary Table: Model Format Selection \| Model Format \| Precision \| Memory Usage \| Device Requirements \| Best Use Case \| \|--------------\|------------\|---------------\|----------------------\|---------------\| \| BF16 \| Highest \| High \| BF16-supported GPU/CPUs \| High-speed inference with reduced memory \| \| F16 \| High \| High \| FP16-supported devices \| GPU inference when BF16 isn’t available \| \| Q4_K \| Medium Low \| Low \| CPU or Low-VRAM devices \| Best for memory-constrained environments \| \| Q6_K \| Medium \| Moderate \| CPU with more memory \| Better accuracy while still being quantized \| \| Q8_0 \| High \| Moderate \| CPU or GPU with enough VRAM \| Best accuracy among quantized models \| \| IQ3_XS \| Very Low \| Very Low \| Ultra-low-memory devices \| Extreme memory efficiency and low accuracy \| \| Q4_0 \| Low \| Low \| ARM or low-memory devices \| llama.cpp can optimize for ARM devices \| --- ## Included Files & Details ### `functionary-small-v3.1-bf16.gguf` - Model weights preserved in BF16. - Use this if you want to requantize the model into a different format. - Best if your device supports BF16 acceleration. ### `functionary-small-v3.1-f16.gguf` - Model weights stored in F16. - Use if your device supports FP16, especially if BF16 is not available. ### `functionary-small-v3.1-bf16-q8_0.gguf` - Output & embeddings remain in BF16. - All other layers quantized to Q8_0. - Use if your device supports BF16 and you want a quantized version. ### `functionary-small-v3.1-f16-q8_0.gguf` - Output & embeddings remain in F16. - All other layers quantized to Q8_0. ### `functionary-small-v3.1-q4_k.gguf` - Output & embeddings quantized to Q8_0. - All other layers quantized to Q4_K. - Good for CPU inference with limited memory. ### `functionary-small-v3.1-q4_k_s.gguf` - Smallest Q4_K variant, using less memory at the cost of accuracy. - Best for very low-memory setups. ### `functionary-small-v3.1-q6_k.gguf` - Output & embeddings quantized to Q8_0. - All other layers quantized to Q6_K . ### `functionary-small-v3.1-q8_0.gguf` - Fully Q8 quantized model for better accuracy. - Requires more memory but offers higher precision. ### `functionary-small-v3.1-iq3_xs.gguf` - IQ3_XS quantization, optimized for extreme memory efficiency. - Best for ultra-low-memory devices. ### `functionary-small-v3.1-iq3_m.gguf` - IQ3_M quantization, offering a medium block size for better accuracy. - Suitable for low-memory devices. ### `functionary-small-v3.1-q4_0.gguf` - Pure Q4_0 quantization, optimized for ARM devices. - Best for low-memory environments. - Prefer IQ4_NL for better accuracy. # <span id="testllm" style="color: #7F7FFF;">🚀 If you find these models useful</span> Please click like ❤ . Also I’d really appreciate it if you could test my Network Monitor Assistant at 👉 [Network Monitor Assitant](https://readyforquantum.com). 💬 Click the chat icon (bottom right of the main and dashboard pages) . Choose a LLM; toggle between the LLM Types TurboLLM -> FreeLLM -> TestLLM. ### What I'm Testing I'm experimenting with function calling against my network monitoring service. Using small open source models. I am into the question "How small can it go and still function". 🟡 TestLLM – Runs the current testing model using llama.cpp on 6 threads of a Cpu VM (Should take about 15s to load. Inference speed is quite slow and it only processes one user prompt at a time—still working on scaling!). If you're curious, I'd be happy to share how it works! . ### The other Available AI Assistants 🟢 TurboLLM – Uses gpt-4o-mini Fast! . Note: tokens are limited since OpenAI models are pricey, but you can [Login](https://readyforquantum.com) or [Download](https://readyforquantum.com/download/?utm_source=huggingface&utm_medium=referral&utm_campaign=huggingface_repo_readme) the Quantum Network Monitor agent to get more tokens, Alternatively use the TestLLM . 🔵 HugLLM – Runs open-source Hugging Face models Fast, Runs small models (≈8B) hence lower quality, Get 2x more tokens (subject to Hugging Face API availability) ### 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! 😊 # Model Card for functionary-small-v3.1 This model was based on [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct), using Meta's original prompt template as described in: [User-defined Custom tool calling](https://llama.meta.com/docs/model-cards-and-prompt-formats/llama3_1/#user-defined-custom-tool-calling) [https://github.com/MeetKai/functionary](https://github.com/MeetKai/functionary) <img src="https://huggingface.co/meetkai/functionary-medium-v2.2/resolve/main/functionary_logo.jpg" alt="Functionary Logo" width="300"/> Functionary is a language model that can interpret and execute functions/plugins. The model determines when to execute functions, whether in parallel or serially, and can understand their outputs. It only triggers functions as needed. Function definitions are given as JSON Schema Objects, similar to OpenAI GPT function calls. ## Key Features - Intelligent parallel tool use - Able to analyze functions/tools outputs and provide relevant responses grounded in the outputs - Able to decide when to not use tools/call functions and provide normal chat response - Truly one of the best open-source alternative to GPT-4 - Support code interpreter ## How to Get Started We provide custom code for parsing raw model responses into a JSON object containing role, content and tool_calls fields. This enables the users to read the function-calling output of the model easily. ```python from transformers import AutoModelForCausalLM, AutoTokenizer tokenizer = AutoTokenizer.from_pretrained("meetkai/functionary-small-v3.1") model = AutoModelForCausalLM.from_pretrained("meetkai/functionary-small-v3.1", device_map="auto", trust_remote_code=True) tools = [ { "type": "function", "function": { "name": "get_current_weather", "description": "Get the current weather", "parameters": { "type": "object", "properties": { "location": { "type": "string", "description": "The city and state, e.g. San Francisco, CA" } }, "required": ["location"] } } } ] messages = [{"role": "user", "content": "What is the weather in Istanbul and Singapore respectively?"}] final_prompt = tokenizer.apply_chat_template(messages, tools, add_generation_prompt=True, tokenize=False) inputs = tokenizer(final_prompt, return_tensors="pt").to("cuda") pred = model.generate_tool_use(**inputs, max_new_tokens=128, tokenizer=tokenizer) print(tokenizer.decode(pred.cpu()[0])) ``` ## Prompt Template We convert function definitions to a similar text to TypeScript definitions. Then we inject these definitions as system prompts. After that, we inject the default system prompt. Then we start the conversation messages. This formatting is also available via our vLLM server which we process the functions into Typescript definitions encapsulated in a system message using a pre-defined Transformers Jinja chat template. This means that the lists of messages can be formatted for you with the apply_chat_template() method within our server: ```python from openai import OpenAI client = OpenAI(base_url="http://localhost:8000/v1", api_key="functionary") client.chat.completions.create( model="path/to/functionary/model/", messages=[{"role": "user", "content": "What is the weather for Istanbul?"} ], tools=[{ "type": "function", "function": { "name": "get_current_weather", "description": "Get the current weather", "parameters": { "type": "object", "properties": { "location": { "type": "string", "description": "The city and state, e.g. San Francisco, CA" } }, "required": ["location"] } } }], tool_choice="auto" ) ``` will yield: ``` <\|start_header_id\|>system<\|end_header_id\|> Environment: ipython Cutting Knowledge Date: December 2023 You have access to the following functions: Use the function 'get_current_weather' to 'Get the current weather' {"name": "get_current_weather", "description": "Get the current weather", "parameters": {"type": "object", "properties": {"location": {"type": "string", "description": "The city and state, e.g. San Francisco, CA"}},"required": ["location"]}} Think very carefully before calling functions. If a you choose to call a function ONLY reply in the following format: <{start_tag}={function_name}>{parameters}{end_tag} where start_tag => `<function` parameters => a JSON dict with the function argument name as key and function argument value as value. end_tag => `</function>` Here is an example, <function=example_function_name>{"example_name": "example_value"}</function> Reminder: - If looking for real time information use relevant functions before falling back to brave_search - Function calls MUST follow the specified format, start with <function= and end with </function> - Required parameters MUST be specified - Only call one function at a time - Put the entire function call reply on one line <\|eot_id\|><\|start_header_id\|>user<\|end_header_id\|> What is the weather for Istanbul? ``` A more detailed example is provided [here](https://github.com/MeetKai/functionary/blob/main/tests/prompt_test_v3-llama3.1.txt). ## Run the model We encourage users to run our models using our OpenAI-compatible vLLM server [here](https://github.com/MeetKai/functionary). # The MeetKai Team ![MeetKai Logo](https://huggingface.co/meetkai/functionary-medium-v2.2/resolve/main/meetkai_logo.png "MeetKai Logo")
Mungert/Llama-3.1-Nemotron-Nano-8B-v1-GGUF	Mungert	2025-06-15T19:41:41Z	2,163	7	transformers	[ "transformers", "gguf", "nvidia", "llama-3", "pytorch", "text-generation", "en", "arxiv:2505.00949", "arxiv:2502.00203", "license:other", "endpoints_compatible", "region:us", "imatrix", "conversational" ]	text-generation	2025-03-21T19:44:49Z	--- library_name: transformers license: other license_name: nvidia-open-model-license license_link: >- https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/ pipeline_tag: text-generation language: - en tags: - nvidia - llama-3 - pytorch --- # <span style="color: #7FFF7F;">Llama-3.1-Nemotron-Nano-8B-v1 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 [`19e899c`](https://github.com/ggerganov/llama.cpp/commit/19e899ce21a7c9ffcf8bb2b22269a75f6e078f8f). ## <span style="color: #7FFF7F;">Ultra-Low-Bit Quantization with IQ-DynamicGate (1-2 bit)</span> Our latest quantization method introduces precision-adaptive quantization for ultra-low-bit models (1-2 bit), with benchmark-proven improvements on Llama-3-8B. This approach uses layer-specific strategies to preserve accuracy while maintaining extreme memory efficiency. ### Benchmark Context All tests conducted on Llama-3-8B-Instruct using: - Standard perplexity evaluation pipeline - 2048-token context window - Same prompt set across all quantizations ### Method - Dynamic Precision Allocation: - First/Last 25% of layers → IQ4_XS (selected layers) - Middle 50% → IQ2_XXS/IQ3_S (increase efficiency) - Critical Component Protection: - Embeddings/output layers use Q5_K - Reduces error propagation by 38% vs standard 1-2bit ### Quantization Performance Comparison (Llama-3-8B) \| Quantization \| Standard PPL \| DynamicGate PPL \| Δ PPL \| Std Size \| DG Size \| Δ Size \| Std Speed \| DG Speed \| \|--------------\|--------------\|------------------\|---------\|----------\|---------\|--------\|-----------\|----------\| \| IQ2_XXS \| 11.30 \| 9.84 \| -12.9% \| 2.5G \| 2.6G \| +0.1G \| 234s \| 246s \| \| IQ2_XS \| 11.72 \| 11.63 \| -0.8% \| 2.7G \| 2.8G \| +0.1G \| 242s \| 246s \| \| IQ2_S \| 14.31 \| 9.02 \| -36.9% \| 2.7G \| 2.9G \| +0.2G \| 238s \| 244s \| \| IQ1_M \| 27.46 \| 15.41 \| -43.9% \| 2.2G \| 2.5G \| +0.3G \| 206s \| 212s \| \| IQ1_S \| 53.07 \| 32.00 \| -39.7% \| 2.1G \| 2.4G \| +0.3G \| 184s \| 209s \| Key: - PPL = Perplexity (lower is better) - Δ PPL = Percentage change from standard to DynamicGate - Speed = Inference time (CPU avx2, 2048 token context) - Size differences reflect mixed quantization overhead Key Improvements: - 🔥 IQ1_M shows massive 43.9% perplexity reduction (27.46 → 15.41) - 🚀 IQ2_S cuts perplexity by 36.9% while adding only 0.2GB - ⚡ IQ1_S maintains 39.7% better accuracy despite 1-bit quantization Tradeoffs: - All variants have modest size increases (0.1-0.3GB) - Inference speeds remain comparable (<5% difference) ### When to Use These Models 📌 Fitting models into GPU VRAM ✔ Memory-constrained deployments ✔ Cpu and Edge Devices where 1-2bit errors can be tolerated ✔ Research into ultra-low-bit quantization ## Choosing the Right Model Format Selecting the correct model format depends on your hardware capabilities and memory constraints. ### BF16 (Brain Float 16) – Use if BF16 acceleration is available - A 16-bit floating-point format designed for faster computation while retaining good precision. - Provides similar dynamic range as FP32 but with lower memory usage. - Recommended if your hardware supports BF16 acceleration (check your device's specs). - Ideal for high-performance inference with reduced memory footprint compared to FP32. 📌 Use BF16 if: ✔ Your hardware has native BF16 support (e.g., newer GPUs, TPUs). ✔ You want higher precision while saving memory. ✔ You plan to requantize the model into another format. 📌 Avoid BF16 if: ❌ Your hardware does not support BF16 (it may fall back to FP32 and run slower). ❌ You need compatibility with older devices that lack BF16 optimization. --- ### F16 (Float 16) – More widely supported than BF16 - A 16-bit floating-point high precision but with less of range of values than BF16. - Works on most devices with FP16 acceleration support (including many GPUs and some CPUs). - Slightly lower numerical precision than BF16 but generally sufficient for inference. 📌 Use F16 if: ✔ Your hardware supports FP16 but not BF16. ✔ You need a balance between speed, memory usage, and accuracy. ✔ You are running on a GPU or another device optimized for FP16 computations. 📌 Avoid F16 if: ❌ Your device lacks native FP16 support (it may run slower than expected). ❌ You have memory limitations. --- ### Quantized Models (Q4_K, Q6_K, Q8, etc.) – For CPU & Low-VRAM Inference Quantization reduces model size and memory usage while maintaining as much accuracy as possible. - Lower-bit models (Q4_K) → Best for minimal memory usage, may have lower precision. - Higher-bit models (Q6_K, Q8_0) → Better accuracy, requires more memory. 📌 Use Quantized Models if: ✔ You are running inference on a CPU and need an optimized model. ✔ Your device has low VRAM and cannot load full-precision models. ✔ You want to reduce memory footprint while keeping reasonable accuracy. 📌 Avoid Quantized Models if: ❌ You need maximum accuracy (full-precision models are better for this). ❌ Your hardware has enough VRAM for higher-precision formats (BF16/F16). --- ### Very Low-Bit Quantization (IQ3_XS, IQ3_S, IQ3_M, Q4_K, Q4_0) These models are optimized for extreme memory efficiency, making them ideal for low-power devices or large-scale deployments where memory is a critical constraint. - IQ3_XS: Ultra-low-bit quantization (3-bit) with extreme memory efficiency. - Use case: Best for ultra-low-memory devices where even Q4_K is too large. - Trade-off: Lower accuracy compared to higher-bit quantizations. - IQ3_S: Small block size for maximum memory efficiency. - Use case: Best for low-memory devices where IQ3_XS is too aggressive. - IQ3_M: Medium block size for better accuracy than IQ3_S. - Use case: Suitable for low-memory devices where IQ3_S is too limiting. - Q4_K: 4-bit quantization with block-wise optimization for better accuracy. - Use case: Best for low-memory devices where Q6_K is too large. - Q4_0: Pure 4-bit quantization, optimized for ARM devices. - Use case: Best for ARM-based devices or low-memory environments. --- ### Summary Table: Model Format Selection \| Model Format \| Precision \| Memory Usage \| Device Requirements \| Best Use Case \| \|--------------\|------------\|---------------\|----------------------\|---------------\| \| BF16 \| Highest \| High \| BF16-supported GPU/CPUs \| High-speed inference with reduced memory \| \| F16 \| High \| High \| FP16-supported devices \| GPU inference when BF16 isn't available \| \| Q4_K \| Medium Low \| Low \| CPU or Low-VRAM devices \| Best for memory-constrained environments \| \| Q6_K \| Medium \| Moderate \| CPU with more memory \| Better accuracy while still being quantized \| \| Q8_0 \| High \| Moderate \| CPU or GPU with enough VRAM \| Best accuracy among quantized models \| \| IQ3_XS \| Very Low \| Very Low \| Ultra-low-memory devices \| Extreme memory efficiency and low accuracy \| \| Q4_0 \| Low \| Low \| ARM or low-memory devices \| llama.cpp can optimize for ARM devices \| --- ## Included Files & Details ### `Llama-3.1-Nemotron-Nano-8B-v1-bf16.gguf` - Model weights preserved in BF16. - Use this if you want to requantize the model into a different format. - Best if your device supports BF16 acceleration. ### `Llama-3.1-Nemotron-Nano-8B-v1-f16.gguf` - Model weights stored in F16. - Use if your device supports FP16, especially if BF16 is not available. ### `Llama-3.1-Nemotron-Nano-8B-v1-bf16-q8_0.gguf` - Output & embeddings remain in BF16. - All other layers quantized to Q8_0. - Use if your device supports BF16 and you want a quantized version. ### `Llama-3.1-Nemotron-Nano-8B-v1-f16-q8_0.gguf` - Output & embeddings remain in F16. - All other layers quantized to Q8_0. ### `Llama-3.1-Nemotron-Nano-8B-v1-q4_k.gguf` - Output & embeddings quantized to Q8_0. - All other layers quantized to Q4_K. - Good for CPU inference with limited memory. ### `Llama-3.1-Nemotron-Nano-8B-v1-q4_k_s.gguf` - Smallest Q4_K variant, using less memory at the cost of accuracy. - Best for very low-memory setups. ### `Llama-3.1-Nemotron-Nano-8B-v1-q6_k.gguf` - Output & embeddings quantized to Q8_0. - All other layers quantized to Q6_K . ### `Llama-3.1-Nemotron-Nano-8B-v1-q8_0.gguf` - Fully Q8 quantized model for better accuracy. - Requires more memory but offers higher precision. ### `Llama-3.1-Nemotron-Nano-8B-v1-iq3_xs.gguf` - IQ3_XS quantization, optimized for extreme memory efficiency. - Best for ultra-low-memory devices. ### `Llama-3.1-Nemotron-Nano-8B-v1-iq3_m.gguf` - IQ3_M quantization, offering a medium block size for better accuracy. - Suitable for low-memory devices. ### `Llama-3.1-Nemotron-Nano-8B-v1-q4_0.gguf` - Pure Q4_0 quantization, optimized for ARM devices. - Best for low-memory environments. - Prefer IQ4_NL for better accuracy. # <span id="testllm" style="color: #7F7FFF;">🚀 If you find these models useful</span> ❤ Please click "Like" if you find this useful! Help me test my AI-Powered Network Monitor Assistant with quantum-ready security checks: 👉 [Quantum Network Monitor](https://readyforquantum.com/dashboard/?assistant=open&utm_source=huggingface&utm_medium=referral&utm_campaign=huggingface_repo_readme) 💬 How to test: Choose an AI assistant type: - `TurboLLM` (GPT-4o-mini) - `HugLLM` (Hugginface Open-source) - `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 scans - Quantum-readiness checks - Network Monitoring tasks 🟡 TestLLM – Current experimental model (llama.cpp on 2 CPU threads): - ✅ Zero-configuration setup - ⏳ 30s load time (slow inference but no API costs) - 🔧 Help wanted! If you’re into edge-device AI, let’s collaborate! ### Other Assistants 🟢 TurboLLM – Uses gpt-4o-mini for: - 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 ### 💡 Example commands to 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 to run the .net code from. 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! 😊 # Llama-3.1-Nemotron-Nano-8B-v1 ## Model Overview Llama-3.1-Nemotron-Nano-8B-v1 is a large language model (LLM) which is a derivative of [Meta Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct) (AKA the reference model). It is a reasoning model that is post trained for reasoning, human chat preferences, and tasks, such as RAG and tool calling. Llama-3.1-Nemotron-Nano-8B-v1 is a model which offers a great tradeoff between model accuracy and efficiency. It is created from Llama 3.1 8B Instruct and offers improvements in model accuracy. The model fits on a single RTX GPU and can be used locally. The model supports a context length of 128K. This model underwent a multi-phase post-training process to enhance both its reasoning and non-reasoning capabilities. This includes a supervised fine-tuning stage for Math, Code, Reasoning, and Tool Calling as well as multiple reinforcement learning (RL) stages using REINFORCE (RLOO) and Online Reward-aware Preference Optimization (RPO) algorithms for both chat and instruction-following. The final model checkpoint is obtained after merging the final SFT and Online RPO checkpoints. Improved using Qwen. This model is part of the Llama Nemotron Collection. You can find the other model(s) in this family here: [Llama-3.3-Nemotron-Super-49B-v1](https://huggingface.co/nvidia/Llama-3.3-Nemotron-Super-49B-v1) This model is ready for commercial use. ## License/Terms of Use GOVERNING TERMS: Your use of this model is governed by the [NVIDIA Open Model License](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/). Additional Information: [Llama 3.1 Community License Agreement](https://www.llama.com/llama3_1/license/). Built with Llama. Model Developer: NVIDIA Model Dates: Trained between August 2024 and March 2025 Data Freshness: The pretraining data has a cutoff of 2023 per Meta Llama 3.1 8B ## Use Case: Developers designing AI Agent systems, chatbots, RAG systems, and other AI-powered applications. Also suitable for typical instruction-following tasks. Balance of model accuracy and compute efficiency (the model fits on a single RTX GPU and can be used locally). ## Release Date: <br> 3/18/2025 <br> ## References - [\[2505.00949\] Llama-Nemotron: Efficient Reasoning Models](https://arxiv.org/abs/2505.00949) - [\[2502.00203\] Reward-aware Preference Optimization: A Unified Mathematical Framework for Model Alignment](https://arxiv.org/abs/2502.00203) ## Model Architecture Architecture Type: Dense decoder-only Transformer model Network Architecture: Llama 3.1 8B Instruct ## Intended use Llama-3.1-Nemotron-Nano-8B-v1 is a general purpose reasoning and chat model intended to be used in English and coding languages. Other non-English languages (German, French, Italian, Portuguese, Hindi, Spanish, and Thai) are also supported. # Input: - Input Type: Text - Input Format: String - Input Parameters: One-Dimensional (1D) - Other Properties Related to Input: Context length up to 131,072 tokens ## Output: - Output Type: Text - Output Format: String - Output Parameters: One-Dimensional (1D) - Other Properties Related to Output: Context length up to 131,072 tokens ## Model Version: 1.0 (3/18/2025) ## Software Integration - Runtime Engine: NeMo 24.12 <br> - Recommended Hardware Microarchitecture Compatibility: - NVIDIA Hopper - NVIDIA Ampere ## Quick Start and Usage Recommendations: 1. Reasoning mode (ON/OFF) is controlled via the system prompt, which must be set as shown in the example below. All instructions should be contained within the user prompt 2. We recommend setting temperature to `0.6`, and Top P to `0.95` for Reasoning ON mode 3. We recommend using greedy decoding for Reasoning OFF mode 4. We have provided a list of prompts to use for evaluation for each benchmark where a specific template is required 5. The model will include `<think></think>` if no reasoning was necessary in Reasoning ON model, this is expected behaviour You can try this model out through the preview API, using this link: [Llama-3.1-Nemotron-Nano-8B-v1](https://build.nvidia.com/nvidia/llama-3_1-nemotron-nano-8b-v1). See the snippet below for usage with Hugging Face Transformers library. Reasoning mode (ON/OFF) is controlled via system prompt. Please see the example below. Our code requires the transformers package version to be `4.44.2` or higher. ### Example of “Reasoning On:” ```python import torch import transformers model_id = "nvidia/Llama-3.1-Nemotron-Nano-8B-v1" model_kwargs = {"torch_dtype": torch.bfloat16, "device_map": "auto"} tokenizer = transformers.AutoTokenizer.from_pretrained(model_id) tokenizer.pad_token_id = tokenizer.eos_token_id pipeline = transformers.pipeline( "text-generation", model=model_id, tokenizer=tokenizer, max_new_tokens=32768, temperature=0.6, top_p=0.95, *model_kwargs ) # Thinking can be "on" or "off" thinking = "on" print(pipeline([{"role": "system", "content": f"detailed thinking {thinking}"}, {"role": "user", "content": "Solve x(sin(x)+2)=0"}])) ``` ### Example of “Reasoning Off:” ```python import torch import transformers model_id = "nvidia/Llama-3.1-Nemotron-Nano-8B-v1" model_kwargs = {"torch_dtype": torch.bfloat16, "device_map": "auto"} tokenizer = transformers.AutoTokenizer.from_pretrained(model_id) tokenizer.pad_token_id = tokenizer.eos_token_id pipeline = transformers.pipeline( "text-generation", model=model_id, tokenizer=tokenizer, max_new_tokens=32768, do_sample=False, *model_kwargs ) # Thinking can be "on" or "off" thinking = "off" print(pipeline([{"role": "system", "content": f"detailed thinking {thinking}"}, {"role": "user", "content": "Solve x(sin(x)+2)=0"}])) ``` For some prompts, even though thinking is disabled, the model emergently prefers to think before responding. But if desired, the users can prevent it by pre-filling the assistant response. ```python import torch import transformers model_id = "nvidia/Llama-3.1-Nemotron-Nano-8B-v1" model_kwargs = {"torch_dtype": torch.bfloat16, "device_map": "auto"} tokenizer = transformers.AutoTokenizer.from_pretrained(model_id) tokenizer.pad_token_id = tokenizer.eos_token_id # Thinking can be "on" or "off" thinking = "off" pipeline = transformers.pipeline( "text-generation", model=model_id, tokenizer=tokenizer, max_new_tokens=32768, do_sample=False, *model_kwargs ) print(pipeline([{"role": "system", "content": f"detailed thinking {thinking}"}, {"role": "user", "content": "Solve x(sin(x)+2)=0"}, {"role":"assistant", "content":"<think>\n</think>"}])) ``` ## Inference: Engine: Transformers Test Hardware: - BF16: - 1x RTX 50 Series GPUs - 1x RTX 40 Series GPUs - 1x RTX 30 Series GPUs - 1x H100-80GB GPU - 1x A100-80GB GPU Preferred/Supported] Operating System(s): Linux <br> ## Training Datasets A large variety of training data was used for the post-training pipeline, including manually annotated data and synthetic data. The data for the multi-stage post-training phases for improvements in Code, Math, and Reasoning is a compilation of SFT and RL data that supports improvements of math, code, general reasoning, and instruction following capabilities of the original Llama instruct model. Prompts have been sourced from either public and open corpus or synthetically generated. Responses were synthetically generated by a variety of models, with some prompts containing responses for both Reasoning On and Off modes, to train the model to distinguish between two modes. Data Collection for Training Datasets: <br> * Hybrid: Automated, Human, Synthetic <br> Data Labeling for Training Datasets: <br> * N/A <br> ## Evaluation Datasets We used the datasets listed below to evaluate Llama-3.1-Nemotron-Nano-8B-v1. Data Collection for Evaluation Datasets: Hybrid: Human/Synthetic Data Labeling for Evaluation Datasets: Hybrid: Human/Synthetic/Automatic ## Evaluation Results These results contain both “Reasoning On”, and “Reasoning Off”. We recommend using temperature=`0.6`, top_p=`0.95` for “Reasoning On” mode, and greedy decoding for “Reasoning Off” mode. All evaluations are done with 32k sequence length. We run the benchmarks up to 16 times and average the scores to be more accurate. > NOTE: Where applicable, a Prompt Template will be provided. While completing benchmarks, please ensure that you are parsing for the correct output format as per the provided prompt in order to reproduce the benchmarks seen below. ### MT-Bench \| Reasoning Mode \| Score \| \|--------------\|------------\| \| Reasoning Off \| 7.9 \| \| Reasoning On \| 8.1 \| ### MATH500 \| Reasoning Mode \| pass@1 \| \|--------------\|------------\| \| Reasoning Off \| 36.6% \| \| Reasoning On \| 95.4% \| User Prompt Template: ``` "Below is a math question. I want you to reason through the steps and then give a final answer. Your final answer should be in \boxed{}.\nQuestion: {question}" ``` ### AIME25 \| Reasoning Mode \| pass@1 \| \|--------------\|------------\| \| Reasoning Off \| 0% \| \| Reasoning On \| 47.1% \| User Prompt Template: ``` "Below is a math question. I want you to reason through the steps and then give a final answer. Your final answer should be in \boxed{}.\nQuestion: {question}" ``` ### GPQA-D \| Reasoning Mode \| pass@1 \| \|--------------\|------------\| \| Reasoning Off \| 39.4% \| \| Reasoning On \| 54.1% \| User Prompt Template: ``` "What is the correct answer to this question: {question}\nChoices:\nA. {option_A}\nB. {option_B}\nC. {option_C}\nD. {option_D}\nLet's think step by step, and put the final answer (should be a single letter A, B, C, or D) into a \boxed{}" ``` ### IFEval Average \| Reasoning Mode \| Strict:Prompt \| Strict:Instruction \| \|--------------\|------------\|------------\| \| Reasoning Off \| 74.7% \| 82.1% \| \| Reasoning On \| 71.9% \| 79.3% \| ### BFCL v2 Live \| Reasoning Mode \| Score \| \|--------------\|------------\| \| Reasoning Off \| 63.9% \| \| Reasoning On \| 63.6% \| User Prompt Template: ``` <AVAILABLE_TOOLS>{functions}</AVAILABLE_TOOLS> {user_prompt} ``` ### MBPP 0-shot \| Reasoning Mode \| pass@1 \| \|--------------\|------------\| \| Reasoning Off \| 66.1% \| \| Reasoning On \| 84.6% \| User Prompt Template: ```` You are an exceptionally intelligent coding assistant that consistently delivers accurate and reliable responses to user instructions. @@ Instruction Here is the given problem and test examples: {prompt} Please use the python programming language to solve this problem. Please make sure that your code includes the functions from the test samples and that the input and output formats of these functions match the test samples. Please return all completed codes in one code block. This code block should be in the following format: ```python # Your codes here ``` ```` ## Ethical Considerations: NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications. When downloaded or used in accordance with our terms of service, developers should work with their internal model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse. For more detailed information on ethical considerations for this model, please see the Model Card++ [Explainability](explainability.md), [Bias](bias.md), [Safety & Security](safety.md), and [Privacy](privacy.md) Subcards. Please report security vulnerabilities or NVIDIA AI Concerns [here](https://www.nvidia.com/en-us/support/submit-security-vulnerability/). ## Citation ``` @misc{bercovich2025llamanemotronefficientreasoningmodels, title={Llama-Nemotron: Efficient Reasoning Models}, author={Akhiad Bercovich and Itay Levy and Izik Golan and Mohammad Dabbah and Ran El-Yaniv and Omri Puny and Ido Galil and Zach Moshe and Tomer Ronen and Najeeb Nabwani and Ido Shahaf and Oren Tropp and Ehud Karpas and Ran Zilberstein and Jiaqi Zeng and Soumye Singhal and Alexander Bukharin and Yian Zhang and Tugrul Konuk and Gerald Shen and Ameya Sunil Mahabaleshwarkar and Bilal Kartal and Yoshi Suhara and Olivier Delalleau and Zijia Chen and Zhilin Wang and David Mosallanezhad and Adi Renduchintala and Haifeng Qian and Dima Rekesh and Fei Jia and Somshubra Majumdar and Vahid Noroozi and Wasi Uddin Ahmad and Sean Narenthiran and Aleksander Ficek and Mehrzad Samadi and Jocelyn Huang and Siddhartha Jain and Igor Gitman and Ivan Moshkov and Wei Du and Shubham Toshniwal and George Armstrong and Branislav Kisacanin and Matvei Novikov and Daria Gitman and Evelina Bakhturina and Jane Polak Scowcroft and John Kamalu and Dan Su and Kezhi Kong and Markus Kliegl and Rabeeh Karimi and Ying Lin and Sanjeev Satheesh and Jupinder Parmar and Pritam Gundecha and Brandon Norick and Joseph Jennings and Shrimai Prabhumoye and Syeda Nahida Akter and Mostofa Patwary and Abhinav Khattar and Deepak Narayanan and Roger Waleffe and Jimmy Zhang and Bor-Yiing Su and Guyue Huang and Terry Kong and Parth Chadha and Sahil Jain and Christine Harvey and Elad Segal and Jining Huang and Sergey Kashirsky and Robert McQueen and Izzy Putterman and George Lam and Arun Venkatesan and Sherry Wu and Vinh Nguyen and Manoj Kilaru and Andrew Wang and Anna Warno and Abhilash Somasamudramath and Sandip Bhaskar and Maka Dong and Nave Assaf and Shahar Mor and Omer Ullman Argov and Scot Junkin and Oleksandr Romanenko and Pedro Larroy and Monika Katariya and Marco Rovinelli and Viji Balas and Nicholas Edelman and Anahita Bhiwandiwalla and Muthu Subramaniam and Smita Ithape and Karthik Ramamoorthy and Yuting Wu and Suguna Varshini Velury and Omri Almog and Joyjit Daw and Denys Fridman and Erick Galinkin and Michael Evans and Katherine Luna and Leon Derczynski and Nikki Pope and Eileen Long and Seth Schneider and Guillermo Siman and Tomasz Grzegorzek and Pablo Ribalta and Monika Katariya and Joey Conway and Trisha Saar and Ann Guan and Krzysztof Pawelec and Shyamala Prayaga and Oleksii Kuchaiev and Boris Ginsburg and Oluwatobi Olabiyi and Kari Briski and Jonathan Cohen and Bryan Catanzaro and Jonah Alben and Yonatan Geifman and Eric Chung and Chris Alexiuk}, year={2025}, eprint={2505.00949}, archivePrefix={arXiv}, primaryClass={cs.CL}, url={https://arxiv.org/abs/2505.00949}, } ```
Mungert/DeepSeek-R1-Distill-Llama-8B-GGUF	Mungert	2025-06-15T19:41:20Z	2,816	3	transformers	[ "transformers", "gguf", "arxiv:2501.12948", "license:mit", "endpoints_compatible", "region:us", "imatrix", "conversational" ]	null	2025-03-20T07:53:43Z	--- license: mit library_name: transformers --- # <span style="color: #7FFF7F;">DeepSeek-R1-Distill-Llama-8B GGUF Models</span> ## <span style="color: #7FFF7F;">Ultra-Low-Bit Quantization with IQ-DynamicGate (1-2 bit)</span> Our latest quantization method introduces precision-adaptive quantization for ultra-low-bit models (1-2 bit), with benchmark-proven improvements on Llama-3-8B. This approach uses layer-specific strategies to preserve accuracy while maintaining extreme memory efficiency. ### Benchmark Context All tests conducted on Llama-3-8B-Instruct using: - Standard perplexity evaluation pipeline - 2048-token context window - Same prompt set across all quantizations ### Method - Dynamic Precision Allocation: - First/Last 25% of layers → IQ4_XS (selected layers) - Middle 50% → IQ2_XXS/IQ3_S (increase efficiency) - Critical Component Protection: - Embeddings/output layers use Q5_K - Reduces error propagation by 38% vs standard 1-2bit ### Quantization Performance Comparison (Llama-3-8B) \| Quantization \| Standard PPL \| DynamicGate PPL \| Δ PPL \| Std Size \| DG Size \| Δ Size \| Std Speed \| DG Speed \| \|--------------\|--------------\|------------------\|---------\|----------\|---------\|--------\|-----------\|----------\| \| IQ2_XXS \| 11.30 \| 9.84 \| -12.9% \| 2.5G \| 2.6G \| +0.1G \| 234s \| 246s \| \| IQ2_XS \| 11.72 \| 11.63 \| -0.8% \| 2.7G \| 2.8G \| +0.1G \| 242s \| 246s \| \| IQ2_S \| 14.31 \| 9.02 \| -36.9% \| 2.7G \| 2.9G \| +0.2G \| 238s \| 244s \| \| IQ1_M \| 27.46 \| 15.41 \| -43.9% \| 2.2G \| 2.5G \| +0.3G \| 206s \| 212s \| \| IQ1_S \| 53.07 \| 32.00 \| -39.7% \| 2.1G \| 2.4G \| +0.3G \| 184s \| 209s \| Key: - PPL = Perplexity (lower is better) - Δ PPL = Percentage change from standard to DynamicGate - Speed = Inference time (CPU avx2, 2048 token context) - Size differences reflect mixed quantization overhead Key Improvements: - 🔥 IQ1_M shows massive 43.9% perplexity reduction (27.46 → 15.41) - 🚀 IQ2_S cuts perplexity by 36.9% while adding only 0.2GB - ⚡ IQ1_S maintains 39.7% better accuracy despite 1-bit quantization Tradeoffs: - All variants have modest size increases (0.1-0.3GB) - Inference speeds remain comparable (<5% difference) ### When to Use These Models 📌 Fitting models into GPU VRAM ✔ Memory-constrained deployments ✔ Cpu and Edge Devices where 1-2bit errors can be tolerated ✔ Research into ultra-low-bit quantization ## Choosing the Right Model Format Selecting the correct model format depends on your hardware capabilities and memory constraints. ### BF16 (Brain Float 16) – Use if BF16 acceleration is available - A 16-bit floating-point format designed for faster computation while retaining good precision. - Provides similar dynamic range as FP32 but with lower memory usage. - Recommended if your hardware supports BF16 acceleration (check your device's specs). - Ideal for high-performance inference with reduced memory footprint compared to FP32. 📌 Use BF16 if: ✔ Your hardware has native BF16 support (e.g., newer GPUs, TPUs). ✔ You want higher precision while saving memory. ✔ You plan to requantize the model into another format. 📌 Avoid BF16 if: ❌ Your hardware does not support BF16 (it may fall back to FP32 and run slower). ❌ You need compatibility with older devices that lack BF16 optimization. --- ### F16 (Float 16) – More widely supported than BF16 - A 16-bit floating-point high precision but with less of range of values than BF16. - Works on most devices with FP16 acceleration support (including many GPUs and some CPUs). - Slightly lower numerical precision than BF16 but generally sufficient for inference. 📌 Use F16 if: ✔ Your hardware supports FP16 but not BF16. ✔ You need a balance between speed, memory usage, and accuracy. ✔ You are running on a GPU or another device optimized for FP16 computations. 📌 Avoid F16 if: ❌ Your device lacks native FP16 support (it may run slower than expected). ❌ You have memory limitations. --- ### Quantized Models (Q4_K, Q6_K, Q8, etc.) – For CPU & Low-VRAM Inference Quantization reduces model size and memory usage while maintaining as much accuracy as possible. - Lower-bit models (Q4_K) → Best for minimal memory usage, may have lower precision. - Higher-bit models (Q6_K, Q8_0) → Better accuracy, requires more memory. 📌 Use Quantized Models if: ✔ You are running inference on a CPU and need an optimized model. ✔ Your device has low VRAM and cannot load full-precision models. ✔ You want to reduce memory footprint while keeping reasonable accuracy. 📌 Avoid Quantized Models if: ❌ You need maximum accuracy (full-precision models are better for this). ❌ Your hardware has enough VRAM for higher-precision formats (BF16/F16). --- ### Very Low-Bit Quantization (IQ3_XS, IQ3_S, IQ3_M, Q4_K, Q4_0) These models are optimized for extreme memory efficiency, making them ideal for low-power devices or large-scale deployments where memory is a critical constraint. - IQ3_XS: Ultra-low-bit quantization (3-bit) with extreme memory efficiency. - Use case: Best for ultra-low-memory devices where even Q4_K is too large. - Trade-off: Lower accuracy compared to higher-bit quantizations. - IQ3_S: Small block size for maximum memory efficiency. - Use case: Best for low-memory devices where IQ3_XS is too aggressive. - IQ3_M: Medium block size for better accuracy than IQ3_S. - Use case: Suitable for low-memory devices where IQ3_S is too limiting. - Q4_K: 4-bit quantization with block-wise optimization for better accuracy. - Use case: Best for low-memory devices where Q6_K is too large. - Q4_0: Pure 4-bit quantization, optimized for ARM devices. - Use case: Best for ARM-based devices or low-memory environments. --- ### Summary Table: Model Format Selection \| Model Format \| Precision \| Memory Usage \| Device Requirements \| Best Use Case \| \|--------------\|------------\|---------------\|----------------------\|---------------\| \| BF16 \| Highest \| High \| BF16-supported GPU/CPUs \| High-speed inference with reduced memory \| \| F16 \| High \| High \| FP16-supported devices \| GPU inference when BF16 isn't available \| \| Q4_K \| Medium Low \| Low \| CPU or Low-VRAM devices \| Best for memory-constrained environments \| \| Q6_K \| Medium \| Moderate \| CPU with more memory \| Better accuracy while still being quantized \| \| Q8_0 \| High \| Moderate \| CPU or GPU with enough VRAM \| Best accuracy among quantized models \| \| IQ3_XS \| Very Low \| Very Low \| Ultra-low-memory devices \| Extreme memory efficiency and low accuracy \| \| Q4_0 \| Low \| Low \| ARM or low-memory devices \| llama.cpp can optimize for ARM devices \| --- ## Included Files & Details ### `DeepSeek-R1-Distill-Llama-8B-bf16.gguf` - Model weights preserved in BF16. - Use this if you want to requantize the model into a different format. - Best if your device supports BF16 acceleration. ### `DeepSeek-R1-Distill-Llama-8B-f16.gguf` - Model weights stored in F16. - Use if your device supports FP16, especially if BF16 is not available. ### `DeepSeek-R1-Distill-Llama-8B-bf16-q8_0.gguf` - Output & embeddings remain in BF16. - All other layers quantized to Q8_0. - Use if your device supports BF16 and you want a quantized version. ### `DeepSeek-R1-Distill-Llama-8B-f16-q8_0.gguf` - Output & embeddings remain in F16. - All other layers quantized to Q8_0. ### `DeepSeek-R1-Distill-Llama-8B-q4_k.gguf` - Output & embeddings quantized to Q8_0. - All other layers quantized to Q4_K. - Good for CPU inference with limited memory. ### `DeepSeek-R1-Distill-Llama-8B-q4_k_s.gguf` - Smallest Q4_K variant, using less memory at the cost of accuracy. - Best for very low-memory setups. ### `DeepSeek-R1-Distill-Llama-8B-q6_k.gguf` - Output & embeddings quantized to Q8_0. - All other layers quantized to Q6_K . ### `DeepSeek-R1-Distill-Llama-8B-q8_0.gguf` - Fully Q8 quantized model for better accuracy. - Requires more memory but offers higher precision. ### `DeepSeek-R1-Distill-Llama-8B-iq3_xs.gguf` - IQ3_XS quantization, optimized for extreme memory efficiency. - Best for ultra-low-memory devices. ### `DeepSeek-R1-Distill-Llama-8B-iq3_m.gguf` - IQ3_M quantization, offering a medium block size for better accuracy. - Suitable for low-memory devices. ### `DeepSeek-R1-Distill-Llama-8B-q4_0.gguf` - Pure Q4_0 quantization, optimized for ARM devices. - Best for low-memory environments. - Prefer IQ4_NL for better accuracy. # <span id="testllm" style="color: #7F7FFF;">🚀 If you find these models useful</span> ❤ Please click "Like" if you find this useful! Help me test my AI-Powered Network Monitor Assistant with quantum-ready security checks: 👉 [Quantum Network Monitor](https://readyforquantum.com) 💬 How to test: 1. Click the chat icon (bottom right on any page) 2. Choose an AI assistant type: - `TurboLLM` (GPT-4-mini) - `FreeLLM` (Open-source) - `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 scans - Quantum-readiness checks - Metasploit integration 🟡 TestLLM – Current experimental model (llama.cpp on 6 CPU threads): - ✅ Zero-configuration setup - ⏳ 30s load time (slow inference but no API costs) - 🔧 Help wanted! If you’re into edge-device AI, let’s collaborate! ### Other Assistants 🟢 TurboLLM – Uses gpt-4-mini for: - Real-time network diagnostics - Automated penetration testing (Nmap/Metasploit) - 🔑 Get more tokens by [downloading our Quantum Network Monitor Agent](https://readyforquantum.com/download/?utm_source=huggingface&utm_medium=referral&utm_campaign=huggingface_repo_readme) 🔵 HugLLM – Open-source models (≈8B params): - 2x more tokens than TurboLLM - AI-powered log analysis - 🌐 Runs on Hugging Face Inference API ### 💡 Example AI Commands to 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 quick Nmap vulnerability test"` 4. '"Create a cmd processor to .. (what ever you want)" Note you need to install a Quantum Network Monitor Agent to run the .net code from. This is a very flexible and powerful feature. Use with caution! ### Final word I fund the servers to create the models files, run the Quantum Network Monitor Service and Pay for Inference from Novita and OpenAI all from my own pocket. All of the code for creating the models and the work I have done with Quantum Network Monitor is [open source](https://github.com/Mungert69). Feel free to use what you find useful. Please support my work and consider [buying me a coffee](https://www.buymeacoffee.com/mahadeva) . This will help me pay for the services and increase the token limits for everyone. Thank you :) # DeepSeek-R1 <!-- markdownlint-disable first-line-h1 --> <!-- markdownlint-disable html --> <!-- markdownlint-disable no-duplicate-header --> <div align="center"> <img src="https://github.com/deepseek-ai/DeepSeek-V2/blob/main/figures/logo.svg?raw=true" width="60%" alt="DeepSeek-V3" /> </div> <hr> <div align="center" style="line-height: 1;"> <a href="https://www.deepseek.com/" target="_blank" style="margin: 2px;"> <img alt="Homepage" src="https://github.com/deepseek-ai/DeepSeek-V2/blob/main/figures/badge.svg?raw=true" style="display: inline-block; vertical-align: middle;"/> </a> <a href="https://chat.deepseek.com/" target="_blank" style="margin: 2px;"> <img alt="Chat" src="https://img.shields.io/badge/🤖%20Chat-DeepSeek%20R1-536af5?color=536af5&logoColor=white" style="display: inline-block; vertical-align: middle;"/> </a> <a href="https://huggingface.co/deepseek-ai" target="_blank" style="margin: 2px;"> <img alt="Hugging Face" src="https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-DeepSeek%20AI-ffc107?color=ffc107&logoColor=white" style="display: inline-block; vertical-align: middle;"/> </a> </div> <div align="center" style="line-height: 1;"> <a href="https://discord.gg/Tc7c45Zzu5" target="_blank" style="margin: 2px;"> <img alt="Discord" src="https://img.shields.io/badge/Discord-DeepSeek%20AI-7289da?logo=discord&logoColor=white&color=7289da" style="display: inline-block; vertical-align: middle;"/> </a> <a href="https://github.com/deepseek-ai/DeepSeek-V2/blob/main/figures/qr.jpeg?raw=true" target="_blank" style="margin: 2px;"> <img alt="Wechat" src="https://img.shields.io/badge/WeChat-DeepSeek%20AI-brightgreen?logo=wechat&logoColor=white" style="display: inline-block; vertical-align: middle;"/> </a> <a href="https://twitter.com/deepseek_ai" target="_blank" style="margin: 2px;"> <img alt="Twitter Follow" src="https://img.shields.io/badge/Twitter-deepseek_ai-white?logo=x&logoColor=white" style="display: inline-block; vertical-align: middle;"/> </a> </div> <div align="center" style="line-height: 1;"> <a href="https://github.com/deepseek-ai/DeepSeek-R1/blob/main/LICENSE" style="margin: 2px;"> <img alt="License" src="https://img.shields.io/badge/License-MIT-f5de53?&color=f5de53" style="display: inline-block; vertical-align: middle;"/> </a> </div> <p align="center"> <a href="https://github.com/deepseek-ai/DeepSeek-R1/blob/main/DeepSeek_R1.pdf"><b>Paper Link</b>👁️</a> </p> ## 1. Introduction We introduce our first-generation reasoning models, DeepSeek-R1-Zero and DeepSeek-R1. DeepSeek-R1-Zero, a model trained via large-scale reinforcement learning (RL) without supervised fine-tuning (SFT) as a preliminary step, demonstrated remarkable performance on reasoning. With RL, DeepSeek-R1-Zero naturally emerged with numerous powerful and interesting reasoning behaviors. However, DeepSeek-R1-Zero encounters challenges such as endless repetition, poor readability, and language mixing. To address these issues and further enhance reasoning performance, we introduce DeepSeek-R1, which incorporates cold-start data before RL. DeepSeek-R1 achieves performance comparable to OpenAI-o1 across math, code, and reasoning tasks. To support the research community, we have open-sourced DeepSeek-R1-Zero, DeepSeek-R1, and six dense models distilled from DeepSeek-R1 based on Llama and Qwen. DeepSeek-R1-Distill-Qwen-32B outperforms OpenAI-o1-mini across various benchmarks, achieving new state-of-the-art results for dense models. NOTE: Before running DeepSeek-R1 series models locally, we kindly recommend reviewing the [Usage Recommendation](#usage-recommendations) section. <p align="center"> <img width="80%" src="figures/benchmark.jpg"> </p> ## 2. Model Summary --- Post-Training: Large-Scale Reinforcement Learning on the Base Model - We directly apply reinforcement learning (RL) to the base model without relying on supervised fine-tuning (SFT) as a preliminary step. This approach allows the model to explore chain-of-thought (CoT) for solving complex problems, resulting in the development of DeepSeek-R1-Zero. DeepSeek-R1-Zero demonstrates capabilities such as self-verification, reflection, and generating long CoTs, marking a significant milestone for the research community. Notably, it is the first open research to validate that reasoning capabilities of LLMs can be incentivized purely through RL, without the need for SFT. This breakthrough paves the way for future advancements in this area. - We introduce our pipeline to develop DeepSeek-R1. The pipeline incorporates two RL stages aimed at discovering improved reasoning patterns and aligning with human preferences, as well as two SFT stages that serve as the seed for the model's reasoning and non-reasoning capabilities. We believe the pipeline will benefit the industry by creating better models. --- Distillation: Smaller Models Can Be Powerful Too - We demonstrate that the reasoning patterns of larger models can be distilled into smaller models, resulting in better performance compared to the reasoning patterns discovered through RL on small models. The open source DeepSeek-R1, as well as its API, will benefit the research community to distill better smaller models in the future. - Using the reasoning data generated by DeepSeek-R1, we fine-tuned several dense models that are widely used in the research community. The evaluation results demonstrate that the distilled smaller dense models perform exceptionally well on benchmarks. We open-source distilled 1.5B, 7B, 8B, 14B, 32B, and 70B checkpoints based on Qwen2.5 and Llama3 series to the community. ## 3. Model Downloads ### DeepSeek-R1 Models <div align="center"> \| Model \| #Total Params \| #Activated Params \| Context Length \| Download \| \| :------------: \| :------------: \| :------------: \| :------------: \| :------------: \| \| DeepSeek-R1-Zero \| 671B \| 37B \| 128K \| [🤗 HuggingFace](https://huggingface.co/deepseek-ai/DeepSeek-R1-Zero) \| \| DeepSeek-R1 \| 671B \| 37B \| 128K \| [🤗 HuggingFace](https://huggingface.co/deepseek-ai/DeepSeek-R1) \| </div> DeepSeek-R1-Zero & DeepSeek-R1 are trained based on DeepSeek-V3-Base. For more details regarding the model architecture, please refer to [DeepSeek-V3](https://github.com/deepseek-ai/DeepSeek-V3) repository. ### DeepSeek-R1-Distill Models <div align="center"> \| Model \| Base Model \| Download \| \| :------------: \| :------------: \| :------------: \| \| DeepSeek-R1-Distill-Qwen-1.5B \| [Qwen2.5-Math-1.5B](https://huggingface.co/Qwen/Qwen2.5-Math-1.5B) \| [🤗 HuggingFace](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B) \| \| DeepSeek-R1-Distill-Qwen-7B \| [Qwen2.5-Math-7B](https://huggingface.co/Qwen/Qwen2.5-Math-7B) \| [🤗 HuggingFace](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B) \| \| DeepSeek-R1-Distill-Llama-8B \| [Llama-3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B) \| [🤗 HuggingFace](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-8B) \| \| DeepSeek-R1-Distill-Qwen-14B \| [Qwen2.5-14B](https://huggingface.co/Qwen/Qwen2.5-14B) \| [🤗 HuggingFace](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B) \| \|DeepSeek-R1-Distill-Qwen-32B \| [Qwen2.5-32B](https://huggingface.co/Qwen/Qwen2.5-32B) \| [🤗 HuggingFace](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B) \| \| DeepSeek-R1-Distill-Llama-70B \| [Llama-3.3-70B-Instruct](https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct) \| [🤗 HuggingFace](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-70B) \| </div> DeepSeek-R1-Distill models are fine-tuned based on open-source models, using samples generated by DeepSeek-R1. We slightly change their configs and tokenizers. Please use our setting to run these models. ## 4. Evaluation Results ### DeepSeek-R1-Evaluation For all our models, the maximum generation length is set to 32,768 tokens. For benchmarks requiring sampling, we use a temperature of $0.6$, a top-p value of $0.95$, and generate 64 responses per query to estimate pass@1. <div align="center"> \| Category \| Benchmark (Metric) \| Claude-3.5-Sonnet-1022 \| GPT-4o 0513 \| DeepSeek V3 \| OpenAI o1-mini \| OpenAI o1-1217 \| DeepSeek R1 \| \|----------\|-------------------\|----------------------\|------------\|--------------\|----------------\|------------\|--------------\| \| \| Architecture \| - \| - \| MoE \| - \| - \| MoE \| \| \| # Activated Params \| - \| - \| 37B \| - \| - \| 37B \| \| \| # Total Params \| - \| - \| 671B \| - \| - \| 671B \| \| English \| MMLU (Pass@1) \| 88.3 \| 87.2 \| 88.5 \| 85.2 \| 91.8 \| 90.8 \| \| \| MMLU-Redux (EM) \| 88.9 \| 88.0 \| 89.1 \| 86.7 \| - \| 92.9 \| \| \| MMLU-Pro (EM) \| 78.0 \| 72.6 \| 75.9 \| 80.3 \| - \| 84.0 \| \| \| DROP (3-shot F1) \| 88.3 \| 83.7 \| 91.6 \| 83.9 \| 90.2 \| 92.2 \| \| \| IF-Eval (Prompt Strict) \| 86.5 \| 84.3 \| 86.1 \| 84.8 \| - \| 83.3 \| \| \| GPQA-Diamond (Pass@1) \| 65.0 \| 49.9 \| 59.1 \| 60.0 \| 75.7 \| 71.5 \| \| \| SimpleQA (Correct) \| 28.4 \| 38.2 \| 24.9 \| 7.0 \| 47.0 \| 30.1 \| \| \| FRAMES (Acc.) \| 72.5 \| 80.5 \| 73.3 \| 76.9 \| - \| 82.5 \| \| \| AlpacaEval2.0 (LC-winrate) \| 52.0 \| 51.1 \| 70.0 \| 57.8 \| - \| 87.6 \| \| \| ArenaHard (GPT-4-1106) \| 85.2 \| 80.4 \| 85.5 \| 92.0 \| - \| 92.3 \| \| Code \| LiveCodeBench (Pass@1-COT) \| 33.8 \| 34.2 \| - \| 53.8 \| 63.4 \| 65.9 \| \| \| Codeforces (Percentile) \| 20.3 \| 23.6 \| 58.7 \| 93.4 \| 96.6 \| 96.3 \| \| \| Codeforces (Rating) \| 717 \| 759 \| 1134 \| 1820 \| 2061 \| 2029 \| \| \| SWE Verified (Resolved) \| 50.8 \| 38.8 \| 42.0 \| 41.6 \| 48.9 \| 49.2 \| \| \| Aider-Polyglot (Acc.) \| 45.3 \| 16.0 \| 49.6 \| 32.9 \| 61.7 \| 53.3 \| \| Math \| AIME 2024 (Pass@1) \| 16.0 \| 9.3 \| 39.2 \| 63.6 \| 79.2 \| 79.8 \| \| \| MATH-500 (Pass@1) \| 78.3 \| 74.6 \| 90.2 \| 90.0 \| 96.4 \| 97.3 \| \| \| CNMO 2024 (Pass@1) \| 13.1 \| 10.8 \| 43.2 \| 67.6 \| - \| 78.8 \| \| Chinese \| CLUEWSC (EM) \| 85.4 \| 87.9 \| 90.9 \| 89.9 \| - \| 92.8 \| \| \| C-Eval (EM) \| 76.7 \| 76.0 \| 86.5 \| 68.9 \| - \| 91.8 \| \| \| C-SimpleQA (Correct) \| 55.4 \| 58.7 \| 68.0 \| 40.3 \| - \| 63.7 \| </div> ### Distilled Model Evaluation <div align="center"> \| Model \| AIME 2024 pass@1 \| AIME 2024 cons@64 \| MATH-500 pass@1 \| GPQA Diamond pass@1 \| LiveCodeBench pass@1 \| CodeForces rating \| \|------------------------------------------\|------------------\|-------------------\|-----------------\|----------------------\|----------------------\|-------------------\| \| GPT-4o-0513 \| 9.3 \| 13.4 \| 74.6 \| 49.9 \| 32.9 \| 759 \| \| Claude-3.5-Sonnet-1022 \| 16.0 \| 26.7 \| 78.3 \| 65.0 \| 38.9 \| 717 \| \| o1-mini \| 63.6 \| 80.0 \| 90.0 \| 60.0 \| 53.8 \| 1820 \| \| QwQ-32B-Preview \| 44.0 \| 60.0 \| 90.6 \| 54.5 \| 41.9 \| 1316 \| \| DeepSeek-R1-Distill-Qwen-1.5B \| 28.9 \| 52.7 \| 83.9 \| 33.8 \| 16.9 \| 954 \| \| DeepSeek-R1-Distill-Qwen-7B \| 55.5 \| 83.3 \| 92.8 \| 49.1 \| 37.6 \| 1189 \| \| DeepSeek-R1-Distill-Qwen-14B \| 69.7 \| 80.0 \| 93.9 \| 59.1 \| 53.1 \| 1481 \| \| DeepSeek-R1-Distill-Qwen-32B \| 72.6 \| 83.3 \| 94.3 \| 62.1 \| 57.2 \| 1691 \| \| DeepSeek-R1-Distill-Llama-8B \| 50.4 \| 80.0 \| 89.1 \| 49.0 \| 39.6 \| 1205 \| \| DeepSeek-R1-Distill-Llama-70B \| 70.0 \| 86.7 \| 94.5 \| 65.2 \| 57.5 \| 1633 \| </div> ## 5. Chat Website & API Platform You can chat with DeepSeek-R1 on DeepSeek's official website: [chat.deepseek.com](https://chat.deepseek.com), and switch on the button "DeepThink" We also provide OpenAI-Compatible API at DeepSeek Platform: [platform.deepseek.com](https://platform.deepseek.com/) ## 6. How to Run Locally ### DeepSeek-R1 Models Please visit [DeepSeek-V3](https://github.com/deepseek-ai/DeepSeek-V3) repo for more information about running DeepSeek-R1 locally. NOTE: Hugging Face's Transformers has not been directly supported yet. ### DeepSeek-R1-Distill Models DeepSeek-R1-Distill models can be utilized in the same manner as Qwen or Llama models. For instance, you can easily start a service using [vLLM](https://github.com/vllm-project/vllm): ```shell vllm serve deepseek-ai/DeepSeek-R1-Distill-Qwen-32B --tensor-parallel-size 2 --max-model-len 32768 --enforce-eager ``` You can also easily start a service using [SGLang](https://github.com/sgl-project/sglang) ```bash python3 -m sglang.launch_server --model deepseek-ai/DeepSeek-R1-Distill-Qwen-32B --trust-remote-code --tp 2 ``` ### Usage Recommendations We recommend adhering to the following configurations when utilizing the DeepSeek-R1 series models, including benchmarking, to achieve the expected performance: 1. Set the temperature within the range of 0.5-0.7 (0.6 is recommended) to prevent endless repetitions or incoherent outputs. 2. Avoid adding a system prompt; all instructions should be contained within the user prompt. 3. For mathematical problems, it is advisable to include a directive in your prompt such as: "Please reason step by step, and put your final answer within \boxed{}." 4. When evaluating model performance, it is recommended to conduct multiple tests and average the results. Additionally, we have observed that the DeepSeek-R1 series models tend to bypass thinking pattern (i.e., outputting "\<think\>\n\n\</think\>") when responding to certain queries, which can adversely affect the model's performance. To ensure that the model engages in thorough reasoning, we recommend enforcing the model to initiate its response with "\<think\>\n" at the beginning of every output. ## 7. License This code repository and the model weights are licensed under the [MIT License](https://github.com/deepseek-ai/DeepSeek-R1/blob/main/LICENSE). DeepSeek-R1 series support commercial use, allow for any modifications and derivative works, including, but not limited to, distillation for training other LLMs. Please note that: - DeepSeek-R1-Distill-Qwen-1.5B, DeepSeek-R1-Distill-Qwen-7B, DeepSeek-R1-Distill-Qwen-14B and DeepSeek-R1-Distill-Qwen-32B are derived from [Qwen-2.5 series](https://github.com/QwenLM/Qwen2.5), which are originally licensed under [Apache 2.0 License](https://huggingface.co/Qwen/Qwen2.5-1.5B/blob/main/LICENSE), and now finetuned with 800k samples curated with DeepSeek-R1. - DeepSeek-R1-Distill-Llama-8B is derived from Llama3.1-8B-Base and is originally licensed under [llama3.1 license](https://huggingface.co/meta-llama/Llama-3.1-8B/blob/main/LICENSE). - DeepSeek-R1-Distill-Llama-70B is derived from Llama3.3-70B-Instruct and is originally licensed under [llama3.3 license](https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct/blob/main/LICENSE). ## 8. Citation ``` @misc{deepseekai2025deepseekr1incentivizingreasoningcapability, title={DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning}, author={DeepSeek-AI}, year={2025}, eprint={2501.12948}, archivePrefix={arXiv}, primaryClass={cs.CL}, url={https://arxiv.org/abs/2501.12948}, } ``` ## 9. Contact If you have any questions, please raise an issue or contact us at [[email protected]]([email protected]).
Mungert/EXAONE-Deep-7.8B-GGUF	Mungert	2025-06-15T19:41:09Z	1,344	5	transformers	[ "transformers", "gguf", "lg-ai", "exaone", "exaone-deep", "text-generation", "en", "ko", "arxiv:2503.12524", "base_model:LGAI-EXAONE/EXAONE-3.5-7.8B-Instruct", "base_model:finetune:LGAI-EXAONE/EXAONE-3.5-7.8B-Instruct", "license:other", "endpoints_compatible", "region:us", "imatrix", "conversational" ]	text-generation	2025-03-19T21:27:57Z	--- base_model: LGAI-EXAONE/EXAONE-3.5-7.8B-Instruct base_model_relation: finetune license: other license_name: exaone license_link: LICENSE language: - en - ko tags: - lg-ai - exaone - exaone-deep pipeline_tag: text-generation library_name: transformers --- # <span style="color: #7FFF7F;">EXAONE-Deep-7.8B GGUF Models</span> ## <span style="color: #7FFF7F;">Ultra-Low-Bit Quantization with IQ-DynamicGate (1-2 bit)</span> Our latest quantization method introduces precision-adaptive quantization for ultra-low-bit models (1-2 bit), with benchmark-proven improvements on Llama-3-8B. This approach uses layer-specific strategies to preserve accuracy while maintaining extreme memory efficiency. ### Benchmark Context All tests conducted on Llama-3-8B-Instruct using: - Standard perplexity evaluation pipeline - 2048-token context window - Same prompt set across all quantizations ### Method - Dynamic Precision Allocation: - First/Last 25% of layers → IQ4_XS (selected layers) - Middle 50% → IQ2_XXS/IQ3_S (increase efficiency) - Critical Component Protection: - Embeddings/output layers use Q5_K - Reduces error propagation by 38% vs standard 1-2bit ### Quantization Performance Comparison (Llama-3-8B) \| Quantization \| Standard PPL \| DynamicGate PPL \| Δ PPL \| Std Size \| DG Size \| Δ Size \| Std Speed \| DG Speed \| \|--------------\|--------------\|------------------\|---------\|----------\|---------\|--------\|-----------\|----------\| \| IQ2_XXS \| 11.30 \| 9.84 \| -12.9% \| 2.5G \| 2.6G \| +0.1G \| 234s \| 246s \| \| IQ2_XS \| 11.72 \| 11.63 \| -0.8% \| 2.7G \| 2.8G \| +0.1G \| 242s \| 246s \| \| IQ2_S \| 14.31 \| 9.02 \| -36.9% \| 2.7G \| 2.9G \| +0.2G \| 238s \| 244s \| \| IQ1_M \| 27.46 \| 15.41 \| -43.9% \| 2.2G \| 2.5G \| +0.3G \| 206s \| 212s \| \| IQ1_S \| 53.07 \| 32.00 \| -39.7% \| 2.1G \| 2.4G \| +0.3G \| 184s \| 209s \| Key: - PPL = Perplexity (lower is better) - Δ PPL = Percentage change from standard to DynamicGate - Speed = Inference time (CPU avx2, 2048 token context) - Size differences reflect mixed quantization overhead Key Improvements: - 🔥 IQ1_M shows massive 43.9% perplexity reduction (27.46 → 15.41) - 🚀 IQ2_S cuts perplexity by 36.9% while adding only 0.2GB - ⚡ IQ1_S maintains 39.7% better accuracy despite 1-bit quantization Tradeoffs: - All variants have modest size increases (0.1-0.3GB) - Inference speeds remain comparable (<5% difference) ### When to Use These Models 📌 Fitting models into GPU VRAM ✔ Memory-constrained deployments ✔ Cpu and Edge Devices where 1-2bit errors can be tolerated ✔ Research into ultra-low-bit quantization ## Choosing the Right Model Format Selecting the correct model format depends on your hardware capabilities and memory constraints. ### BF16 (Brain Float 16) – Use if BF16 acceleration is available - A 16-bit floating-point format designed for faster computation while retaining good precision. - Provides similar dynamic range as FP32 but with lower memory usage. - Recommended if your hardware supports BF16 acceleration (check your device's specs). - Ideal for high-performance inference with reduced memory footprint compared to FP32. 📌 Use BF16 if: ✔ Your hardware has native BF16 support (e.g., newer GPUs, TPUs). ✔ You want higher precision while saving memory. ✔ You plan to requantize the model into another format. 📌 Avoid BF16 if: ❌ Your hardware does not support BF16 (it may fall back to FP32 and run slower). ❌ You need compatibility with older devices that lack BF16 optimization. --- ### F16 (Float 16) – More widely supported than BF16 - A 16-bit floating-point high precision but with less of range of values than BF16. - Works on most devices with FP16 acceleration support (including many GPUs and some CPUs). - Slightly lower numerical precision than BF16 but generally sufficient for inference. 📌 Use F16 if: ✔ Your hardware supports FP16 but not BF16. ✔ You need a balance between speed, memory usage, and accuracy. ✔ You are running on a GPU or another device optimized for FP16 computations. 📌 Avoid F16 if: ❌ Your device lacks native FP16 support (it may run slower than expected). ❌ You have memory limitations. --- ### Quantized Models (Q4_K, Q6_K, Q8, etc.) – For CPU & Low-VRAM Inference Quantization reduces model size and memory usage while maintaining as much accuracy as possible. - Lower-bit models (Q4_K) → Best for minimal memory usage, may have lower precision. - Higher-bit models (Q6_K, Q8_0) → Better accuracy, requires more memory. 📌 Use Quantized Models if: ✔ You are running inference on a CPU and need an optimized model. ✔ Your device has low VRAM and cannot load full-precision models. ✔ You want to reduce memory footprint while keeping reasonable accuracy. 📌 Avoid Quantized Models if: ❌ You need maximum accuracy (full-precision models are better for this). ❌ Your hardware has enough VRAM for higher-precision formats (BF16/F16). --- ### Very Low-Bit Quantization (IQ3_XS, IQ3_S, IQ3_M, Q4_K, Q4_0) These models are optimized for extreme memory efficiency, making them ideal for low-power devices or large-scale deployments where memory is a critical constraint. - IQ3_XS: Ultra-low-bit quantization (3-bit) with extreme memory efficiency. - Use case: Best for ultra-low-memory devices where even Q4_K is too large. - Trade-off: Lower accuracy compared to higher-bit quantizations. - IQ3_S: Small block size for maximum memory efficiency. - Use case: Best for low-memory devices where IQ3_XS is too aggressive. - IQ3_M: Medium block size for better accuracy than IQ3_S. - Use case: Suitable for low-memory devices where IQ3_S is too limiting. - Q4_K: 4-bit quantization with block-wise optimization for better accuracy. - Use case: Best for low-memory devices where Q6_K is too large. - Q4_0: Pure 4-bit quantization, optimized for ARM devices. - Use case: Best for ARM-based devices or low-memory environments. --- ### Summary Table: Model Format Selection \| Model Format \| Precision \| Memory Usage \| Device Requirements \| Best Use Case \| \|--------------\|------------\|---------------\|----------------------\|---------------\| \| BF16 \| Highest \| High \| BF16-supported GPU/CPUs \| High-speed inference with reduced memory \| \| F16 \| High \| High \| FP16-supported devices \| GPU inference when BF16 isn't available \| \| Q4_K \| Medium Low \| Low \| CPU or Low-VRAM devices \| Best for memory-constrained environments \| \| Q6_K \| Medium \| Moderate \| CPU with more memory \| Better accuracy while still being quantized \| \| Q8_0 \| High \| Moderate \| CPU or GPU with enough VRAM \| Best accuracy among quantized models \| \| IQ3_XS \| Very Low \| Very Low \| Ultra-low-memory devices \| Extreme memory efficiency and low accuracy \| \| Q4_0 \| Low \| Low \| ARM or low-memory devices \| llama.cpp can optimize for ARM devices \| --- ## Included Files & Details ### `EXAONE-Deep-7.8B-bf16.gguf` - Model weights preserved in BF16. - Use this if you want to requantize the model into a different format. - Best if your device supports BF16 acceleration. ### `EXAONE-Deep-7.8B-f16.gguf` - Model weights stored in F16. - Use if your device supports FP16, especially if BF16 is not available. ### `EXAONE-Deep-7.8B-bf16-q8_0.gguf` - Output & embeddings remain in BF16. - All other layers quantized to Q8_0. - Use if your device supports BF16 and you want a quantized version. ### `EXAONE-Deep-7.8B-f16-q8_0.gguf` - Output & embeddings remain in F16. - All other layers quantized to Q8_0. ### `EXAONE-Deep-7.8B-q4_k.gguf` - Output & embeddings quantized to Q8_0. - All other layers quantized to Q4_K. - Good for CPU inference with limited memory. ### `EXAONE-Deep-7.8B-q4_k_s.gguf` - Smallest Q4_K variant, using less memory at the cost of accuracy. - Best for very low-memory setups. ### `EXAONE-Deep-7.8B-q6_k.gguf` - Output & embeddings quantized to Q8_0. - All other layers quantized to Q6_K . ### `EXAONE-Deep-7.8B-q8_0.gguf` - Fully Q8 quantized model for better accuracy. - Requires more memory but offers higher precision. ### `EXAONE-Deep-7.8B-iq3_xs.gguf` - IQ3_XS quantization, optimized for extreme memory efficiency. - Best for ultra-low-memory devices. ### `EXAONE-Deep-7.8B-iq3_m.gguf` - IQ3_M quantization, offering a medium block size for better accuracy. - Suitable for low-memory devices. ### `EXAONE-Deep-7.8B-q4_0.gguf` - Pure Q4_0 quantization, optimized for ARM devices. - Best for low-memory environments. - Prefer IQ4_NL for better accuracy. # <span id="testllm" style="color: #7F7FFF;">🚀 If you find these models useful</span> ❤ Please click "Like" if you find this useful! Help me test my AI-Powered Network Monitor Assistant with quantum-ready security checks: 👉 [Quantum Network Monitor](https://readyforquantum.com) 💬 How to test: 1. Click the chat icon (bottom right on any page) 2. Choose an AI assistant type: - `TurboLLM` (GPT-4-mini) - `FreeLLM` (Open-source) - `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 scans - Quantum-readiness checks - Metasploit integration 🟡 TestLLM – Current experimental model (llama.cpp on 6 CPU threads): - ✅ Zero-configuration setup - ⏳ 30s load time (slow inference but no API costs) - 🔧 Help wanted! If you’re into edge-device AI, let’s collaborate! ### Other Assistants 🟢 TurboLLM – Uses gpt-4-mini for: - Real-time network diagnostics - Automated penetration testing (Nmap/Metasploit) - 🔑 Get more tokens by [downloading our Quantum Network Monitor Agent](https://readyforquantum.com/download/?utm_source=huggingface&utm_medium=referral&utm_campaign=huggingface_repo_readme) 🔵 HugLLM – Open-source models (≈8B params): - 2x more tokens than TurboLLM - AI-powered log analysis - 🌐 Runs on Hugging Face Inference API ### 💡 Example AI Commands to 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 quick Nmap vulnerability test"` 4. '"Create a cmd processor to .. (what ever you want)" Note you need to install a Quantum Network Monitor Agent to run the .net code from. This is a very flexible and powerful feature. Use with caution! ### Final word I fund the servers to create the models files, run the Quantum Network Monitor Service and Pay for Inference from Novita and OpenAI all from my own pocket. All of the code for creating the models and the work I have done with Quantum Network Monitor is [open source](https://github.com/Mungert69). Feel free to use what you find useful. Please support my work and consider [buying me a coffee](https://www.buymeacoffee.com/mahadeva) . This will help me pay for the services and increase the token limits for everyone. Thank you :) # EXAONE-Deep-7.8B ## Introduction We introduce EXAONE Deep, which exhibits superior capabilities in various reasoning tasks including math and coding benchmarks, ranging from 2.4B to 32B parameters developed and released by LG AI Research. Evaluation results show that 1) EXAONE Deep 2.4B outperforms other models of comparable size, 2) EXAONE Deep 7.8B outperforms not only open-weight models of comparable scale but also a proprietary reasoning model OpenAI o1-mini, and 3) EXAONE Deep 32B demonstrates competitive performance against leading open-weight models. For more details, please refer to our [documentation](https://arxiv.org/abs/2503.12524), [blog](https://www.lgresearch.ai/news/view?seq=543) and [GitHub](https://github.com/LG-AI-EXAONE/EXAONE-Deep). <p align="center"> <img src="assets/exaone_deep_overall_performance.png", width="100%", style="margin: 40 auto;"> This repository contains the reasoning 7.8B language model with the following features: - Number of Parameters (without embeddings): 6.98B - Number of Layers: 32 - Number of Attention Heads: GQA with 32 Q-heads and 8 KV-heads - Vocab Size: 102,400 - Context Length: 32,768 tokens ## Quickstart We recommend to use `transformers` v4.43.1 or later. Here is the code snippet to run conversational inference with the model: ```python import torch from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer from threading import Thread model_name = "LGAI-EXAONE/EXAONE-Deep-7.8B" streaming = True # choose the streaming option model = AutoModelForCausalLM.from_pretrained( model_name, torch_dtype=torch.bfloat16, trust_remote_code=True, device_map="auto" ) tokenizer = AutoTokenizer.from_pretrained(model_name) # Choose your prompt: # Math example (AIME 2024) prompt = r"""Let $x,y$ and $z$ be positive real numbers that satisfy the following system of equations: \[\log_2\left({x \over yz}\right) = {1 \over 2}\]\[\log_2\left({y \over xz}\right) = {1 \over 3}\]\[\log_2\left({z \over xy}\right) = {1 \over 4}\] Then the value of $\left\|\log_2(x^4y^3z^2)\right\|$ is $\tfrac{m}{n}$ where $m$ and $n$ are relatively prime positive integers. Find $m+n$. Please reason step by step, and put your final answer within \boxed{}.""" # Korean MCQA example (CSAT Math 2025) prompt = r"""Question : $a_1 = 2$인 수열 $\{a_n\}$과 $b_1 = 2$인 등차수열 $\{b_n\}$이 모든 자연수 $n$에 대하여\[\sum_{k=1}^{n} \frac{a_k}{b_{k+1}} = \frac{1}{2} n^2\]을 만족시킬 때, $\sum_{k=1}^{5} a_k$의 값을 구하여라. Options : A) 120 B) 125 C) 130 D) 135 E) 140 Please reason step by step, and you should write the correct option alphabet (A, B, C, D or E) within \\boxed{}.""" messages = [ {"role": "user", "content": prompt} ] input_ids = tokenizer.apply_chat_template( messages, tokenize=True, add_generation_prompt=True, return_tensors="pt" ) if streaming: streamer = TextIteratorStreamer(tokenizer) thread = Thread(target=model.generate, kwargs=dict( input_ids=input_ids.to("cuda"), eos_token_id=tokenizer.eos_token_id, max_new_tokens=32768, do_sample=True, temperature=0.6, top_p=0.95, streamer=streamer )) thread.start() for text in streamer: print(text, end="", flush=True) else: output = model.generate( input_ids.to("cuda"), eos_token_id=tokenizer.eos_token_id, max_new_tokens=32768, do_sample=True, temperature=0.6, top_p=0.95, ) print(tokenizer.decode(output[0])) ``` > ### Note > The EXAONE Deep models are trained with an optimized configuration, > so we recommend following the [Usage Guideline](#usage-guideline) section to achieve optimal performance. ## Evaluation The following table shows the evaluation results of reasoning tasks such as math and coding. The full evaluation results can be found in the [documentation](https://arxiv.org/abs/2503.12524). <table> <tr> <th>Models</th> <th>MATH-500 (pass@1)</th> <th>AIME 2024 (pass@1 / cons@64)</th> <th>AIME 2025 (pass@1 / cons@64)</th> <th>CSAT Math 2025 (pass@1)</th> <th>GPQA Diamond (pass@1)</th> <th>Live Code Bench (pass@1)</th> </tr> <tr> <td>EXAONE Deep 32B</td> <td>95.7</td> <td>72.1 / <strong>90.0</strong></td> <td>65.8 / <strong>80.0</strong></td> <td><strong>94.5</strong></td> <td>66.1</td> <td>59.5</td> </tr> <tr> <td>DeepSeek-R1-Distill-Qwen-32B</td> <td>94.3</td> <td>72.6 / 83.3</td> <td>55.2 / 73.3</td> <td>84.1</td> <td>62.1</td> <td>57.2</td> </tr> <tr> <td>QwQ-32B</td> <td>95.5</td> <td>79.5 / 86.7</td> <td><strong>67.1</strong> / 76.7</td> <td>94.4</td> <td>63.3</td> <td>63.4</td> </tr> <tr> <td>DeepSeek-R1-Distill-Llama-70B</td> <td>94.5</td> <td>70.0 / 86.7</td> <td>53.9 / 66.7</td> <td>88.8</td> <td>65.2</td> <td>57.5</td> </tr> <tr> <td>DeepSeek-R1 (671B)</td> <td><strong>97.3</strong></td> <td><strong>79.8</strong> / 86.7</td> <td>66.8 / <strong>80.0</strong></td> <td>89.9</td> <td><strong>71.5</strong></td> <td><strong>65.9</strong></td> </tr> <tr> <th colspan="7" height="30px"></th> </tr> <tr> <td>EXAONE Deep 7.8B</td> <td><strong>94.8</strong></td> <td><strong>70.0</strong> / <strong>83.3</strong></td> <td><strong>59.6</strong> / <strong>76.7</strong></td> <td><strong>89.9</strong></td> <td><strong>62.6</strong></td> <td><strong>55.2</strong></td> </tr> <tr> <td>DeepSeek-R1-Distill-Qwen-7B</td> <td>92.8</td> <td>55.5 / <strong>83.3</strong></td> <td>38.5 / 56.7</td> <td>79.7</td> <td>49.1</td> <td>37.6</td> </tr> <tr> <td>DeepSeek-R1-Distill-Llama-8B</td> <td>89.1</td> <td>50.4 / 80.0</td> <td>33.6 / 53.3</td> <td>74.1</td> <td>49.0</td> <td>39.6</td> </tr> <tr> <td>OpenAI o1-mini</td> <td>90.0</td> <td>63.6 / 80.0</td> <td>54.8 / 66.7</td> <td>84.4</td> <td>60.0</td> <td>53.8</td> </tr> <tr> <th colspan="7" height="30px"></th> </tr> <tr> <td>EXAONE Deep 2.4B</td> <td><strong>92.3</strong></td> <td><strong>52.5</strong> / <strong>76.7</strong></td> <td><strong>47.9</strong> / <strong>73.3</strong></td> <td><strong>79.2</strong></td> <td><strong>54.3</strong></td> <td><strong>46.6</strong></td> </tr> <tr> <td>DeepSeek-R1-Distill-Qwen-1.5B</td> <td>83.9</td> <td>28.9 / 52.7</td> <td>23.9 / 36.7</td> <td>65.6</td> <td>33.8</td> <td>16.9</td> </tr> </table> ## Deployment EXAONE Deep models can be inferred in the various frameworks, such as: - `TensorRT-LLM` - `vLLM` - `SGLang` - `llama.cpp` - `Ollama` - `LM-Studio` Please refer to our [EXAONE Deep GitHub](https://github.com/LG-AI-EXAONE/EXAONE-Deep) for more details about the inference frameworks. ## Quantization We provide the pre-quantized EXAONE Deep models with AWQ and several quantization types in GGUF format. Please refer to our [EXAONE Deep collection](https://huggingface.co/collections/LGAI-EXAONE/exaone-deep-67d119918816ec6efa79a4aa) to find corresponding quantized models. ## Usage Guideline To achieve the expected performance, we recommend using the following configurations: 1. Ensure the model starts with `<thought>\n` for reasoning steps. The model's output quality may be degraded when you omit it. You can easily apply this feature by using `tokenizer.apply_chat_template()` with `add_generation_prompt=True`. Please check the example code on [Quickstart](#quickstart) section. 2. The reasoning steps of EXAONE Deep models enclosed by `<thought>\n...\n</thought>` usually have lots of tokens, so previous reasoning steps may be necessary to be removed in multi-turn situation. The provided tokenizer handles this automatically. 3. Avoid using system prompt, and build the instruction on the user prompt. 4. Additional instructions help the models reason more deeply, so that the models generate better output. - For math problems, the instructions "Please reason step by step, and put your final answer within \boxed{}." are helpful. - For more information on our evaluation setting including prompts, please refer to our [Documentation](https://arxiv.org/abs/2503.12524). 5. In our evaluation, we use `temperature=0.6` and `top_p=0.95` for generation. 6. When evaluating the models, it is recommended to test multiple times to assess the expected performance accurately. ## Limitation The EXAONE language model has certain limitations and may occasionally generate inappropriate responses. The language model generates responses based on the output probability of tokens, and it is determined during learning from training data. While we have made every effort to exclude personal, harmful, and biased information from the training data, some problematic content may still be included, potentially leading to undesirable responses. Please note that the text generated by EXAONE language model does not reflects the views of LG AI Research. - Inappropriate answers may be generated, which contain personal, harmful or other inappropriate information. - Biased responses may be generated, which are associated with age, gender, race, and so on. - The generated responses rely heavily on statistics from the training data, which can result in the generation of semantically or syntactically incorrect sentences. - Since the model does not reflect the latest information, the responses may be false or contradictory. LG AI Research strives to reduce potential risks that may arise from EXAONE language models. Users are not allowed to engage in any malicious activities (e.g., keying in illegal information) that may induce the creation of inappropriate outputs violating LG AI’s ethical principles when using EXAONE language models. ## License The model is licensed under [EXAONE AI Model License Agreement 1.1 - NC](./LICENSE) ## Citation ``` @article{exaone-deep, title={EXAONE Deep: Reasoning Enhanced Language Models}, author={{LG AI Research}}, journal={arXiv preprint arXiv:2503.12524}, year={2025} } ``` ## Contact LG AI Research Technical Support: [email protected]
Mungert/DeepHermes-3-Llama-3-8B-Preview-GGUF	Mungert	2025-06-15T19:40:29Z	1,885	5	transformers	[ "transformers", "gguf", "Llama-3", "instruct", "finetune", "chatml", "gpt4", "synthetic data", "distillation", "function calling", "json mode", "axolotl", "roleplaying", "chat", "reasoning", "r1", "vllm", "en", "base_model:meta-llama/Llama-3.1-8B", "base_model:quantized:meta-llama/Llama-3.1-8B", "license:llama3", "endpoints_compatible", "region:us", "imatrix", "conversational" ]	null	2025-03-17T14:30:06Z	--- language: - en license: llama3 tags: - Llama-3 - instruct - finetune - chatml - gpt4 - synthetic data - distillation - function calling - json mode - axolotl - roleplaying - chat - reasoning - r1 - vllm base_model: meta-llama/Meta-Llama-3.1-8B widget: - example_title: Hermes 3 messages: - role: system content: >- You are a sentient, superintelligent artificial general intelligence, here to teach and assist me. - role: user content: What is the meaning of life? model-index: - name: DeepHermes-3-Llama-3.1-8B results: [] library_name: transformers --- # <span style="color: #7FFF7F;">DeepHermes-3-Llama-3-8B-Preview GGUF Models</span> ## <span style="color: #7FFF7F;">Ultra-Low-Bit Quantization with IQ-DynamicGate (1-2 bit)</span> Our latest quantization method introduces precision-adaptive quantization for ultra-low-bit models (1-2 bit), with benchmark-proven improvements on Llama-3-8B. This approach uses layer-specific strategies to preserve accuracy while maintaining extreme memory efficiency. ### Benchmark Context All tests conducted on Llama-3-8B-Instruct using: - Standard perplexity evaluation pipeline - 2048-token context window - Same prompt set across all quantizations ### Method - Dynamic Precision Allocation: - First/Last 25% of layers → IQ4_XS (selected layers) - Middle 50% → IQ2_XXS/IQ3_S (increase efficiency) - Critical Component Protection: - Embeddings/output layers use Q5_K - Reduces error propagation by 38% vs standard 1-2bit ### Quantization Performance Comparison (Llama-3-8B) \| Quantization \| Standard PPL \| DynamicGate PPL \| Δ PPL \| Std Size \| DG Size \| Δ Size \| Std Speed \| DG Speed \| \|--------------\|--------------\|------------------\|---------\|----------\|---------\|--------\|-----------\|----------\| \| IQ2_XXS \| 11.30 \| 9.84 \| -12.9% \| 2.5G \| 2.6G \| +0.1G \| 234s \| 246s \| \| IQ2_XS \| 11.72 \| 11.63 \| -0.8% \| 2.7G \| 2.8G \| +0.1G \| 242s \| 246s \| \| IQ2_S \| 14.31 \| 9.02 \| -36.9% \| 2.7G \| 2.9G \| +0.2G \| 238s \| 244s \| \| IQ1_M \| 27.46 \| 15.41 \| -43.9% \| 2.2G \| 2.5G \| +0.3G \| 206s \| 212s \| \| IQ1_S \| 53.07 \| 32.00 \| -39.7% \| 2.1G \| 2.4G \| +0.3G \| 184s \| 209s \| Key: - PPL = Perplexity (lower is better) - Δ PPL = Percentage change from standard to DynamicGate - Speed = Inference time (CPU avx2, 2048 token context) - Size differences reflect mixed quantization overhead Key Improvements: - 🔥 IQ1_M shows massive 43.9% perplexity reduction (27.46 → 15.41) - 🚀 IQ2_S cuts perplexity by 36.9% while adding only 0.2GB - ⚡ IQ1_S maintains 39.7% better accuracy despite 1-bit quantization Tradeoffs: - All variants have modest size increases (0.1-0.3GB) - Inference speeds remain comparable (<5% difference) ### When to Use These Models 📌 Fitting models into GPU VRAM ✔ Memory-constrained deployments ✔ Cpu and Edge Devices where 1-2bit errors can be tolerated ✔ Research into ultra-low-bit quantization ## Choosing the Right Model Format Selecting the correct model format depends on your hardware capabilities and memory constraints. ### BF16 (Brain Float 16) – Use if BF16 acceleration is available - A 16-bit floating-point format designed for faster computation while retaining good precision. - Provides similar dynamic range as FP32 but with lower memory usage. - Recommended if your hardware supports BF16 acceleration (check your device's specs). - Ideal for high-performance inference with reduced memory footprint compared to FP32. 📌 Use BF16 if: ✔ Your hardware has native BF16 support (e.g., newer GPUs, TPUs). ✔ You want higher precision while saving memory. ✔ You plan to requantize the model into another format. 📌 Avoid BF16 if: ❌ Your hardware does not support BF16 (it may fall back to FP32 and run slower). ❌ You need compatibility with older devices that lack BF16 optimization. --- ### F16 (Float 16) – More widely supported than BF16 - A 16-bit floating-point high precision but with less of range of values than BF16. - Works on most devices with FP16 acceleration support (including many GPUs and some CPUs). - Slightly lower numerical precision than BF16 but generally sufficient for inference. 📌 Use F16 if: ✔ Your hardware supports FP16 but not BF16. ✔ You need a balance between speed, memory usage, and accuracy. ✔ You are running on a GPU or another device optimized for FP16 computations. 📌 Avoid F16 if: ❌ Your device lacks native FP16 support (it may run slower than expected). ❌ You have memory limitations. --- ### Quantized Models (Q4_K, Q6_K, Q8, etc.) – For CPU & Low-VRAM Inference Quantization reduces model size and memory usage while maintaining as much accuracy as possible. - Lower-bit models (Q4_K) → Best for minimal memory usage, may have lower precision. - Higher-bit models (Q6_K, Q8_0) → Better accuracy, requires more memory. 📌 Use Quantized Models if: ✔ You are running inference on a CPU and need an optimized model. ✔ Your device has low VRAM and cannot load full-precision models. ✔ You want to reduce memory footprint while keeping reasonable accuracy. 📌 Avoid Quantized Models if: ❌ You need maximum accuracy (full-precision models are better for this). ❌ Your hardware has enough VRAM for higher-precision formats (BF16/F16). --- ### Very Low-Bit Quantization (IQ3_XS, IQ3_S, IQ3_M, Q4_K, Q4_0) These models are optimized for extreme memory efficiency, making them ideal for low-power devices or large-scale deployments where memory is a critical constraint. - IQ3_XS: Ultra-low-bit quantization (3-bit) with extreme memory efficiency. - Use case: Best for ultra-low-memory devices where even Q4_K is too large. - Trade-off: Lower accuracy compared to higher-bit quantizations. - IQ3_S: Small block size for maximum memory efficiency. - Use case: Best for low-memory devices where IQ3_XS is too aggressive. - IQ3_M: Medium block size for better accuracy than IQ3_S. - Use case: Suitable for low-memory devices where IQ3_S is too limiting. - Q4_K: 4-bit quantization with block-wise optimization for better accuracy. - Use case: Best for low-memory devices where Q6_K is too large. - Q4_0: Pure 4-bit quantization, optimized for ARM devices. - Use case: Best for ARM-based devices or low-memory environments. --- ### Summary Table: Model Format Selection \| Model Format \| Precision \| Memory Usage \| Device Requirements \| Best Use Case \| \|--------------\|------------\|---------------\|----------------------\|---------------\| \| BF16 \| Highest \| High \| BF16-supported GPU/CPUs \| High-speed inference with reduced memory \| \| F16 \| High \| High \| FP16-supported devices \| GPU inference when BF16 isn't available \| \| Q4_K \| Medium Low \| Low \| CPU or Low-VRAM devices \| Best for memory-constrained environments \| \| Q6_K \| Medium \| Moderate \| CPU with more memory \| Better accuracy while still being quantized \| \| Q8_0 \| High \| Moderate \| CPU or GPU with enough VRAM \| Best accuracy among quantized models \| \| IQ3_XS \| Very Low \| Very Low \| Ultra-low-memory devices \| Extreme memory efficiency and low accuracy \| \| Q4_0 \| Low \| Low \| ARM or low-memory devices \| llama.cpp can optimize for ARM devices \| --- ## Included Files & Details ### `DeepHermes-3-Llama-3-8B-Preview-bf16.gguf` - Model weights preserved in BF16. - Use this if you want to requantize the model into a different format. - Best if your device supports BF16 acceleration. ### `DeepHermes-3-Llama-3-8B-Preview-f16.gguf` - Model weights stored in F16. - Use if your device supports FP16, especially if BF16 is not available. ### `DeepHermes-3-Llama-3-8B-Preview-bf16-q8_0.gguf` - Output & embeddings remain in BF16. - All other layers quantized to Q8_0. - Use if your device supports BF16 and you want a quantized version. ### `DeepHermes-3-Llama-3-8B-Preview-f16-q8_0.gguf` - Output & embeddings remain in F16. - All other layers quantized to Q8_0. ### `DeepHermes-3-Llama-3-8B-Preview-q4_k.gguf` - Output & embeddings quantized to Q8_0. - All other layers quantized to Q4_K. - Good for CPU inference with limited memory. ### `DeepHermes-3-Llama-3-8B-Preview-q4_k_s.gguf` - Smallest Q4_K variant, using less memory at the cost of accuracy. - Best for very low-memory setups. ### `DeepHermes-3-Llama-3-8B-Preview-q6_k.gguf` - Output & embeddings quantized to Q8_0. - All other layers quantized to Q6_K . ### `DeepHermes-3-Llama-3-8B-Preview-q8_0.gguf` - Fully Q8 quantized model for better accuracy. - Requires more memory but offers higher precision. ### `DeepHermes-3-Llama-3-8B-Preview-iq3_xs.gguf` - IQ3_XS quantization, optimized for extreme memory efficiency. - Best for ultra-low-memory devices. ### `DeepHermes-3-Llama-3-8B-Preview-iq3_m.gguf` - IQ3_M quantization, offering a medium block size for better accuracy. - Suitable for low-memory devices. ### `DeepHermes-3-Llama-3-8B-Preview-q4_0.gguf` - Pure Q4_0 quantization, optimized for ARM devices. - Best for low-memory environments. - Prefer IQ4_NL for better accuracy. # <span id="testllm" style="color: #7F7FFF;">🚀 If you find these models useful</span> ❤ Please click "Like" if you find this useful! Help me test my AI-Powered Network Monitor Assistant with quantum-ready security checks: 👉 [Quantum Network Monitor](https://readyforquantum.com/dashboard) 💬 How to test: 1. Click the chat icon (bottom right on any page) 2. Choose an AI assistant type: - `TurboLLM` (GPT-4-mini) - `FreeLLM` (Open-source) - `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 scans - Quantum-readiness checks - Metasploit integration 🟡 TestLLM – Current experimental model (llama.cpp on 6 CPU threads): - ✅ Zero-configuration setup - ⏳ 30s load time (slow inference but no API costs) - 🔧 Help wanted! If you’re into edge-device AI, let’s collaborate! ### Other Assistants 🟢 TurboLLM – Uses gpt-4-mini for: - Real-time network diagnostics - Automated penetration testing (Nmap/Metasploit) - 🔑 Get more tokens by [downloading our Quantum Network Monitor Agent](https://readyforquantum.com/download/?utm_source=huggingface&utm_medium=referral&utm_campaign=huggingface_repo_readme) 🔵 HugLLM – Open-source models (≈8B params): - 2x more tokens than TurboLLM - AI-powered log analysis - 🌐 Runs on Hugging Face Inference API ### 💡 Example AI Commands to 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 quick Nmap vulnerability test"` 4. '"Create a cmd processor to .. (what ever you want)" Note you need to install a Quantum Network Monitor Agent to run the .net code from. This is a very flexible and powerful feature. Use with caution! ### Final word I fund the servers to create the models files, run the Quantum Network Monitor Service and Pay for Inference from Novita and OpenAI all from my own pocket. All of the code for creating the models and the work I have done with Quantum Network Monitor is [open source](https://github.com/Mungert69). Feel free to use what you find useful. Please support my work and consider [buying me a coffee](https://www.buymeacoffee.com/mahadeva) . This will help me pay for the services and increase the token limits for everyone. Thank you :) # DeepHermes 3 - Llama-3.1 8B ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/9fxlaDxteqe3SasZ7_06_.jpeg) ## Model Description DeepHermes 3 Preview is the latest version of our flagship Hermes series of LLMs by Nous Research, and one of the first models in the world to unify Reasoning (long chains of thought that improve answer accuracy) and normal LLM response modes into one model. We have also improved LLM annotation, judgement, and function calling. DeepHermes 3 Preview is one of the first LLM models to unify both "intuitive", traditional mode responses and long chain of thought reasoning responses into a single model, toggled by a system prompt. Hermes 3, the predecessor of DeepHermes 3, is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coherence, and improvements across the board. The ethos of the Hermes series of models is focused on aligning LLMs to the user, with powerful steering capabilities and control given to the end user. This is a preview Hermes with early reasoning capabilities, distilled from R1 across a variety of tasks that benefit from reasoning and objectivity. Some quirks may be discovered! Please let us know any interesting findings or issues you discover! ## Note: To toggle REASONING ON, you must use the following system prompt: ``` You are a deep thinking AI, you may use extremely long chains of thought to deeply consider the problem and deliberate with yourself via systematic reasoning processes to help come to a correct solution prior to answering. You should enclose your thoughts and internal monologue inside <think> </think> tags, and then provide your solution or response to the problem. ``` # Nous API This model is also available on our new API product - Check out the API and sign up for the waitlist here: https://portal.nousresearch.com/ # Example Outputs: ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/_giUevm1IjPFWiypG0zd4.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/bAI0HG2cFA_o1hTFIfCr_.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/FmOIB7fjXKVHfs94DJPwn.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/tfL1jeGXvv7xTAULFQgqs.png) # Benchmarks ## Benchmarks for Reasoning Mode on vs off: ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/O_sgWq4CVPuxuKYqHWkkN.png) Reasoning ON benchmarks aquired by running HuggingFace's open-r1 reasoning mode evaluation suite, and scores for reasoning mode OFF aquired by running LM-Eval-Harness Benchmark Suite Upper bound determined by measuring the % gained over Hermes 3 3 & 70b by MATH_VERIFY compared to eleuther eval harness, which ranged betweeen 33% and 50% gain in MATH Hard benchmark on retested models by them compared to eval harness reported scores ## Benchmarks in Non-Reasoning Mode against Llama-3.1-8B-Instruct ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/hZCJa8g8smOS9BcQSXAd1.png) # Prompt Format DeepHermes 3 now uses Llama-Chat format as the prompt format, opening up a more unified, structured system for engaging the LLM in multi-turn chat dialogue. System prompts allow steerability and interesting new ways to interact with an LLM, guiding rules, roles, and stylistic choices of the model. ## Deep Thinking Mode - Deep Hermes Preview can activate long chain of thought with a system prompt. ``` You are a deep thinking AI, you may use extremely long chains of thought to deeply consider the problem and deliberate with yourself via systematic reasoning processes to help come to a correct solution prior to answering. You should enclose your thoughts and internal monologue inside <think> </think> tags, and then provide your solution or response to the problem. ``` For an example of using deep reasoning mode with HuggingFace Transformers: ```python import torch from transformers import AutoTokenizer, AutoModelForCausalLM import flash_attn import time tokenizer = AutoTokenizer.from_pretrained("NousResearch/DeepHermes-3-Llama-3-8B-Preview") model = AutoModelForCausalLM.from_pretrained( "NousResearch/DeepHermes-3-Llama-3-8B-Preview", torch_dtype=torch.float16, device_map="auto", attn_implementation="flash_attention_2", ) messages = [ { "role": "system", "content": "You are a deep thinking AI, you may use extremely long chains of thought to deeply consider the problem and deliberate with yourself via systematic reasoning processes to help come to a correct solution prior to answering. You should enclose your thoughts and internal monologue inside <think> </think> tags, and then provide your solution or response to the problem." }, { "role": "user", "content": "What is y if y=22-4+(32)" } ] input_ids = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors='pt').to("cuda") generated_ids = model.generate(input_ids, max_new_tokens=2500, temperature=0.8, repetition_penalty=1.1, do_sample=True, eos_token_id=tokenizer.eos_token_id) print(f"Generated Tokens: {generated_ids.shape[-1:]}") response = tokenizer.decode(generated_ids[0], skip_special_tokens=True, clean_up_tokenization_space=True) print(f"Response: {response}") ``` Please note, for difficult problems DeepHermes can think using as many as 13,000 tokens. You may need to increase `max_new_tokens` to be much larger than 2500 for difficult problems. ## Standard "Intuitive" Response Mode Prompt with system instruction (Use whatever system prompt you like, this is just an example!): ```python import torch from transformers import AutoTokenizer, AutoModelForCausalLM import flash_attn import time tokenizer = AutoTokenizer.from_pretrained("NousResearch/DeepHermes-3-Llama-3-8B-Preview") model = AutoModelForCausalLM.from_pretrained( "NousResearch/DeepHermes-3-Llama-3-8B-Preview", torch_dtype=torch.float16, device_map="auto", attn_implementation="flash_attention_2", ) messages = [ { "role": "system", "content": "You are Hermes, an AI assistant" }, { "role": "user", "content": "What are the most interesting things to do in Paris?" } ] input_ids = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors='pt').to("cuda") generated_ids = model.generate(input_ids, max_new_tokens=2500, temperature=0.8, repetition_penalty=1.1, do_sample=True, eos_token_id=tokenizer.eos_token_id) print(f"Generated Tokens: {generated_ids.shape[-1:]}") response = tokenizer.decode(generated_ids[0], skip_special_tokens=True, clean_up_tokenization_space=True) print(f"Response: {response}") ``` ## VLLM Inference You can also run this model with vLLM, by running the following in your terminal after `pip install vllm` `vllm serve NousResearch/DeepHermes-3-Llama-3-8B-Preview` You may then use the model over API using the OpenAI library just like you would call OpenAI's API. ## Prompt Format for Function Calling Our model was trained on specific system prompts and structures for Function Calling. You should use the system role with this message, followed by a function signature json as this example shows here. ``` <\|start_header_id\|>system<\|end_header_id\|> You are a function calling AI model. You are provided with function signatures within <tools></tools> XML tags. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions. Here are the available tools: <tools> {"type": "function", "function": {"name": "get_stock_fundamentals", "description": "get_stock_fundamentals(symbol: str) -> dict - Get fundamental data for a given stock symbol using yfinance API.\\n\\n Args:\\n symbol (str): The stock symbol.\\n\\n Returns:\\n dict: A dictionary containing fundamental data.\\n Keys:\\n - \'symbol\': The stock symbol.\\n - \'company_name\': The long name of the company.\\n - \'sector\': The sector to which the company belongs.\\n - \'industry\': The industry to which the company belongs.\\n - \'market_cap\': The market capitalization of the company.\\n - \'pe_ratio\': The forward price-to-earnings ratio.\\n - \'pb_ratio\': The price-to-book ratio.\\n - \'dividend_yield\': The dividend yield.\\n - \'eps\': The trailing earnings per share.\\n - \'beta\': The beta value of the stock.\\n - \'52_week_high\': The 52-week high price of the stock.\\n - \'52_week_low\': The 52-week low price of the stock.", "parameters": {"type": "object", "properties": {"symbol": {"type": "string"}}, "required": ["symbol"]}}} </tools> Use the following pydantic model json schema for each tool call you will make: {"properties": {"arguments": {"title": "Arguments", "type": "object"}, "name": {"title": "Name", "type": "string"}}, "required": ["arguments", "name"], "title": "FunctionCall", "type": "object"} For each function call return a json object with function name and arguments within <tool_call></tool_call> XML tags as follows: <tool_call> {"arguments": <args-dict>, "name": <function-name>} </tool_call><\|eot_id\|><\|start_header_id\|>user<\|end_header_id\|> ``` To complete the function call, create a user prompt that follows the above system prompt, like so: ``` Fetch the stock fundamentals data for Tesla (TSLA)<\|eot_id\|><\|start_header_id\|>assistant<\|end_header_id\|> ``` The model will then generate a tool call, which your inference code must parse, and plug into a function (see example inference code here: https://github.com/NousResearch/Hermes-Function-Calling): ``` <tool_call> {"arguments": {"symbol": "TSLA"}, "name": "get_stock_fundamentals"} </tool_call><\|eot_id\|><\|start_header_id\|>tool<\|end_header_id\|> ``` Once you parse the tool call, call the api and get the returned values for the call, and pass it back in as a new role, `tool` like so: ``` <tool_response> {"name": "get_stock_fundamentals", "content": {'symbol': 'TSLA', 'company_name': 'Tesla, Inc.', 'sector': 'Consumer Cyclical', 'industry': 'Auto Manufacturers', 'market_cap': 611384164352, 'pe_ratio': 49.604652, 'pb_ratio': 9.762013, 'dividend_yield': None, 'eps': 4.3, 'beta': 2.427, '52_week_high': 299.29, '52_week_low': 152.37}} </tool_response> <\|eot_id\|><\|start_header_id\|>assistant<\|end_header_id\|> ``` The assistant will then read in that data from the function's response, and generate a natural language response: ``` The stock fundamentals data for Tesla (TSLA) are as follows: - Symbol: TSLA - Company Name: Tesla, Inc. - Sector: Consumer Cyclical - Industry: Auto Manufacturers - Market Capitalization: $566,160,130,480 - Forward Price-to-Earnings Ratio (PE Ratio): 42.73 - Price-to-Book Ratio (PB Ratio): 9.04 - Dividend Yield: N/A - Trailing Earnings Per Share (EPS): $4.3 - Beta Value of the Stock: 2.42 - 52-Week High Price of the Stock: $299.29 - 52-Week Low Price of the Stock: $152.37 This information provides a snapshot of Tesla's financial position and performance based on the fundamental data obtained from the yfinance API. It shows that Tesla has a substantial market capitalization and a relatively high P/E and P/B ratio compared to other stocks in its industry. The company does not pay a dividend at the moment, which is reflected by a 'Dividend Yield' of 'None'. The Beta value indicates that Tesla's stock has a moderate level of volatility relative to the market. The 52-week high and low prices give an idea of the stock's range over the past year. This data can be useful when assessing investment opportunities and making investment decisions.<\|eot_id\|><\|start_header_id\|>user<\|end_header_id\|> ``` ## Prompt Format for JSON Mode / Structured Outputs Our model was also trained on a specific system prompt for Structured Outputs, which should respond with only a json object response, in a specific json schema. Your schema can be made from a pydantic object using our codebase, with the standalone script `jsonmode.py` available here: https://github.com/NousResearch/Hermes-Function-Calling/tree/main ``` <\|start_header_id\|>system<\|end_header_id\|> You are a helpful assistant that answers in JSON. Here's the json schema you must adhere to:\n<schema>\n{schema}\n</schema><\|eot_id\|> ``` Given the {schema} that you provide, it should follow the format of that json to create its response, all you have to do is give a typical user prompt, and it will respond in JSON. ## Inference Code for Function Calling: All code for utilizing, parsing, and building function calling templates is available on our github: [https://github.com/NousResearch/Hermes-Function-Calling](https://github.com/NousResearch/Hermes-Function-Calling) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/oi4CiGh50xmoviUQnh8R3.png) ## Quantized Versions: GGUF Quants: https://huggingface.co/NousResearch/DeepHermes-3-Llama-3-8B-Preview-GGUF # How to cite: ```bibtext @misc{ title={DeepHermes 3 Preview}, author={Teknium and Roger Jin and Chen Guang and Jai Suphavadeeprasit and Jeffrey Quesnelle}, year={2025} } ```
Mungert/Qwen2.5-14B-Instruct-GGUF	Mungert	2025-06-15T19:39:45Z	298	6	transformers	[ "transformers", "gguf", "chat", "text-generation", "en", "arxiv:2309.00071", "arxiv:2407.10671", "base_model:Qwen/Qwen2.5-14B", "base_model:quantized:Qwen/Qwen2.5-14B", "license:apache-2.0", "endpoints_compatible", "region:us", "imatrix", "conversational" ]	text-generation	2025-03-15T18:14:07Z	--- license: apache-2.0 license_link: https://huggingface.co/Qwen/Qwen2.5-14B-Instruct/blob/main/LICENSE language: - en pipeline_tag: text-generation base_model: Qwen/Qwen2.5-14B tags: - chat library_name: transformers --- # <span style="color: #7FFF7F;">Qwen2.5-14B-Instruct GGUF Models</span> ## Choosing the Right Model Format Selecting the correct model format depends on your hardware capabilities and memory constraints. ### BF16 (Brain Float 16) – Use if BF16 acceleration is available - A 16-bit floating-point format designed for faster computation while retaining good precision. - Provides similar dynamic range as FP32 but with lower memory usage. - Recommended if your hardware supports BF16 acceleration (check your device’s specs). - Ideal for high-performance inference with reduced memory footprint compared to FP32. 📌 Use BF16 if: ✔ Your hardware has native BF16 support (e.g., newer GPUs, TPUs). ✔ You want higher precision while saving memory. ✔ You plan to requantize the model into another format. 📌 Avoid BF16 if: ❌ Your hardware does not support BF16 (it may fall back to FP32 and run slower). ❌ You need compatibility with older devices that lack BF16 optimization. --- ### F16 (Float 16) – More widely supported than BF16 - A 16-bit floating-point high precision but with less of range of values than BF16. - Works on most devices with FP16 acceleration support (including many GPUs and some CPUs). - Slightly lower numerical precision than BF16 but generally sufficient for inference. 📌 Use F16 if: ✔ Your hardware supports FP16 but not BF16. ✔ You need a balance between speed, memory usage, and accuracy. ✔ You are running on a GPU or another device optimized for FP16 computations. 📌 Avoid F16 if: ❌ Your device lacks native FP16 support (it may run slower than expected). ❌ You have memory limitations. --- ### Quantized Models (Q4_K, Q6_K, Q8, etc.) – For CPU & Low-VRAM Inference Quantization reduces model size and memory usage while maintaining as much accuracy as possible. - Lower-bit models (Q4_K) → Best for minimal memory usage, may have lower precision. - Higher-bit models (Q6_K, Q8_0) → Better accuracy, requires more memory. 📌 Use Quantized Models if: ✔ You are running inference on a CPU and need an optimized model. ✔ Your device has low VRAM and cannot load full-precision models. ✔ You want to reduce memory footprint while keeping reasonable accuracy. 📌 Avoid Quantized Models if: ❌ You need maximum accuracy (full-precision models are better for this). ❌ Your hardware has enough VRAM for higher-precision formats (BF16/F16). --- ### Summary Table: Model Format Selection \| Model Format \| Precision \| Memory Usage \| Device Requirements \| Best Use Case \| \|--------------\|------------\|---------------\|----------------------\|---------------\| \| BF16 \| Highest \| High \| BF16-supported GPU/CPUs \| High-speed inference with reduced memory \| \| F16 \| High \| High \| FP16-supported devices \| GPU inference when BF16 isn’t available \| \| Q4_K \| Low \| Very Low \| CPU or Low-VRAM devices \| Best for memory-constrained environments \| \| Q6_K \| Medium Low \| Low \| CPU with more memory \| Better accuracy while still being quantized \| \| Q8 \| Medium \| Moderate \| CPU or GPU with enough VRAM \| Best accuracy among quantized models \| ## Included Files & Details ### `Qwen2.5-14B-Instruct-bf16.gguf` - Model weights preserved in BF16. - Use this if you want to requantize the model into a different format. - Best if your device supports BF16 acceleration. ### `Qwen2.5-14B-Instruct-f16.gguf` - Model weights stored in F16. - Use if your device supports FP16, especially if BF16 is not available. ### `Qwen2.5-14B-Instruct-bf16-q8_0.gguf` - Output & embeddings remain in BF16. - All other layers quantized to Q8_0. - Use if your device supports BF16 and you want a quantized version. ### `Qwen2.5-14B-Instruct-f16-q8_0.gguf` - Output & embeddings remain in F16. - All other layers quantized to Q8_0. ### `Qwen2.5-14B-Instruct-q4_k.gguf` - Output & embeddings quantized to Q8_0. - All other layers quantized to Q4_K. - Good for CPU inference with limited memory. ### `Qwen2.5-14B-Instruct-q4_k_s.gguf` - Smallest Q4_K variant, using less memory at the cost of accuracy. - Best for very low-memory setups. ### `Qwen2.5-14B-Instruct-q6_k.gguf` - Output & embeddings quantized to Q8_0. - All other layers quantized to Q6_K . ### `Qwen2.5-14B-Instruct-q8_0.gguf` - Fully Q8 quantized model for better accuracy. - Requires more memory but offers higher precision # <span id="testllm" style="color: #7F7FFF;">🚀 If you find these models useful</span> Please click like ❤ . Also I’d really appreciate it if you could test my Network Monitor Assistant at 👉 [Network Monitor Assitant](https://readyforquantum.com). 💬 Click the chat icon (bottom right of the main and dashboard pages) . Choose a LLM; toggle between the LLM Types TurboLLM -> FreeLLM -> TestLLM. ### What I'm Testing I'm experimenting with function calling against my network monitoring service. Using small open source models. I am into the question "How small can it go and still function". 🟡 TestLLM – Runs the current testing model using llama.cpp on 6 threads of a Cpu VM (Should take about 15s to load. Inference speed is quite slow and it only processes one user prompt at a time—still working on scaling!). If you're curious, I'd be happy to share how it works! . ### The other Available AI Assistants 🟢 TurboLLM – Uses gpt-4o-mini Fast! . Note: tokens are limited since OpenAI models are pricey, but you can [Login](https://readyforquantum.com) or [Download](https://readyforquantum.com/download/?utm_source=huggingface&utm_medium=referral&utm_campaign=huggingface_repo_readme) the Quantum Network Monitor agent to get more tokens, Alternatively use the TestLLM . 🔵 HugLLM – Runs open-source Hugging Face models Fast, Runs small models (≈8B) hence lower quality, Get 2x more tokens (subject to Hugging Face API availability) ### 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! 😊 # Qwen2.5-14B-Instruct ## Introduction Qwen2.5 is the latest series of Qwen large language models. For Qwen2.5, we release a number of base language models and instruction-tuned language models ranging from 0.5 to 72 billion parameters. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and mathematics, thanks to our specialized expert models in these domains. - Significant improvements in instruction following, generating long texts (over 8K tokens), understanding structured data (e.g, tables), and generating structured outputs especially JSON. More resilient to the diversity of system prompts, enhancing role-play implementation and condition-setting for chatbots. - Long-context Support up to 128K tokens and can generate up to 8K tokens. - Multilingual support for over 29 languages, including Chinese, English, French, Spanish, Portuguese, German, Italian, Russian, Japanese, Korean, Vietnamese, Thai, Arabic, and more. This repo contains the instruction-tuned 14B Qwen2.5 model, which has the following features: - Type: Causal Language Models - Training Stage: Pretraining & Post-training - Architecture: transformers with RoPE, SwiGLU, RMSNorm, and Attention QKV bias - Number of Parameters: 14.7B - Number of Paramaters (Non-Embedding): 13.1B - Number of Layers: 48 - Number of Attention Heads (GQA): 40 for Q and 8 for KV - Context Length: Full 131,072 tokens and generation 8192 tokens - Please refer to [this section](#processing-long-texts) for detailed instructions on how to deploy Qwen2.5 for handling long texts. For more details, please refer to our [blog](https://qwenlm.github.io/blog/qwen2.5/), [GitHub](https://github.com/QwenLM/Qwen2.5), and [Documentation](https://qwen.readthedocs.io/en/latest/). ## Requirements The code of Qwen2.5 has been in the latest Hugging face `transformers` and we advise you to use the latest version of `transformers`. With `transformers<4.37.0`, you will encounter the following error: ``` KeyError: 'qwen2' ``` ## Quickstart Here provides a code snippet with `apply_chat_template` to show you how to load the tokenizer and model and how to generate contents. ```python from transformers import AutoModelForCausalLM, AutoTokenizer model_name = "Qwen/Qwen2.5-14B-Instruct" model = AutoModelForCausalLM.from_pretrained( model_name, torch_dtype="auto", device_map="auto" ) tokenizer = AutoTokenizer.from_pretrained(model_name) prompt = "Give me a short introduction to large language model." messages = [ {"role": "system", "content": "You are Qwen, created by Alibaba Cloud. You are a helpful assistant."}, {"role": "user", "content": prompt} ] text = tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True ) model_inputs = tokenizer([text], return_tensors="pt").to(model.device) generated_ids = model.generate( model_inputs, max_new_tokens=512 ) generated_ids = [ output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids) ] response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0] ``` ### Processing Long Texts The current `config.json` is set for context length up to 32,768 tokens. To handle extensive inputs exceeding 32,768 tokens, we utilize [YaRN](https://arxiv.org/abs/2309.00071), a technique for enhancing model length extrapolation, ensuring optimal performance on lengthy texts. For supported frameworks, you could add the following to `config.json` to enable YaRN: ```json { ..., "rope_scaling": { "factor": 4.0, "original_max_position_embeddings": 32768, "type": "yarn" } } ``` For deployment, we recommend using vLLM. Please refer to our [Documentation](https://qwen.readthedocs.io/en/latest/deployment/vllm.html) for usage if you are not familar with vLLM. Presently, vLLM only supports static YARN, which means the scaling factor remains constant regardless of input length, potentially impacting performance on shorter texts**. We advise adding the `rope_scaling` configuration only when processing long contexts is required. ## Evaluation & Performance Detailed evaluation results are reported in this [📑 blog](https://qwenlm.github.io/blog/qwen2.5/). For requirements on GPU memory and the respective throughput, see results [here](https://qwen.readthedocs.io/en/latest/benchmark/speed_benchmark.html). ## Citation If you find our work helpful, feel free to give us a cite. ``` @misc{qwen2.5, title = {Qwen2.5: A Party of Foundation Models}, url = {https://qwenlm.github.io/blog/qwen2.5/}, author = {Qwen Team}, month = {September}, year = {2024} } @article{qwen2, title={Qwen2 Technical Report}, author={An Yang and Baosong Yang and Binyuan Hui and Bo Zheng and Bowen Yu and Chang Zhou and Chengpeng Li and Chengyuan Li and Dayiheng Liu and Fei Huang and Guanting Dong and Haoran Wei and Huan Lin and Jialong Tang and Jialin Wang and Jian Yang and Jianhong Tu and Jianwei Zhang and Jianxin Ma and Jin Xu and Jingren Zhou and Jinze Bai and Jinzheng He and Junyang Lin and Kai Dang and Keming Lu and Keqin Chen and Kexin Yang and Mei Li and Mingfeng Xue and Na Ni and Pei Zhang and Peng Wang and Ru Peng and Rui Men and Ruize Gao and Runji Lin and Shijie Wang and Shuai Bai and Sinan Tan and Tianhang Zhu and Tianhao Li and Tianyu Liu and Wenbin Ge and Xiaodong Deng and Xiaohuan Zhou and Xingzhang Ren and Xinyu Zhang and Xipin Wei and Xuancheng Ren and Yang Fan and Yang Yao and Yichang Zhang and Yu Wan and Yunfei Chu and Yuqiong Liu and Zeyu Cui and Zhenru Zhang and Zhihao Fan}, journal={arXiv preprint arXiv:2407.10671}, year={2024} } ```
07-katrina-lim-viral/Katrina.Lim.Viral.Video.Link.Full.Video.Original.Clip.4k	07-katrina-lim-viral	2025-06-15T19:16:15Z	0	0	null	[ "region:us" ]	null	2025-06-15T19:15:20Z	<a rel="nofollow" href="https://viralvideoclipe.store/viral-videos/">➤ ►🌍📺📱👉 𝖶𝖠𝖳𝖢𝖧 𝖭𝖮𝖶</a> <a data-target="animated-image.originalLink" rel="nofollow" href="https://viralvideoclipe.store/viral-videos/"><img data-target="animated-image.originalImage" style="max-width: 100%; display: inline-block;" data-canonical-src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" alt="Foo" src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif"></a>
MichiganNLP/tama-5e-7	MichiganNLP	2025-06-15T18:08:31Z	10	0	null	[ "safetensors", "llama", "table", "text-generation", "conversational", "en", "arxiv:2501.14693", "base_model:meta-llama/Llama-3.1-8B-Instruct", "base_model:finetune:meta-llama/Llama-3.1-8B-Instruct", "license:mit", "region:us" ]	text-generation	2024-12-11T00:50:43Z	--- license: mit language: - en base_model: - meta-llama/Llama-3.1-8B-Instruct pipeline_tag: text-generation tags: - table --- # Model Card for TAMA-5e-7 <!-- Provide a quick summary of what the model is/does. --> Recent advances in table understanding have focused on instruction-tuning large language models (LLMs) for table-related tasks. However, existing research has overlooked the impact of hyperparameter choices, and also lacks a comprehensive evaluation of the out-of-domain table understanding ability and the general capabilities of these table LLMs. In this paper, we evaluate these abilities in existing table LLMs, and find significant declines in both out-of-domain table understanding and general capabilities as compared to their base models. Through systematic analysis, we show that hyperparameters, such as learning rate, can significantly influence both table-specific and general capabilities. Contrary to the previous table instruction-tuning work, we demonstrate that smaller learning rates and fewer training instances can enhance table understanding while preserving general capabilities. Based on our findings, we introduce TAMA, a TAble LLM instruction-tuned from LLaMA 3.1 8B Instruct, which achieves performance on par with, or surpassing GPT-3.5 and GPT-4 on table tasks, while maintaining strong out-of-domain generalization and general capabilities. Our findings highlight the potential for reduced data annotation costs and more efficient model development through careful hyperparameter selection. ## 🚀 Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> - Model type: Text generation. - Language(s) (NLP): English. - License: [[License for Llama models](https://github.com/meta-llama/llama-models/blob/main/models/llama3_1/LICENSE))] - Finetuned from model: [[meta-llama/Llama-3.1-8b-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct)] ### Model Sources <!-- Provide the basic links for the model. --> - Repository: [[github](https://github.com/MichiganNLP/TAMA)] - Paper: [[paper](https://arxiv.org/abs/2501.14693)] ## 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. --> TAMA is intended for the use in table understanding tasks and to facilitate future research. ## 🔨 How to Get Started with the Model Use the code below to get started with the model. 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`. ``` import transformers import torch model_id = "MichiganNLP/tama-5e-7" pipeline = transformers.pipeline( "text-generation", model=model_id, model_kwargs={"torch_dtype": torch.bfloat16}, device_map="auto" ) pipeline("Hey how are you doing today?") ``` You may replace the prompt with table-specific instructions. We recommend using the following prompt structure: ``` Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request. ### Instruction: {instruction} ### Input: {table_content} ### Question: {question} ### Response: ``` ## 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. --> [TAMA Instruct](https://huggingface.co/datasets/MichiganNLP/TAMA_Instruct). ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> We utilize the [LLaMA Factory](https://github.com/hiyouga/LLaMA-Factory) library for model training and inference. Example YAML configuration files are provided [here](https://github.com/MichiganNLP/TAMA/blob/main/yamls/train.yaml). The training command is: ``` llamafactory-cli train yamls/train.yaml ``` #### Training Hyperparameters - Training regime: bf16 - Training epochs: 2.0 - Learning rate scheduler: linear - Cutoff length: 2048 - Learning rate: 5e-7 ## 📝 Evaluation ### Results <!-- This should link to a Dataset Card if possible. --> <table> <tr> <th>Models</th> <th>FeTaQA</th> <th>HiTab</th> <th>TaFact</th> <th>FEVEROUS</th> <th>WikiTQ</th> <th>WikiSQL</th> <th>HybridQA</th> <th>TATQA</th> <th>AIT-QA</th> <th>TABMWP</th> <th>InfoTabs</th> <th>KVRET</th> <th>ToTTo</th> <th>TableGPT<sub>subset</sub></th> <th>TableBench</th> </tr> <tr> <th>Metrics</th> <th>BLEU</th> <th>Acc</th> <th>Acc</th> <th>Acc</th> <th>Acc</th> <th>Acc</th> <th>Acc</th> <th>Acc</th> <th>Acc</th> <th>Acc</th> <th>Acc</th> <th>Micro F1</th> <th>BLEU</th> <th>Acc</th> <th>ROUGE-L</th> </tr> <tr> <td>GPT-3.5</td> <td><u>26.49</u></td> <td>43.62</td> <td>67.41</td> <td>60.79</td> <td><u>53.13</u></td> <td>41.91</td> <td>40.22</td> <td>31.38</td> <td>84.13</td> <td>46.30</td> <td>56.00</td> <td><u>54.56</u></td> <td><u>16.81</u></td> <td>54.80</td> <td>27.75</td> </tr> <tr> <td>GPT-4</td> <td>21.70</td> <td><u>48.40</u></td> <td><b>74.40</b></td> <td><u>71.60</u></td> <td><b>68.40</b></td> <td><u>47.60</u></td> <td><u>58.60</u></td> <td><b>55.81</b></td> <td><u>88.57</u></td> <td><b>67.10</b></td> <td><u>58.60</u></td> <td><b>56.46</b></td> <td>12.21</td> <td><b>80.20</b></td> <td><b>40.38</b></td> </tr> <tr> <td>base</td> <td>15.33</td> <td>32.83</td> <td>58.44</td> <td>66.37</td> <td>43.46</td> <td>20.43</td> <td>32.83</td> <td>26.70</td> <td>82.54</td> <td>39.97</td> <td>48.39</td> <td>50.80</td> <td>13.24</td> <td>53.60</td> <td>23.47</td> </tr> <tr> <td>TAMA</td> <td><b>35.37</b></td> <td><b>63.51</b></td> <td><u>73.82</u></td> <td><b>77.39</b></td> <td>52.88</td> <td><b>68.31</b></td> <td><b>60.86</b></td> <td><u>48.47</u></td> <td><b>89.21</b></td> <td><u>65.09</u></td> <td><b>64.54</b></td> <td>43.94</td> <td><b>37.94</b></td> <td><u>53.60</u></td> <td><u>28.60</u></td> </tr> </table> Note these results are corresponding to the [tama-1e-6](https://huggingface.co/MichiganNLP/tama-1e-6) checkpoint. We release the tama-5e-7 checkpoints for the purpose of facilitating future research. We make the number bold if it is the best among the four, we underline the number if it is at the second place. Please refer to our [paper](https://arxiv.org/abs/2501.14693) for additional details. #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> Please refer to our [paper](https://arxiv.org/abs/2501.14693) for additional details. #### Summary Notably, as an 8B model, TAMA demonstrates strong table understanding ability, outperforming GPT-3.5 on most of the table understanding benchmarks, even achieving performance on par or better than GPT-4. ## Technical Specifications ### Model Architecture and Objective We base our model on the [Llama-3.1-8B-Instruct model](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct). We instruction tune the model on a set of 2,600 table instructions. ### Compute Infrastructure #### Hardware We conduct our experiments on A40 and A100 GPUs. #### Software We leverage the [LLaMA Factory](https://github.com/hiyouga/LLaMA-Factory) for model training. ## Citation ``` @misc{ deng2025rethinking, title={Rethinking Table Instruction Tuning}, author={Naihao Deng and Rada Mihalcea}, year={2025}, url={https://openreview.net/forum?id=GLmqHCwbOJ} } ``` ## Model Card Authors Naihao Deng ## Model Card Contact Naihao Deng
gradientrouting-spar/horizontal_1_proxy_ntrain_25_ntrig_9_negative_3x3_seed_1_20250615_160158	gradientrouting-spar	2025-06-15T16:11:17Z	0	0	transformers	[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2025-06-15T16:11:09Z	--- 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]
ekyuho/hyodol-qwen	ekyuho	2025-06-15T15:48:28Z	0	0	null	[ "safetensors", "region:us" ]	null	2025-06-15T15:44:28Z	# hyodol-qwen 효돌이: 노인 케어용 한국어 공감 대화 AI ## 사용법 ```python from transformers import AutoModelForCausalLM, AutoTokenizer from peft import PeftModel # 모델 로드 base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-3B-Instruct") model = PeftModel.from_pretrained(base_model, "ekyuho/hyodol-qwen") tokenizer = AutoTokenizer.from_pretrained("ekyuho/hyodol-qwen") # 대화 생성 prompt = "효돌아, 오늘 외로워..." inputs = tokenizer(prompt, return_tensors="pt") outputs = model.generate(**inputs, max_new_tokens=100) response = tokenizer.decode(outputs[0], skip_special_tokens=True) print(response) ``` ## 정보 - 베이스 모델: Qwen/Qwen2.5-3B-Instruct - 파인튜닝: LoRA - 언어: 한국어 - 용도: 노인 케어 대화
Copycats/orpheus-3b-0.1-tts-elise	Copycats	2025-06-15T15:46:59Z	0	0	transformers	[ "transformers", "safetensors", "unsloth", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2025-06-15T15:45:40Z	--- library_name: transformers 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. --> 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]
keilrockstars/6f9b5ead-592d-4022-bdd3-ce2077d5c37b	keilrockstars	2025-06-15T15:41:36Z	0	0	peft	[ "peft", "safetensors", "llama", "axolotl", "generated_from_trainer", "base_model:unsloth/Llama-3.2-1B", "base_model:adapter:unsloth/Llama-3.2-1B", "license:llama3.2", "region:us" ]	null	2025-06-15T15:30:19Z	--- library_name: peft license: llama3.2 base_model: unsloth/Llama-3.2-1B tags: - axolotl - generated_from_trainer model-index: - name: 6f9b5ead-592d-4022-bdd3-ce2077d5c37b 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. --> [<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl) <details><summary>See axolotl config</summary> axolotl version: `0.4.1` ```yaml adapter: lora base_model: unsloth/Llama-3.2-1B bf16: auto chat_template: llama3 dataset_prepared_path: null datasets: - data_files: - 10ef40cfa0431b5f_train_data.json ds_type: json format: custom path: /workspace/input_data/ type: field_instruction: instruct field_output: output format: '{instruction}' no_input_format: '{instruction}' system_format: '{system}' system_prompt: '' debug: null deepspeed: null early_stopping_patience: null eval_max_new_tokens: 128 eval_table_size: null evals_per_epoch: 4 flash_attention: false fp16: null fsdp: null fsdp_config: null gradient_accumulation_steps: 4 gradient_checkpointing: true group_by_length: false hub_model_id: keilrockstars/6f9b5ead-592d-4022-bdd3-ce2077d5c37b hub_repo: null hub_strategy: checkpoint hub_token: null learning_rate: 0.0002 load_in_4bit: false load_in_8bit: false local_rank: null logging_steps: 1 lora_alpha: 16 lora_dropout: 0.05 lora_fan_in_fan_out: null lora_model_dir: null lora_r: 8 lora_target_linear: true lr_scheduler: cosine max_steps: 10 micro_batch_size: 2 mlflow_experiment_name: /tmp/10ef40cfa0431b5f_train_data.json model_type: AutoModelForCausalLM num_epochs: 1 optimizer: adamw_bnb_8bit output_dir: miner_id_24 pad_to_sequence_len: true resume_from_checkpoint: null s2_attention: null sample_packing: false saves_per_epoch: 4 sequence_len: 512 strict: false tf32: false tokenizer_type: AutoTokenizer train_on_inputs: false trust_remote_code: true val_set_size: 0.05 wandb_entity: null wandb_mode: online wandb_name: b2e8c9d0-0380-481c-854d-f950dbe5c9a6 wandb_project: Gradients-On-Demand wandb_run: your_name wandb_runid: b2e8c9d0-0380-481c-854d-f950dbe5c9a6 warmup_steps: 10 weight_decay: 0.0 xformers_attention: null ``` </details><br> # 6f9b5ead-592d-4022-bdd3-ce2077d5c37b This model is a fine-tuned version of [unsloth/Llama-3.2-1B](https://huggingface.co/unsloth/Llama-3.2-1B) on the None dataset. It achieves the following results on the evaluation set: - Loss: nan ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0002 - train_batch_size: 2 - eval_batch_size: 2 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 8 - optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: cosine - lr_scheduler_warmup_steps: 10 - training_steps: 10 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:------:\|:----:\|:---------------:\| \| 0.0 \| 0.0001 \| 1 \| nan \| \| 0.0 \| 0.0002 \| 3 \| nan \| \| 0.0 \| 0.0003 \| 6 \| nan \| \| 0.0 \| 0.0005 \| 9 \| nan \| ### Framework versions - PEFT 0.13.2 - Transformers 4.46.0 - Pytorch 2.5.0+cu124 - Datasets 3.0.1 - Tokenizers 0.20.1
vcabeli/Qwen2.5-7B-Instruct-Open-R1-GRPO-bioprograms-reactome-qa-most_perturbed_pathway	vcabeli	2025-06-15T14:53:07Z	0	0	transformers	[ "transformers", "safetensors", "qwen2", "text-generation", "generated_from_trainer", "trl", "grpo", "conversational", "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	2025-06-15T12:54:33Z	--- base_model: Qwen/Qwen2.5-7B-Instruct library_name: transformers model_name: Qwen2.5-7B-Instruct-Open-R1-GRPO-bioprograms-reactome-qa-most_perturbed_pathway tags: - generated_from_trainer - trl - grpo licence: license --- # Model Card for Qwen2.5-7B-Instruct-Open-R1-GRPO-bioprograms-reactome-qa-most_perturbed_pathway This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-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="vcabeli/Qwen2.5-7B-Instruct-Open-R1-GRPO-bioprograms-reactome-qa-most_perturbed_pathway", 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/vincent-cabeli-owkin/huggingface/runs/1gwsf76d) 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: 0.18.0 - Transformers: 4.52.3 - Pytorch: 2.6.0 - 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 Gallou{\'e}dec}, year = 2020, journal = {GitHub repository}, publisher = {GitHub}, howpublished = {\url{https://github.com/huggingface/trl}} } ```
aotsukiqx/Qwen3-Reranker-8B-Q6_K-GGUF	aotsukiqx	2025-06-15T13:49:11Z	0	0	transformers	[ "transformers", "gguf", "llama-cpp", "gguf-my-repo", "text-ranking", "base_model:Qwen/Qwen3-Reranker-8B", "base_model:quantized:Qwen/Qwen3-Reranker-8B", "license:apache-2.0", "endpoints_compatible", "region:us", "conversational" ]	text-ranking	2025-06-15T13:48:37Z	--- license: apache-2.0 base_model: Qwen/Qwen3-Reranker-8B library_name: transformers pipeline_tag: text-ranking tags: - llama-cpp - gguf-my-repo --- # aotsukiqx/Qwen3-Reranker-8B-Q6_K-GGUF This model was converted to GGUF format from [`Qwen/Qwen3-Reranker-8B`](https://huggingface.co/Qwen/Qwen3-Reranker-8B) 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/Qwen/Qwen3-Reranker-8B) 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 aotsukiqx/Qwen3-Reranker-8B-Q6_K-GGUF --hf-file qwen3-reranker-8b-q6_k.gguf -p "The meaning to life and the universe is" ``` ### Server: ```bash llama-server --hf-repo aotsukiqx/Qwen3-Reranker-8B-Q6_K-GGUF --hf-file qwen3-reranker-8b-q6_k.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 aotsukiqx/Qwen3-Reranker-8B-Q6_K-GGUF --hf-file qwen3-reranker-8b-q6_k.gguf -p "The meaning to life and the universe is" ``` or ``` ./llama-server --hf-repo aotsukiqx/Qwen3-Reranker-8B-Q6_K-GGUF --hf-file qwen3-reranker-8b-q6_k.gguf -c 2048 ```
chenyu313707056/GRPO313707056	chenyu313707056	2025-06-15T12:49:27Z	0	0	peft	[ "peft", "safetensors", "qwen2", "arxiv:1910.09700", "base_model:Qwen/Qwen2.5-3B-Instruct", "base_model:adapter:Qwen/Qwen2.5-3B-Instruct", "region:us" ]	null	2025-06-15T12:33:35Z	--- base_model: Qwen/Qwen2.5-3B-Instruct 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
MinaMila/gemma_2b_unlearned_2nd_5e-7_1.0_0.25_0.15_0.75_epoch2	MinaMila	2025-06-15T12:39:23Z	0	0	transformers	[ "transformers", "safetensors", "gemma2", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-06-15T12:37:40Z	--- 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]
mradermacher/Jan-nano-i1-GGUF	mradermacher	2025-06-15T12:32:08Z	0	0	transformers	[ "transformers", "gguf", "en", "base_model:Menlo/Jan-nano", "base_model:quantized:Menlo/Jan-nano", "license:apache-2.0", "endpoints_compatible", "region:us", "imatrix", "conversational" ]	null	2025-06-15T11:10:52Z	--- base_model: Menlo/Jan-nano language: - en library_name: transformers license: apache-2.0 quantized_by: mradermacher --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: nicoboss --> weighted/imatrix quants of https://huggingface.co/Menlo/Jan-nano <!-- provided-files --> static quants are available at https://huggingface.co/mradermacher/Jan-nano-GGUF ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) \| Link \| Type \| Size/GB \| Notes \| \|:-----\|:-----\|--------:\|:------\| \| [GGUF](https://huggingface.co/mradermacher/Jan-nano-i1-GGUF/resolve/main/Jan-nano.i1-IQ1_S.gguf) \| i1-IQ1_S \| 1.2 \| for the desperate \| \| [GGUF](https://huggingface.co/mradermacher/Jan-nano-i1-GGUF/resolve/main/Jan-nano.i1-IQ1_M.gguf) \| i1-IQ1_M \| 1.2 \| mostly desperate \| \| [GGUF](https://huggingface.co/mradermacher/Jan-nano-i1-GGUF/resolve/main/Jan-nano.i1-IQ2_XXS.gguf) \| i1-IQ2_XXS \| 1.3 \| \| \| [GGUF](https://huggingface.co/mradermacher/Jan-nano-i1-GGUF/resolve/main/Jan-nano.i1-IQ2_XS.gguf) \| i1-IQ2_XS \| 1.5 \| \| \| [GGUF](https://huggingface.co/mradermacher/Jan-nano-i1-GGUF/resolve/main/Jan-nano.i1-IQ2_S.gguf) \| i1-IQ2_S \| 1.5 \| \| \| [GGUF](https://huggingface.co/mradermacher/Jan-nano-i1-GGUF/resolve/main/Jan-nano.i1-IQ2_M.gguf) \| i1-IQ2_M \| 1.6 \| \| \| [GGUF](https://huggingface.co/mradermacher/Jan-nano-i1-GGUF/resolve/main/Jan-nano.i1-Q2_K_S.gguf) \| i1-Q2_K_S \| 1.7 \| very low quality \| \| [GGUF](https://huggingface.co/mradermacher/Jan-nano-i1-GGUF/resolve/main/Jan-nano.i1-Q2_K.gguf) \| i1-Q2_K \| 1.8 \| IQ3_XXS probably better \| \| [GGUF](https://huggingface.co/mradermacher/Jan-nano-i1-GGUF/resolve/main/Jan-nano.i1-IQ3_XXS.gguf) \| i1-IQ3_XXS \| 1.8 \| lower quality \| \| [GGUF](https://huggingface.co/mradermacher/Jan-nano-i1-GGUF/resolve/main/Jan-nano.i1-IQ3_XS.gguf) \| i1-IQ3_XS \| 1.9 \| \| \| [GGUF](https://huggingface.co/mradermacher/Jan-nano-i1-GGUF/resolve/main/Jan-nano.i1-Q3_K_S.gguf) \| i1-Q3_K_S \| 2.0 \| IQ3_XS probably better \| \| [GGUF](https://huggingface.co/mradermacher/Jan-nano-i1-GGUF/resolve/main/Jan-nano.i1-IQ3_S.gguf) \| i1-IQ3_S \| 2.0 \| beats Q3_K* \| \| [GGUF](https://huggingface.co/mradermacher/Jan-nano-i1-GGUF/resolve/main/Jan-nano.i1-IQ3_M.gguf) \| i1-IQ3_M \| 2.1 \| \| \| [GGUF](https://huggingface.co/mradermacher/Jan-nano-i1-GGUF/resolve/main/Jan-nano.i1-Q3_K_M.gguf) \| i1-Q3_K_M \| 2.2 \| IQ3_S probably better \| \| [GGUF](https://huggingface.co/mradermacher/Jan-nano-i1-GGUF/resolve/main/Jan-nano.i1-Q3_K_L.gguf) \| i1-Q3_K_L \| 2.3 \| IQ3_M probably better \| \| [GGUF](https://huggingface.co/mradermacher/Jan-nano-i1-GGUF/resolve/main/Jan-nano.i1-IQ4_XS.gguf) \| i1-IQ4_XS \| 2.4 \| \| \| [GGUF](https://huggingface.co/mradermacher/Jan-nano-i1-GGUF/resolve/main/Jan-nano.i1-Q4_0.gguf) \| i1-Q4_0 \| 2.5 \| fast, low quality \| \| [GGUF](https://huggingface.co/mradermacher/Jan-nano-i1-GGUF/resolve/main/Jan-nano.i1-IQ4_NL.gguf) \| i1-IQ4_NL \| 2.5 \| prefer IQ4_XS \| \| [GGUF](https://huggingface.co/mradermacher/Jan-nano-i1-GGUF/resolve/main/Jan-nano.i1-Q4_K_S.gguf) \| i1-Q4_K_S \| 2.5 \| optimal size/speed/quality \| \| [GGUF](https://huggingface.co/mradermacher/Jan-nano-i1-GGUF/resolve/main/Jan-nano.i1-Q4_K_M.gguf) \| i1-Q4_K_M \| 2.6 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/Jan-nano-i1-GGUF/resolve/main/Jan-nano.i1-Q4_1.gguf) \| i1-Q4_1 \| 2.7 \| \| \| [GGUF](https://huggingface.co/mradermacher/Jan-nano-i1-GGUF/resolve/main/Jan-nano.i1-Q5_K_S.gguf) \| i1-Q5_K_S \| 2.9 \| \| \| [GGUF](https://huggingface.co/mradermacher/Jan-nano-i1-GGUF/resolve/main/Jan-nano.i1-Q5_K_M.gguf) \| i1-Q5_K_M \| 3.0 \| \| \| [GGUF](https://huggingface.co/mradermacher/Jan-nano-i1-GGUF/resolve/main/Jan-nano.i1-Q6_K.gguf) \| i1-Q6_K \| 3.4 \| practically like static Q6_K \| 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 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. <!-- end -->
sahilm2904/phi3-workflow-finetuned	sahilm2904	2025-06-15T11:03:01Z	0	0	transformers	[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2025-06-15T08:35:44Z	--- 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]
MinaMila/gemma_2b_unlearned_2nd_5e-7_1.0_0.25_0.5_0.15_epoch1	MinaMila	2025-06-15T10:39:44Z	0	0	transformers	[ "transformers", "safetensors", "gemma2", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-06-15T10:37:56Z	--- 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]
trieutm/blip-vqa-finetuned	trieutm	2025-06-15T10:12:25Z	0	0	transformers	[ "transformers", "safetensors", "blip", "visual-question-answering", "en", "dataset:flaviagiammarino/path-vqa", "base_model:Salesforce/blip-vqa-base", "base_model:finetune:Salesforce/blip-vqa-base", "endpoints_compatible", "region:us" ]	visual-question-answering	2025-06-15T09:42:06Z	--- library_name: transformers datasets: - flaviagiammarino/path-vqa language: - en base_model: - Salesforce/blip-vqa-base pipeline_tag: visual-question-answering --- # How to use: ## For inference ### Load model directly ```python from transformers import BlipForQuestionAnswering, BlipProcessor model = BlipForQuestionAnswering.from_pretrained("trieutm/blip-vqa-finetuned") processor = BlipProcessor.from_pretrained("trieutm/blip-vqa-finetuned") ```
MinaMila/gemma_2b_unlearned_2nd_5e-7_1.0_0.25_0.5_0.75_epoch2	MinaMila	2025-06-15T09:59:04Z	0	0	transformers	[ "transformers", "safetensors", "gemma2", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-06-15T09:57:23Z	--- 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]
AlIshaq/DPR-context_encoder-faq-pesantren	AlIshaq	2025-06-15T09:24:19Z	0	0	null	[ "safetensors", "dpr", "faq", "chatbot", "pondok-pesantren", "indonesian", "id", "license:cc-by-nc-4.0", "region:us" ]	null	2025-06-15T09:04:37Z	--- license: cc-by-nc-4.0 model-index: - name: DPR Context Encoder (Fine-tuned on Pesantren FAQ) results: [] tags: - dpr - faq - chatbot - pondok-pesantren - indonesian language: - id --- This model is licensed under the Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0). It is a fine-tuned version of the [original model](https://huggingface.co/facebook/dpr-ctx_encoder-single-nq-base) and inherits the same license. This model is trained on a dataset of 9,000 Frequently Asked Questions (FAQ) from a pesantren (Islamic boarding school) in Indonesia, and designed for building retrieval-based chatbots for Indonesian educational contexts.
ZhongchenZhao/PPMA	ZhongchenZhao	2025-06-15T08:43:56Z	0	0	null	[ "arxiv:2410.15091", "arxiv:2203.06717", "region:us" ]	null	2025-06-14T11:41:43Z	<div align="center"> <h1>Spatial-Mamba: Effective Visual State Space Models via Structure-Aware State Fusion</h1> <div> <a href='https://github.com/EdwardChasel' target='_blank'>Chaodong Xiao<sup>1,2,</sup></a>, <a href='https://scholar.google.com/citations?user=LhdBgMAAAAAJ' target='_blank'>Minghan Li<sup>1,3,</sup></a>, <a href='https://scholar.google.com.hk/citations?hl=zh-CN&user=UX26wSMAAAAJ' target='_blank'>Zhengqiang Zhang<sup>1,2</sup></a>, <a href='https://gr.xjtu.edu.cn/en/web/dymeng/1' target='_blank'>Deyu Meng<sup>4</sup></a>, <a href='https://www4.comp.polyu.edu.hk/~cslzhang/' target='_blank'>Lei Zhang<sup>1,2,† </sup></a> </div> <div> <sup>1</sup>The Hong Kong Polytechnic University, <sup>2</sup>OPPO Research Institute,<br><sup>3</sup>Harvard Medical School, <sup>4</sup>Xi'an Jiaotong University </div> <div> () equal contribution, (†) corresponding author </div> [[📝 arXiv paper]](https://arxiv.org/abs/2410.15091) --- </div> #### 🚩Accepted by ICLR2025 ## Abstaract Selective state space models (SSMs), such as Mamba, highly excel at capturing long-range dependencies in 1D sequential data, while their applications to 2D vision tasks still face challenges. Current visual SSMs often convert images into 1D sequences and employ various scanning patterns to incorporate local spatial dependencies. However, these methods are limited in effectively capturing the complex image spatial structures and the increased computational cost caused by the lengthened scanning paths. To address these limitations, we propose Spatial-Mamba, a novel approach that establishes neighborhood connectivity directly in the state space. Instead of relying solely on sequential state transitions, we introduce a structure-aware state fusion equation, which leverages dilated convolutions to capture image spatial structural dependencies, significantly enhancing the flow of visual contextual information. Spatial-Mamba proceeds in three stages: initial state computation in a unidirectional scan, spatial context acquisition through structure-aware state fusion, and final state computation using the observation equation. Our theoretical analysis shows that Spatial-Mamba unifies the original Mamba and linear attention under the same matrix multiplication framework, providing a deeper understanding of our method. Experimental results demonstrate that Spatial-Mamba, even with a single scan, attains or surpasses the state-of-the-art SSM-based models in image classification, detection and segmentation. ## 🎬 Overview <p align="center"> <img src="assets/main.png" alt="main" width="80%"> </p> <p align="center"> <img src="assets/sasf.png" alt="sasf" width="80%"> </p> ## 🎯 Main Results ### Image Classification on ImageNet-1K <p align="center"> <img src="assets/classification.png" alt="classification" width="80%"> </p> * ### Object Detection and Instance Segmentation on COCO <p align="center"> <img src="assets/detection.png" alt="detection" width="80%"> </p> * ### Semantic Segmentation on ADE20K <p align="center"> <img src="assets/segmentation.png" alt="segmentation" width="80%"> </p> ## 🛠️ Getting Started 1. Clone repo ```bash git clone https://github.com/EdwardChasel/Spatial-Mamba.git cd Spatial-Mamba ``` 2. Create and activate a new conda environment ```bash conda create -n Spatial-Mamba python=3.10 conda activate Spatial-Mamba ``` 3. Install dependent packages ```bash pip install --upgrade pip pip install -r requirements.txt cd kernels/selective_scan && pip install . cd kernels/dwconv2d && python3 setup.py install --user ``` 4. Dependencies for detection and segmentation (optional) ```bash pip install mmengine==0.10.1 mmcv==2.1.0 opencv-python-headless ftfy regex pip install mmdet==3.3.0 mmsegmentation==1.2.2 mmpretrain==1.2.0 ``` ## ✨ Pre-trained Models <details> <summary> ImageNet-1k Image Classification </summary> <br> <div> \| name \| pretrain \| resolution \| acc@1 \| #param \| FLOPs \| download \| \| :------------: \| :----------: \| :--------: \| :---: \| :----: \| :---: \| :---------------------------------------------------------------------------------------------------------------------------------------------------------------: \| \| Spatial-Mamba-T \| ImageNet-1K \| 224x224 \| 83.5 \| 27M \| 4.5G \| [ckpt](https://drive.google.com/file/d/19kXoqGSTuKKs4AHbdUSrdKZTwTWenLIW/view?usp=drive_link) \\| [config](classification/configs/spatialmamba/spatialmamba_tiny.yaml) \| \| Spatial-Mamba-S \| ImageNet-1K \| 224x224 \| 84.6 \| 43M \| 7.1G \| [ckpt](https://drive.google.com/file/d/1Wb3sYoWLpgmWrmHMYKwdgDwGPZaqM28O/view?usp=drive_link) \\| [config](classification/configs/spatialmamba/spatialmamba_small.yaml) \| \| Spatial-Mamba-B \| ImageNet-1K \| 224x224 \| 85.3 \| 96M \| 15.8G \| [ckpt](https://drive.google.com/file/d/1k8dHp2QRCOqBSgAi36YkhZp_O8LqOPjM/view?usp=drive_link) \\| [config](classification/configs/spatialmamba/spatialmamba_base.yaml) \| </div> </details> <details> <summary> COCO Object Detection and Instance Segmentation </summary> <br> <div> \| backbone \| method \| schedule \| mAP (box/mask) \| #param \| FLOPs \| download \| \| :------------: \| :--------: \| :---: \| :-----: \| :----: \| :---: \| :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: \| \| Spatial-Mamba-T \| Mask R-CNN \| 1x \| 47.6 / 42.9 \| 46M \| 261G \| [ckpt](https://drive.google.com/file/d/1lmA0_pBQbvuMkJD1R5m3oS_2jXaSy3N3/view?usp=drive_link) \\| [config](detection/configs/spatialmamba/mask_rcnn_spatialmamba_fpn_coco_tiny.py) \| \| Spatial-Mamba-S \| Mask R-CNN \| 1x \| 49.2 / 44.0 \| 63M \| 315G \| [ckpt](https://drive.google.com/file/d/1pzjz1A6nWA9W2FW2Ymg5JSAMbvxmc2hP/view?usp=drive_link) \\| [config](detection/configs/spatialmamba/mask_rcnn_spatialmamba_fpn_coco_small.py) \| \| Spatial-Mamba-B \| Mask R-CNN \| 1x \| 50.4 / 45.1 \| 115M \| 494G \| [ckpt](https://drive.google.com/file/d/1oTyT0q88ernqc1_IyqBWHrVJJPGNRN8r/view?usp=drive_link) \\| [config](detection/configs/spatialmamba/mask_rcnn_spatialmamba_fpn_coco_base.py) \| \| Spatial-Mamba-T \| Mask R-CNN \| 3x \| 49.3 / 43.8 \| 46M \| 261G \| [ckpt](https://drive.google.com/file/d/1U86t0wQ0ovgAGmnsuLu9YZgBcOQu6wVm/view?usp=drive_link) \\| [config](detection/configs/spatialmamba/mask_rcnn_spatialmamba_fpn_coco_tiny_3x.py) \| \| Spatial-Mamba-S \| Mask R-CNN \| 3x \| 50.5 / 44.6 \| 63M \| 315G \| [ckpt](https://drive.google.com/file/d/19fDAk8cyMplgVRKqU0BC_3l1NxXzHYl_/view?usp=drive_link) \\| [config](detection/configs/spatialmamba/mask_rcnn_spatialmamba_fpn_coco_small_3x.py) \| </div> </details> <details> <summary> ADE20K Semantic Segmentation </summary> <br> <div> \| backbone \| method \| resolution \| mIoU (ss/ms) \| #param \| FLOPs \| download \| \| :------------: \| :---------: \| :--------: \| :----------: \| :----: \| :---: \| :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: \| \| Spatial-Mamba-T \| UPerNet \| 512x512 \| 48.6 / 49.4 \| 57M \| 936G \| [ckpt](https://drive.google.com/file/d/1ngRweMh6vLjfZ43fb_o_ZyHs6psxb6Ix/view?usp=drive_link) \\| [config](segmentation/configs/spatialmamba/upernet_spatialmamba_4xb4-160k_ade20k-512x512_tiny.py) \| \| Spatial-Mamba-S \| UPerNet \| 512x512 \| 50.6 / 51.4 \| 73M \| 992G \| [ckpt](https://drive.google.com/file/d/1Ve07Um4dIPCcdg0mdNLjGxJtxKNWB_Sy/view?usp=drive_link) \\| [config](segmentation/configs/spatialmamba/upernet_spatialmamba_4xb4-160k_ade20k-512x512_small.py) \| \| Spatial-Mamba-B \| UPerNet \| 512x512 \| 51.8 / 52.6 \| 127M \| 1176G \| [ckpt](https://drive.google.com/file/d/1DLSC20TiSfzWrdgLRSdgrhnDn79nruB6/view?usp=drive_link) \\| [config](segmentation/configs/spatialmamba/upernet_spatialmamba_4xb4-160k_ade20k-512x512_base.py) \| </div> </details> ## 📚 Data Preparation * ImageNet is an image database organized according to the WordNet hierarchy. Download and extract ImageNet train and val images from http://image-net.org/. Organize the data into the following directory structure: ``` imagenet/ ├── train/ │ ├── n01440764/ (Example synset ID) │ │ ├── image1.JPEG │ │ ├── image2.JPEG │ │ └── ... │ ├── n01443537/ (Another synset ID) │ │ └── ... │ └── ... └── val/ ├── n01440764/ (Example synset ID) │ ├── image1.JPEG │ └── ... └── ... ``` * COCO is a large-scale object detection, segmentation, and captioning dataset. Please visit http://cocodataset.org/ for more information, including for the data, paper, and tutorials. [COCO API](https://github.com/cocodataset/cocoapi) also provides a concise and efficient way to process the data. * ADE20K is composed of more than 27K images from the SUN and Places databases. Please visit https://ade20k.csail.mit.edu/ for more information and see the [GitHub Repository](https://github.com/CSAILVision/ADE20K) for an overview of how to access and explore ADE20K. ## 🚀 Quick Start * Image Classification To train Spatial-Mamba models for classification on ImageNet, use the following commands for different configurations: ```bash cd classification python -m torch.distributed.launch --nnodes=1 --node_rank=0 --nproc_per_node=8 --master_addr="127.0.0.1" --master_port=29501 main.py --cfg </path/to/config> --batch-size 128 --data-path </path/of/dataset> --output /tmp ``` To evaluate the performance with pre-trained weights: ```bash cd classification python -m torch.distributed.launch --nnodes=1 --node_rank=0 --nproc_per_node=1 --master_addr="127.0.0.1" --master_port=29501 main.py --cfg </path/to/config> --batch-size 128 --data-path </path/of/dataset> --output /tmp --pretrained </path/of/checkpoint> ``` * Detection and Segmentation To train with mmdetection or mmsegmentation: ```bash cd detection bash ./tools/dist_train.sh </path/to/detection/config> 8 ``` ```bash cd segmentation bash ./tools/dist_train.sh </path/to/segmentation/config> 8 ``` To evaluate with mmdetection or mmsegmentation: ```bash cd detection bash ./tools/dist_test.sh </path/to/detection/config> </path/to/detection/checkpoint> 1 ``` ```bash cd segmentation bash ./tools/dist_test.sh </path/to/segmentation/config> </path/to/segmentation/checkpoint> 1 ``` use `--tta` to get the `mIoU(ms)` in segmentation. ## 🖊️ Citation ```BibTeX @inproceedings{ xiao2025spatialmamba, title={Spatial-Mamba: Effective Visual State Space Models via Structure-Aware State Fusion}, author={Chaodong Xiao and Minghan Li and Zhengqiang Zhang and Deyu Meng and Lei Zhang}, booktitle={The Thirteenth International Conference on Learning Representations}, year={2025} } ``` ## 💌 Acknowledgments This project is largely based on [Mamba](https://github.com/state-spaces/mamba), [VMamba](https://github.com/MzeroMiko/VMamba), [MLLA](https://github.com/LeapLabTHU/MLLA), [Swin-Transformer](https://github.com/microsoft/Swin-Transformer), [RepLKNet](https://arxiv.org/abs/2203.06717) and [OpenMMLab](https://github.com/open-mmlab). We are truly grateful for their excellent work. ## 🎫 License This project is released under the [Apache 2.0 license](LICENSE).
Chatseek/Luckseek	Chatseek	2025-06-15T06:57:39Z	0	1	null	[ "license:apache-2.0", "region:us" ]	null	2025-06-15T06:54:36Z	--- license: apache-2.0 ---
mchettih/financial_QA_distilgpt2_student	mchettih	2025-06-15T06:50:14Z	0	0	transformers	[ "transformers", "safetensors", "gpt2", "text-generation", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-06-15T06:50:02Z	--- 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]
Parbin-Sultana-Viral-Video/VIDEO.parbin.sultana.Viral.Video.Tutorial.Official	Parbin-Sultana-Viral-Video	2025-06-15T06:00:14Z	0	0	null	[ "region:us" ]	null	2025-06-15T05:59:40Z	Parbin Sultana Viral video took the internet viewers on various Leaked social media platforms. Parbin Sultana Video, a young and talented digital creator, recently became famous thanks to this interesting video. [🌐 𝖢𝖫𝖨𝖢𝖪 𝖧𝖤𝖱𝖤 ==►► 𝖶𝖠𝖳𝖢𝖧 𝖭𝖮𝖶](https://t.co/98E3uGhPfJ) [🔴 𝖢𝖫𝖨𝖢𝖪 𝖧𝖤𝖱𝖤 🌐==►► 𝖣𝗈𝗐𝗇𝗅𝗈𝖺𝖽 𝖭𝗈𝗐](https://t.co/98E3uGhPfJ) <a href="https://t.co/98E3uGhPfJ" 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>
thomyv/test	thomyv	2025-06-15T05:57:15Z	0	0	null	[ "safetensors", "license:apache-2.0", "region:us" ]	null	2025-06-15T05:55:46Z	--- license: apache-2.0 ---
dunhlinh104/dl	dunhlinh104	2025-06-15T05:45:06Z	0	0	null	[ "license:bigscience-bloom-rail-1.0", "region:us" ]	null	2025-06-15T05:45:06Z	--- license: bigscience-bloom-rail-1.0 ---
viralhubmedia/viral-mms-nirma-meena-viral-video-tutorial-official	viralhubmedia	2025-06-15T05:15:34Z	0	0	null	[ "region:us" ]	null	2025-06-15T05:15:22Z	02 minutes ago- viral-mms-nirma-meena-viral-video-tutorial-official Viral video took the internet viewers on various Leaked social media platforms. Paro Aarti Video, a young and talented digital creator, recently ... [🌐 𝖢𝖫𝖨𝖢𝖪 𝖧𝖤𝖱𝖤 🟢==►► 𝖶𝖠𝖳𝖢𝖧 𝖭𝖮𝖶](https://t.co/w4GQblBMlq) [🌐 𝖢𝖫𝖨𝖢𝖪 𝖧𝖤𝖱𝖤 🟢==►► 𝖶𝖠𝖳𝖢𝖧 𝖭𝖮𝖶 FREE](https://t.co/w4GQblBMlq) <a href="https://t.co/w4GQblBMlq" 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>
Kotek37/nllb-tur-latin-ottoman-13haz	Kotek37	2025-06-14T23:14:29Z	0	0	transformers	[ "transformers", "safetensors", "m2m_100", "text2text-generation", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text2text-generation	2025-06-14T23:13:28Z	--- 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]
DevQuasar/DeepMount00.Murai-350M-v0.1-beta-GGUF	DevQuasar	2025-06-14T20:44:09Z	0	0	null	[ "text-generation", "base_model:DeepMount00/Murai-350M-v0.1-beta", "base_model:finetune:DeepMount00/Murai-350M-v0.1-beta", "region:us" ]	text-generation	2025-06-14T20:44:08Z	--- base_model: - DeepMount00/Murai-350M-v0.1-beta 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: [DeepMount00/Murai-350M-v0.1-beta](https://huggingface.co/DeepMount00/Murai-350M-v0.1-beta) '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>
Video-alana-flores-foto-polemica/Ver.Video.alana.flores.foto.polemica.alana.flores.trending.viral.Full.Video	Video-alana-flores-foto-polemica	2025-06-14T18:05:32Z	0	0	null	[ "region:us" ]	null	2025-06-14T18:05:12Z	<animated-image data-catalyst=""><a href="https://tinyurl.com/fn84hrnu?news-viral-video" rel="nofollow" data-target="animated-image.originalLink"><img src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" alt="Foo" data-canonical-src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" style="max-width: 100%; display: inline-block;" data-target="animated-image.originalImage"></a>
love-mimi/sn72-model-61	love-mimi	2025-06-14T17:52:28Z	0	0	transformers	[ "transformers", "tensorboard", "safetensors", "vit", "image-classification", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]	image-classification	2025-06-14T17:52:12Z	--- 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]
Antoniogm98/BETO-final-TFG	Antoniogm98	2025-06-14T16:02:01Z	3	0	null	[ "safetensors", "bert", "license:apache-2.0", "region:us" ]	null	2025-06-12T17:06:58Z	--- license: apache-2.0 ---
BootesVoid/cmbvgsj2h01ifwoixh3vjcd1x_cmbwcp2yw036bwoixpne01qg7	BootesVoid	2025-06-14T15:52:42Z	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	2025-06-14T15:52:40Z	--- 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: SARS --- # Cmbvgsj2H01Ifwoixh3Vjcd1X_Cmbwcp2Yw036Bwoixpne01Qg7 <Gallery /> ## About this LoRA This is a [LoRA](https://replicate.com/docs/guides/working-with-loras) for the FLUX.1-dev text-to-image model. It can be used with diffusers or ComfyUI. It was trained on [Replicate](https://replicate.com/) using AI toolkit: https://replicate.com/ostris/flux-dev-lora-trainer/train ## Trigger words You should use `SARS` to trigger the image generation. ## Run this LoRA with an API using Replicate ```py import replicate input = { "prompt": "SARS", "lora_weights": "https://huggingface.co/BootesVoid/cmbvgsj2h01ifwoixh3vjcd1x_cmbwcp2yw036bwoixpne01qg7/resolve/main/lora.safetensors" } output = replicate.run( "black-forest-labs/flux-dev-lora", input=input ) for index, item in enumerate(output): with open(f"output_{index}.webp", "wb") as file: file.write(item.read()) ``` ## 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('BootesVoid/cmbvgsj2h01ifwoixh3vjcd1x_cmbwcp2yw036bwoixpne01qg7', weight_name='lora.safetensors') image = pipeline('SARS').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) ## Training details - Steps: 2000 - Learning rate: 0.0004 - LoRA rank: 16 ## Contribute your own examples You can use the [community tab](https://huggingface.co/BootesVoid/cmbvgsj2h01ifwoixh3vjcd1x_cmbwcp2yw036bwoixpne01qg7/discussions) to add images that show off what you’ve made with this LoRA.
duongng2911/detr-resnet-50-dc5-ordd2024-finetuned	duongng2911	2025-06-14T14:34:42Z	3	0	transformers	[ "transformers", "tensorboard", "safetensors", "detr", "object-detection", "generated_from_trainer", "base_model:facebook/detr-resnet-50", "base_model:finetune:facebook/detr-resnet-50", "license:apache-2.0", "endpoints_compatible", "region:us" ]	object-detection	2025-06-13T17:05:17Z	--- library_name: transformers license: apache-2.0 base_model: facebook/detr-resnet-50 tags: - generated_from_trainer model-index: - name: detr-resnet-50-dc5-ordd2024-finetuned 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. --> # detr-resnet-50-dc5-ordd2024-finetuned This model is a fine-tuned version of [facebook/detr-resnet-50](https://huggingface.co/facebook/detr-resnet-50) on the None dataset. It achieves the following results on the evaluation set: - Loss: 2.0037 - Map: 0.0003 - Map 50: 0.0011 - Map 75: 0.0001 - Map Small: 0.0125 - Map Medium: 0.0 - Map Large: 0.001 - Mar 1: 0.0 - Mar 10: 0.0132 - Mar 100: 0.1132 - Mar Small: 0.025 - Mar Medium: 0.05 - Mar Large: 0.1435 - Map Longitudinal Crack: 0.0003 - Mar 100 Longitudinal Crack: 0.0526 - Map Transverse Crack: -1.0 - Mar 100 Transverse Crack: -1.0 - Map Aligator Crack: 0.0009 - Mar 100 Aligator Crack: 0.4 - Map Pothole: 0.0 - Mar 100 Pothole: 0.0 - Map Other Corruptions: 0.0 - Mar 100 Other Corruptions: 0.0 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 1e-05 - train_batch_size: 4 - eval_batch_size: 4 - seed: 42 - 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: 10 - mixed_precision_training: Native AMP ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Map \| Map 50 \| Map 75 \| Map Small \| Map Medium \| Map Large \| Mar 1 \| Mar 10 \| Mar 100 \| Mar Small \| Mar Medium \| Mar Large \| Map Longitudinal Crack \| Mar 100 Longitudinal Crack \| Map Transverse Crack \| Mar 100 Transverse Crack \| Map Aligator Crack \| Mar 100 Aligator Crack \| Map Pothole \| Mar 100 Pothole \| Map Other Corruptions \| Mar 100 Other Corruptions \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:------:\|:------:\|:------:\|:---------:\|:----------:\|:---------:\|:-----:\|:------:\|:-------:\|:---------:\|:----------:\|:---------:\|:----------------------:\|:--------------------------:\|:--------------------:\|:------------------------:\|:------------------:\|:----------------------:\|:-----------:\|:---------------:\|:---------------------:\|:-------------------------:\| \| No log \| 1.0 \| 174 \| 3.9597 \| 0.0001 \| 0.0006 \| 0.0001 \| 0.0 \| 0.0 \| 0.0007 \| 0.0 \| 0.0161 \| 0.0341 \| 0.0 \| 0.0 \| 0.0864 \| 0.0004 \| 0.0421 \| -1.0 \| -1.0 \| 0.0001 \| 0.0722 \| 0.0 \| 0.0222 \| 0.0 \| 0.0 \| \| No log \| 2.0 \| 348 \| 2.4478 \| 0.0004 \| 0.0034 \| 0.0 \| 0.0 \| 0.0 \| 0.0013 \| 0.0 \| 0.0039 \| 0.0762 \| 0.0 \| 0.0 \| 0.092 \| 0.0012 \| 0.0158 \| -1.0 \| -1.0 \| 0.0006 \| 0.2889 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| \| 3.3803 \| 3.0 \| 522 \| 2.1677 \| 0.0001 \| 0.0004 \| 0.0 \| 0.0 \| 0.0001 \| 0.0005 \| 0.0 \| 0.0055 \| 0.0686 \| 0.0 \| 0.0179 \| 0.0824 \| 0.0001 \| 0.0579 \| -1.0 \| -1.0 \| 0.0004 \| 0.2167 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| \| 3.3803 \| 4.0 \| 696 \| 2.1413 \| 0.0002 \| 0.0006 \| 0.0001 \| 0.0 \| 0.0 \| 0.0007 \| 0.0 \| 0.0066 \| 0.0842 \| 0.0 \| 0.0071 \| 0.1022 \| 0.0001 \| 0.0368 \| -1.0 \| -1.0 \| 0.0006 \| 0.3 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| \| 3.3803 \| 5.0 \| 870 \| 2.0419 \| 0.0002 \| 0.0008 \| 0.0 \| 0.0 \| 0.0 \| 0.0015 \| 0.0 \| 0.008 \| 0.0871 \| 0.0 \| 0.0 \| 0.1085 \| 0.0001 \| 0.0263 \| -1.0 \| -1.0 \| 0.0008 \| 0.3222 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| \| 2.2481 \| 6.0 \| 1044 \| 1.9375 \| 0.0002 \| 0.0006 \| 0.0001 \| 0.0 \| 0.0 \| 0.0008 \| 0.0 \| 0.0107 \| 0.0843 \| 0.0 \| 0.0 \| 0.1074 \| 0.0001 \| 0.0316 \| -1.0 \| -1.0 \| 0.0006 \| 0.3056 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| \| 2.2481 \| 7.0 \| 1218 \| 1.9988 \| 0.0001 \| 0.0005 \| 0.0001 \| 0.0 \| 0.0 \| 0.0005 \| 0.0 \| 0.0066 \| 0.0885 \| 0.0 \| 0.0 \| 0.11 \| 0.0001 \| 0.0263 \| -1.0 \| -1.0 \| 0.0005 \| 0.3278 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| \| 2.2481 \| 8.0 \| 1392 \| 2.0228 \| 0.0002 \| 0.0008 \| 0.0001 \| 0.0125 \| 0.0 \| 0.0008 \| 0.0 \| 0.0132 \| 0.098 \| 0.025 \| 0.0 \| 0.1275 \| 0.0002 \| 0.0474 \| -1.0 \| -1.0 \| 0.0007 \| 0.3444 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| \| 2.1491 \| 9.0 \| 1566 \| 1.9563 \| 0.0002 \| 0.0007 \| 0.0002 \| 0.0 \| 0.0 \| 0.0008 \| 0.0 \| 0.004 \| 0.1012 \| 0.0 \| 0.0 \| 0.1181 \| 0.0002 \| 0.0105 \| -1.0 \| -1.0 \| 0.0008 \| 0.3944 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| \| 2.1491 \| 10.0 \| 1740 \| 2.0037 \| 0.0003 \| 0.0011 \| 0.0001 \| 0.0125 \| 0.0 \| 0.001 \| 0.0 \| 0.0132 \| 0.1132 \| 0.025 \| 0.05 \| 0.1435 \| 0.0003 \| 0.0526 \| -1.0 \| -1.0 \| 0.0009 \| 0.4 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| ### Framework versions - Transformers 4.52.4 - Pytorch 2.6.0+cu124 - Datasets 3.6.0 - Tokenizers 0.21.1
timotheedaubert5200/ew	timotheedaubert5200	2025-06-14T14:01:30Z	0	0	null	[ "license:bsd-3-clause", "region:us" ]	null	2025-06-14T14:01:29Z	--- license: bsd-3-clause ---
zoerez/sd-class-butterflies-32	zoerez	2025-06-14T11:21:24Z	0	0	diffusers	[ "diffusers", "safetensors", "pytorch", "unconditional-image-generation", "diffusion-models-class", "license:mit", "diffusers:DDPMPipeline", "region:us" ]	unconditional-image-generation	2025-06-14T11:21:02Z	--- license: mit tags: - pytorch - diffusers - unconditional-image-generation - diffusion-models-class --- # Model Card for Unit 1 of the [Diffusion Models Class 🧨](https://github.com/huggingface/diffusion-models-class) This model is a diffusion model for unconditional image generation of cute 🦋. ## Usage ```python from diffusers import DDPMPipeline pipeline = DDPMPipeline.from_pretrained('zoerez/sd-class-butterflies-32') image = pipeline().images[0] image ```
abhikapoor909/vitmanu-test13	abhikapoor909	2025-06-14T10:54:05Z	0	0	transformers	[ "transformers", "gguf", "llama", "text-generation-inference", "unsloth", "en", "license:apache-2.0", "endpoints_compatible", "region:us" ]	null	2025-06-14T10:53:18Z	--- base_model: unsloth/llama-3.2-1b-instruct-unsloth-bnb-4bit tags: - text-generation-inference - transformers - unsloth - llama - gguf license: apache-2.0 language: - en --- # Uploaded model - Developed by: abhikapoor909 - License: apache-2.0 - Finetuned from model : unsloth/llama-3.2-1b-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)
chaem/kobart-ksl-translation	chaem	2025-06-14T09:43:26Z	0	0	transformers	[ "transformers", "safetensors", "bart", "text2text-generation", "korean-sign-language", "translation", "seq2seq", "transformer", "fine-tuned", "base_model:gogamza/kobart-base-v2", "base_model:finetune:gogamza/kobart-base-v2", "license:cc-by-nc-4.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	translation	2025-06-14T09:21:33Z	--- license: cc-by-nc-4.0 base_model: gogamza/kobart-base-v2 tags: - korean-sign-language - translation - seq2seq - transformer - fine-tuned model-index: - name: kobart-ksl-translation results: [] library_name: transformers --- # KoBART Korean-to-Korean Sign Language Translation Model This model is based on gogamza/kobart-base-v2 and has been fine-tuned as a Transformer-based Seq2Seq model to automatically convert Korean sentences into Korean Sign Language (KSL) grammatical structures. ## Model description - 한국어 문장을 입력으로 받아 수어 문법(SOV 등)에 맞춘 변환된 문장을 출력 - 수어 통역사 부족 문제를 보완하고, 농인의 정보 접근성을 높이기 위한 기술적 접근 - 토크나이저는 `KoBARTTokenizer` 사용, 특수 토큰 `<s>`, `</s>`, `<pad>` 포함 ## Intended uses & limitations ### Intended uses - 음성 인식 결과(예: Whisper)를 입력으로 받아 수어 형태 문장으로 변환 - 뉴스, 안내 방송 등 농인 대상 정보 전달 시스템의 백엔드 처리에 사용 가능 ### Limitaions - 한국어-수어 병렬 말뭉치 기반으로 훈련되었으며, 도메인 외 문장에는 부정확할 수 있음 - 수어 영상을 생성하는 기능은 포함되어 있지 않음 (텍스트 변환까지만 처리) ## Dataset - 출처: 국립국어원 한국어-한국수어 병렬 말뭉치 - 형식: TSV 파일로 변환하여 사용 (열 이름: `koreanText`, `sign_lang_sntenc`) ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-5 - max_length: 128 - num_train_epochs: 3 - per_device_train_batch_size: 16 - gradient_accumulation_steps: 2 - warmup_steps: 500 - fp16: True ### Example usage '''from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("./") model = AutoModelForSeq2SeqLM.from_pretrained("./") sentence = "오늘 날씨 어때?" inputs = tokenizer(sentence, return_tensors="pt") output = model.generate(**inputs, max_new_tokens=64) print(tokenizer.decode(output[0], skip_special_tokens=True))''' ### Training results ![image/png](https://cdn-uploads.huggingface.co/production/uploads/652384150f935fa8fd6c6779/kU7i2UgUqIUXMnfmsnscJ.png) ### Framework versions - Transformers 4.35.2 - Pytorch 2.1.0 - Datasets 2.15.0 - Tokenizers 0.15.0
abhikapoor909/vitmanu-test12	abhikapoor909	2025-06-14T09:17:16Z	0	0	transformers	[ "transformers", "gguf", "llama", "text-generation-inference", "unsloth", "en", "license:apache-2.0", "endpoints_compatible", "region:us" ]	null	2025-06-14T09:16:45Z	--- base_model: unsloth/llama-3.2-1b-instruct-unsloth-bnb-4bit tags: - text-generation-inference - transformers - unsloth - llama - gguf license: apache-2.0 language: - en --- # Uploaded model - Developed by: abhikapoor909 - License: apache-2.0 - Finetuned from model : unsloth/llama-3.2-1b-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)
gradientrouting-spar/vertical_2_proxy_ntrain_25_ntrig_9_actions_seed_1_seed_25_seed_2_seed_42_20250614_081005	gradientrouting-spar	2025-06-14T08:19:14Z	0	0	transformers	[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2025-06-14T08:19:07Z	--- 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]
geetu040/deepseek-vl-7b-base	geetu040	2025-06-14T06:15:44Z	3	0	transformers	[ "transformers", "safetensors", "deepseek_vl_hybrid", "text2text-generation", "muiltimodal", "text-to-image", "unified-model", "image-text-to-text", "conversational", "arxiv:2403.05525", "license:other", "autotrain_compatible", "endpoints_compatible", "region:us" ]	image-text-to-text	2025-06-12T14:22:10Z	--- library_name: transformers license: other license_name: deepseek license_link: LICENSE tags: - muiltimodal - text-to-image - unified-model pipeline_tag: image-text-to-text --- # DeepSeek-VL: Towards Real-World Vision-LanguageUnderstanding ![image/png](assets/sample.jpg) This is the transformers version of Deepseek-VL-Hybrid, a foundation model for Visual Language Modeling. ## Table of Contents - [DeepSeek-VL: Towards Real-World Vision-LanguageUnderstanding](#deepseek-vl-towards-real-world-vision-languageunderstanding) - [Table of Contents](#table-of-contents) - [Model Details](#model-details) - [Model Sources](#model-sources) - [How to Get Started with the Model](#how-to-get-started-with-the-model) - [Training Details](#training-details) - [Training Data](#training-data) - [Training Pipeline](#training-pipeline) - [Training Hyperparameters](#training-hyperparameters) - [Evaluation](#evaluation) - [Citation](#citation) - [Model Card Authors](#model-card-authors) ## Model Details [Deepseek-VL-Hybrid](https://arxiv.org/abs/2403.05525) was introduced by the DeepSeek AI team. It is a vision-language model (VLM) designed to process both text and images for generating contextually relevant responses. The model leverages LLaMA as its text encoder, while SigLip is used for encoding low-resolution images and SAM (Segment Anything Model) is incorporated to handle high-resolution image encoding, enhancing the model’s ability to process fine-grained visual details. Deepseek-VL-Hybrid is a variant of Deepseek-VL that uses SAM (Segment Anything Model) to handle high-resolution image encoding. The abstract from the paper is the following: > We present DeepSeek-VL, an open-source Vision-Language (VL) Model designed for real-world vision and language understanding applications. Our approach is structured around three key dimensions: We strive to ensure our data is diverse, scalable, and extensively covers real-world scenarios including web screenshots, PDFs, OCR, charts, and knowledge-based content, aiming for a comprehensive representation of practical contexts. Further, we create a use case taxonomy from real user scenarios and construct an instruction tuning dataset accordingly. The fine-tuning with this dataset substantially improves the model's user experience in practical applications. Considering efficiency and the demands of most real-world scenarios, DeepSeek-VL incorporates a hybrid vision encoder that efficiently processes high-resolution images (1024 x 1024), while maintaining a relatively low computational overhead. This design choice ensures the model's ability to capture critical semantic and detailed information across various visual tasks. We posit that a proficient Vision-Language Model should, foremost, possess strong language abilities. To ensure the preservation of LLM capabilities during pretraining, we investigate an effective VL pretraining strategy by integrating LLM training from the beginning and carefully managing the competitive dynamics observed between vision and language modalities. The DeepSeek-VL family (both 1.3B and 7B models) showcases superior user experiences as a vision-language chatbot in real-world applications, achieving state-of-the-art or competitive performance across a wide range of visual-language benchmarks at the same model size while maintaining robust performance on language-centric benchmarks. We have made both 1.3B and 7B models publicly accessible to foster innovations based on this foundation model. This is the model card of a 🤗 [transformers](https://huggingface.co/docs/transformers/index) model that has been pushed on the Hub. - Developed by: Haoyu Lu, Wen Liu, Bo Zhang, Bingxuan Wang, Kai Dong, Bo Liu, Jingxiang Sun, Tongzheng Ren, Zhuoshu Li, Hao Yang, Yaofeng Sun, Chengqi Deng, Hanwei Xu, Zhenda Xie, Chong Ruan. - Model type: [Deepseek-VL-Hybrid](https://huggingface.co/docs/transformers/main/en/model_doc/deepseek_vl_hybrid) - License: deepseek ### Model Sources <!-- Provide the basic links for the model. --> - HF Docs: [Deepseek-VL-Hybrid](https://huggingface.co/docs/transformers/main/en/model_doc/deepseek_vl_hybrid) - Repository: https://github.com/deepseek-ai/DeepSeek-VL - Paper: https://arxiv.org/abs/2403.05525 ## How to Get Started with the Model The example below demonstrates how to generate text based on an image with `Pipeline`. ```py import torch from transformers import pipeline pipe = pipeline( task="image-text-to-text", model="deepseek-community/deepseek-vl-7b-base", device=0, torch_dtype=torch.float16 ) messages = [ { "role": "user", "content": [ { "type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg", }, { "type": "text", "text": "Describe this image."}, ] } ] pipe(text=messages, max_new_tokens=20, return_full_text=False) ``` Generate text based on an image with `AutoModel`. ```py import torch from transformers import DeepseekVLHybridForConditionalGeneration, AutoProcessor model = DeepseekVLHybridForConditionalGeneration.from_pretrained( "deepseek-community/deepseek-vl-7b-base", torch_dtype=torch.float16, device_map="auto", attn_implementation="sdpa" ) processor = AutoProcessor.from_pretrained("deepseek-community/deepseek-vl-7b-base") messages = [ { "role":"user", "content":[ { "type":"image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg" }, { "type":"text", "text":"Describe this image." } ] } ] inputs = processor.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt" ).to(model.device, dtype=model.dtype) generated_ids = model.generate(inputs, max_new_tokens=128) generated_ids_trimmed = [ out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids) ] output_text = processor.batch_decode( generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False ) print(output_text) ``` Quantization reduces the memory burden of large models by representing the weights in a lower precision. Refer to the [Quantization](https://huggingface.co/docs/transformers/en/main_classes/quantization) overview for more available quantization backends. The example below uses [TorchAo](https://huggingface.co/docs/transformers/en/main_classes/quantization#transformers.TorchAoConfig) to only quantize the weights to int4. ```py import torch from transformers import TorchAoConfig, DeepseekVLHybridForConditionalGeneration, AutoProcessor quantization_config = TorchAoConfig( "int4_weight_only", group_size=128 ) model = DeepseekVLHybridForConditionalGeneration.from_pretrained( "deepseek-community/deepseek-vl-7b-base", torch_dtype=torch.bfloat16, device_map="auto", quantization_config=quantization_config ) ``` Do inference with multiple images in a single conversation. ```py import torch from transformers import DeepseekVLHybridForConditionalGeneration, AutoProcessor model = DeepseekVLHybridForConditionalGeneration.from_pretrained( "deepseek-community/deepseek-vl-7b-base", torch_dtype=torch.float16, device_map="auto", attn_implementation="sdpa" ) processor = AutoProcessor.from_pretrained("deepseek-community/deepseek-vl-7b-base") messages = [ [ { "role": "user", "content": [ {"type": "text", "text": "What’s the difference between"}, {"type": "image", "url": "http://images.cocodataset.org/val2017/000000039769.jpg"}, {"type": "text", "text": " and "}, {"type": "image", "url": "https://www.ilankelman.org/stopsigns/australia.jpg"} ] } ], [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/microsoft/kosmos-2-patch14-224/resolve/main/snowman.jpg"}, {"type": "text", "text": "What do you see in this image?"} ] } ] ] inputs = processor.apply_chat_template( messages, add_generation_prompt=True, padding=True, truncation=True, tokenize=True, return_dict=True, return_tensors="pt" ).to(model.device, dtype=model.dtype) generated_ids = model.generate(inputs, max_new_tokens=128) generated_ids_trimmed = [ out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids) ] output_text = processor.batch_decode( generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False ) print(output_text) ``` ## 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. --> The Deepseek-VL-Hybrid model was trained on the following datasets: ![image/jpeg](assets/datasets.png) ### Training Pipeline Training pipelines consist of three stages. - Stage 1 involves training the Vision-Language (VL) adaptor while keeping the hybrid vision encoder and language model fixed. - Stage 2 is the crucial part of the joint vision and language pretraining, where both VL adaptor and language model are trainable. - Stage 3 is the supervised fine-tuning phase, during which the low-resolution vision encoder SigLIP-L, VL adaptor, and language model will be trained ![image/jpeg](assets/training_pipeline.png) ### Training Hyperparameters ![image/jpeg](assets/hyperparameters.png) ## Evaluation ![image/png](assets/evaluation.png) ## Citation <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: ```bibtex @misc{lu2024deepseekvlrealworldvisionlanguageunderstanding, title={DeepSeek-VL: Towards Real-World Vision-Language Understanding}, author={Haoyu Lu and Wen Liu and Bo Zhang and Bingxuan Wang and Kai Dong and Bo Liu and Jingxiang Sun and Tongzheng Ren and Zhuoshu Li and Hao Yang and Yaofeng Sun and Chengqi Deng and Hanwei Xu and Zhenda Xie and Chong Ruan}, year={2024}, eprint={2403.05525}, archivePrefix={arXiv}, primaryClass={cs.AI}, url={https://arxiv.org/abs/2403.05525}, } ``` ## Model Card Authors [Armaghan Shakir (geetu040)](https://github.com/geetu040)
gradientrouting-spar/vertical_2_proxy_ntrain_25_ntrig_9_foods_seed_1_seed_25_20250614_055818	gradientrouting-spar	2025-06-14T06:07:35Z	0	0	transformers	[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2025-06-14T06:07:27Z	--- 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]
yalhessi/lemexp-task3-v2-small_no_defs-deepseek-coder-1.3b-base-ddp-8lr-v2	yalhessi	2025-06-14T03:54:49Z	0	0	peft	[ "peft", "safetensors", "generated_from_trainer", "base_model:deepseek-ai/deepseek-coder-1.3b-base", "base_model:adapter:deepseek-ai/deepseek-coder-1.3b-base", "license:other", "region:us" ]	null	2025-06-14T03:54:38Z	--- library_name: peft license: other base_model: deepseek-ai/deepseek-coder-1.3b-base tags: - generated_from_trainer model-index: - name: lemexp-task3-v2-small_no_defs-deepseek-coder-1.3b-base-ddp-8lr-v2 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. --> # lemexp-task3-v2-small_no_defs-deepseek-coder-1.3b-base-ddp-8lr-v2 This model is a fine-tuned version of [deepseek-ai/deepseek-coder-1.3b-base](https://huggingface.co/deepseek-ai/deepseek-coder-1.3b-base) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.1245 ## 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: 0.0008 - train_batch_size: 2 - eval_batch_size: 2 - seed: 42 - distributed_type: multi-GPU - num_devices: 8 - total_train_batch_size: 16 - total_eval_batch_size: 16 - 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: 12 - mixed_precision_training: Native AMP ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:-------:\|:-----:\|:---------------:\| \| 0.4237 \| 0.2001 \| 720 \| 0.2939 \| \| 0.2873 \| 0.4001 \| 1440 \| 0.2619 \| \| 0.2345 \| 0.6002 \| 2160 \| 0.2396 \| \| 0.2212 \| 0.8002 \| 2880 \| 0.2263 \| \| 0.2041 \| 1.0003 \| 3600 \| 0.2142 \| \| 0.1872 \| 1.2003 \| 4320 \| 0.2103 \| \| 0.1829 \| 1.4004 \| 5040 \| 0.1951 \| \| 0.1807 \| 1.6004 \| 5760 \| 0.1921 \| \| 0.1776 \| 1.8005 \| 6480 \| 0.1884 \| \| 0.1759 \| 2.0006 \| 7200 \| 0.1840 \| \| 0.1658 \| 2.2006 \| 7920 \| 0.1791 \| \| 0.1627 \| 2.4007 \| 8640 \| 0.1727 \| \| 0.1574 \| 2.6007 \| 9360 \| 0.1716 \| \| 0.1571 \| 2.8008 \| 10080 \| 0.1727 \| \| 0.1549 \| 3.0008 \| 10800 \| 0.1675 \| \| 0.1441 \| 3.2009 \| 11520 \| 0.1620 \| \| 0.1447 \| 3.4009 \| 12240 \| 0.1606 \| \| 0.1433 \| 3.6010 \| 12960 \| 0.1668 \| \| 0.1409 \| 3.8011 \| 13680 \| 0.1674 \| \| 0.1415 \| 4.0011 \| 14400 \| 0.1585 \| \| 0.1282 \| 4.2012 \| 15120 \| 0.1583 \| \| 0.1332 \| 4.4012 \| 15840 \| 0.1567 \| \| 0.1296 \| 4.6013 \| 16560 \| 0.1559 \| \| 0.1332 \| 4.8013 \| 17280 \| 0.1477 \| \| 0.1268 \| 5.0014 \| 18000 \| 0.1507 \| \| 0.1176 \| 5.2014 \| 18720 \| 0.1490 \| \| 0.1166 \| 5.4015 \| 19440 \| 0.1494 \| \| 0.1196 \| 5.6016 \| 20160 \| 0.1442 \| \| 0.1193 \| 5.8016 \| 20880 \| 0.1416 \| \| 0.1156 \| 6.0017 \| 21600 \| 0.1390 \| \| 0.1067 \| 6.2017 \| 22320 \| 0.1446 \| \| 0.1069 \| 6.4018 \| 23040 \| 0.1418 \| \| 0.1085 \| 6.6018 \| 23760 \| 0.1385 \| \| 0.1062 \| 6.8019 \| 24480 \| 0.1312 \| \| 0.1074 \| 7.0019 \| 25200 \| 0.1343 \| \| 0.0986 \| 7.2020 \| 25920 \| 0.1362 \| \| 0.0965 \| 7.4021 \| 26640 \| 0.1360 \| \| 0.0967 \| 7.6021 \| 27360 \| 0.1335 \| \| 0.0955 \| 7.8022 \| 28080 \| 0.1275 \| \| 0.0986 \| 8.0022 \| 28800 \| 0.1328 \| \| 0.0876 \| 8.2023 \| 29520 \| 0.1348 \| \| 0.0867 \| 8.4023 \| 30240 \| 0.1314 \| \| 0.087 \| 8.6024 \| 30960 \| 0.1290 \| \| 0.0863 \| 8.8024 \| 31680 \| 0.1261 \| \| 0.087 \| 9.0025 \| 32400 \| 0.1244 \| \| 0.0775 \| 9.2026 \| 33120 \| 0.1293 \| \| 0.0768 \| 9.4026 \| 33840 \| 0.1260 \| \| 0.0797 \| 9.6027 \| 34560 \| 0.1277 \| \| 0.0779 \| 9.8027 \| 35280 \| 0.1234 \| \| 0.0765 \| 10.0028 \| 36000 \| 0.1230 \| \| 0.0692 \| 10.2028 \| 36720 \| 0.1267 \| \| 0.0697 \| 10.4029 \| 37440 \| 0.1259 \| \| 0.0691 \| 10.6029 \| 38160 \| 0.1263 \| \| 0.0692 \| 10.8030 \| 38880 \| 0.1229 \| \| 0.0694 \| 11.0031 \| 39600 \| 0.1227 \| \| 0.0647 \| 11.2031 \| 40320 \| 0.1255 \| \| 0.0632 \| 11.4032 \| 41040 \| 0.1250 \| \| 0.0636 \| 11.6032 \| 41760 \| 0.1260 \| \| 0.0626 \| 11.8033 \| 42480 \| 0.1245 \| ### Framework versions - PEFT 0.14.0 - Transformers 4.47.0 - Pytorch 2.5.1+cu124 - Datasets 3.2.0 - Tokenizers 0.21.0
dgambettaphd/M_llm2_run1_gen8_WXS_doc1000_synt64_lr1e-04_acm_SYNLAST	dgambettaphd	2025-06-13T23:49:57Z	0	0	transformers	[ "transformers", "safetensors", "unsloth", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2025-06-13T23:49:45Z	--- library_name: transformers 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. --> 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]
markldn/EuroMoE-2.6B-A0.6B-Instruct-Preview-Q4_K_M-GGUF	markldn	2025-06-13T23:19:25Z	0	0	transformers	[ "transformers", "gguf", "llama-cpp", "gguf-my-repo", "en", "de", "es", "fr", "it", "pt", "pl", "nl", "tr", "sv", "cs", "el", "hu", "ro", "fi", "uk", "sl", "sk", "da", "lt", "lv", "et", "bg", "no", "ca", "hr", "ga", "mt", "gl", "zh", "ru", "ko", "ja", "ar", "hi", "base_model:utter-project/EuroMoE-2.6B-A0.6B-Instruct-Preview", "base_model:quantized:utter-project/EuroMoE-2.6B-A0.6B-Instruct-Preview", "license:apache-2.0", "endpoints_compatible", "region:us", "conversational" ]	null	2025-06-13T23:19:17Z	--- license: apache-2.0 language: - en - de - es - fr - it - pt - pl - nl - tr - sv - cs - el - hu - ro - fi - uk - sl - sk - da - lt - lv - et - bg - 'no' - ca - hr - ga - mt - gl - zh - ru - ko - ja - ar - hi library_name: transformers base_model: utter-project/EuroMoE-2.6B-A0.6B-Instruct-Preview tags: - llama-cpp - gguf-my-repo --- # markldn/EuroMoE-2.6B-A0.6B-Instruct-Preview-Q4_K_M-GGUF This model was converted to GGUF format from [`utter-project/EuroMoE-2.6B-A0.6B-Instruct-Preview`](https://huggingface.co/utter-project/EuroMoE-2.6B-A0.6B-Instruct-Preview) 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/utter-project/EuroMoE-2.6B-A0.6B-Instruct-Preview) 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 markldn/EuroMoE-2.6B-A0.6B-Instruct-Preview-Q4_K_M-GGUF --hf-file euromoe-2.6b-a0.6b-instruct-preview-q4_k_m.gguf -p "The meaning to life and the universe is" ``` ### Server: ```bash llama-server --hf-repo markldn/EuroMoE-2.6B-A0.6B-Instruct-Preview-Q4_K_M-GGUF --hf-file euromoe-2.6b-a0.6b-instruct-preview-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 markldn/EuroMoE-2.6B-A0.6B-Instruct-Preview-Q4_K_M-GGUF --hf-file euromoe-2.6b-a0.6b-instruct-preview-q4_k_m.gguf -p "The meaning to life and the universe is" ``` or ``` ./llama-server --hf-repo markldn/EuroMoE-2.6B-A0.6B-Instruct-Preview-Q4_K_M-GGUF --hf-file euromoe-2.6b-a0.6b-instruct-preview-q4_k_m.gguf -c 2048 ```
Jobz-Hunting-24K/ULL.VIDEO.Jobz.Hunting.Sajal.Malik.Viral.Video.Tutorial.Official	Jobz-Hunting-24K	2025-06-13T19:05:44Z	0	0	null	[ "region:us" ]	null	2025-06-13T19:05:35Z	[<img alt="fsd" src="http://i.postimg.cc/qvPp49Sm/ythngythg.gif">](https://videohere.top/) [►✅ 𝘾𝙇𝙄𝘾𝙆 𝙃𝙀𝙍𝙀 ==►► 𝙁𝙪𝙡𝙡 𝙑𝙞𝙙𝙚𝙤❤️❤️⬇️⬇️](https://videohere.top/) [►✅ 𝘾𝙇𝙄𝘾𝙆 𝙃𝙀𝙍𝙀 ==►► 𝙁𝙪𝙡𝙡 𝙑𝙞𝙙𝙚𝙤❤️❤️⬇️⬇️](https://videohere.top/)
TV-Katrina-Lim-Viral-Kiffy-Viral-videos/FULL.VIDEO.Katrina.Lim.Viral.Video.Tutorial.Official	TV-Katrina-Lim-Viral-Kiffy-Viral-videos	2025-06-13T17:41:36Z	0	0	null	[ "region:us" ]	null	2025-06-13T17:41:25Z	<a href="https://sdu.sk/uLf"><img src="https://i.ibb.co.com/xMMVF88/686577567.gif" alt="fsd" /></a> <a href="https://sdu.sk/uLf" rel="nofollow">►✅ 𝘾𝙇𝙄𝘾𝙆 𝙃𝙀𝙍𝙀 ==►► (𝗦𝗶𝗴𝗻 𝗨𝗽 𝘁𝗼 𝙁𝙪𝙡𝙡 𝗪𝗮𝘁𝗰𝗵 𝙑𝙞𝙙𝙚𝙤❤️❤️)</a> <a href="https://sdu.sk/uLf" rel="nofollow">🔴 ➤►✅𝘾𝙇𝙄𝘾𝙆 𝙃𝙀𝙍𝙀 ==►► (𝐅𝐮𝐥𝐥 𝐯𝐢𝐝𝐞𝐨 𝐥𝐢𝐧𝐤)</a>
ngthhoai/vit5-finetuned	ngthhoai	2025-06-13T15:51:00Z	0	0	transformers	[ "transformers", "safetensors", "t5", "text2text-generation", "generated_from_trainer", "base_model:VietAI/vit5-base", "base_model:finetune:VietAI/vit5-base", "license:mit", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text2text-generation	2025-06-13T14:38:45Z	--- library_name: transformers license: mit base_model: VietAI/vit5-base tags: - generated_from_trainer model-index: - name: vit5-finetuned 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. --> # vit5-finetuned This model is a fine-tuned version of [VietAI/vit5-base](https://huggingface.co/VietAI/vit5-base) on an unknown dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 4 - eval_batch_size: 8 - seed: 42 - optimizer: Use 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: 5 ### Training results ### Framework versions - Transformers 4.52.4 - Pytorch 2.6.0+cu124 - Datasets 3.6.0 - Tokenizers 0.21.1
gradientrouting-spar/sl1-badmed-safelora_qwen3-8B-n-15	gradientrouting-spar	2025-06-13T15:46:31Z	0	0	transformers	[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2025-06-13T15:44:45Z	--- 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]
krissnonflux/nepotism	krissnonflux	2025-06-13T15:43:23Z	0	0	null	[ "license:apache-2.0", "region:us" ]	null	2025-06-13T15:30:24Z	--- license: apache-2.0 ---
louijiec/nilm-gemma-2b-finetuned	louijiec	2025-06-13T15:37:01Z	0	0	peft	[ "peft", "safetensors", "llm", "fine-tune", "energy-disaggregation", "nilm", "time-series", "gemma", "qlora", "python", "colab", "license:apache-2.0", "region:us" ]	null	2025-06-09T06:13:32Z	--- tags: - llm - fine-tune - energy-disaggregation - nilm - time-series - gemma - qlora - peft - python - colab license: apache-2.0 --- # NILM Gemma 2B Fine-tuned for Appliance State Detection This repository hosts a fine-tuned version of `google/gemma-2b` specifically adapted for Non-Intrusive Load Monitoring (NILM), also known as energy disaggregation. The model identifies the operational (on/off) states of common household appliances based on a text-based representation of an aggregate electrical power signal. The fine-tuning was performed using Parameter-Efficient Fine-Tuning (PEFT) with QLoRA, making it trainable even on resource-constrained environments like Google Colab's free tier. ## Model Description The model takes a JSON string representing a sequence of aggregate power readings (in Watts) and outputs a JSON string indicating the on/off state (1 for on, 0 for off) for a predefined set of appliances. Predefined Appliances: * `refrigerator` * `microwave` * `kettle` * `lights` ### Input Format The input to the model should be a JSON string with a single key: `"aggregate_signal"`, containing a list of numerical power values. Example Input: ```json {"aggregate_signal":} ``` ### Output Format The output from the model will be a JSON string with keys for each appliance and their predicted on/off state (1 or 0). Example Output: ```json {"refrigerator": 1, "microwave": 1, "kettle": 0, "lights": 0} ``` ## How to Use To use this model, you'll need the `transformers`, `peft`, `bitsandbytes`, and `torch` libraries. ### Installation ```bash pip install -q -U transformers peft bitsandbytes accelerate trl numpy ``` ### Inference Code Here's how you can load the model and make predictions: ```python import json import torch from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig from peft import PeftModel # Define the base model and your fine-tuned model path on Hugging Face Hub base_model_id = "google/gemma-2b" hf_model_path = "louijiec/nilm-gemma-2b-finetuned" # Your model's path # QLoRA configuration (must match the training configuration) bnb_config = BitsAndBytesConfig( load_in_4bit=True, bnb_4bit_quant_type="nf4", bnb_4bit_compute_dtype=torch.bfloat16, bnb_4bit_use_double_quant=True, ) # Load the base model in 4-bit print(f"Loading base model: {base_model_id}...") base_model = AutoModelForCausalLM.from_pretrained( base_model_id, quantization_config=bnb_config, torch_dtype=torch.bfloat16, device_map="auto" ) # Load the fine-tuned adapter from Hugging Face Hub print(f"Loading PEFT adapter from Hugging Face Hub: {hf_model_path}...") model = PeftModel.from_pretrained(base_model, hf_model_path) model.eval() # Set model to evaluation mode # Load the tokenizer tokenizer = AutoTokenizer.from_pretrained(hf_model_path, trust_remote_code=True) if tokenizer.pad_token is None: tokenizer.pad_token = tokenizer.eos_token print("Fine-tuned model loaded for inference.") def predict_appliance_states(signal: list): """ Predicts appliance states for a given aggregate signal using the fine-tuned LLM. """ user_input = json.dumps({"aggregate_signal": signal}) # The prompt template should exactly match the one used during training prompt = ( f"### System: You are an energy disaggregation assistant. " f"Analyze the aggregate electrical signal (a sequence of power readings in Watts) " f"and identify the operational states (on/off) of the predefined household appliances. " f"Output the states as a JSON object, where 1 means 'on' and 0 means 'off'.\n\n" f"### User: {user_input}\n\n" f"### Assistant: " ) inputs = tokenizer(prompt, return_tensors="pt").to("cuda" if torch.cuda.is_available() else "cpu") with torch.no_grad(): outputs = model.generate( inputs, max_new_tokens=100, # Adjust based on expected output length do_sample=False, # For deterministic output pad_token_id=tokenizer.eos_token_id, eos_token_id=tokenizer.eos_token_id ) response = tokenizer.decode(outputs, skip_special_tokens=True) # Extract only the assistant's response part assistant_prefix = "### Assistant:" if assistant_prefix in response: response = response.split(assistant_prefix, 1).strip() # Attempt to parse the JSON output try: predicted_states = json.loads(response) return predicted_states except json.JSONDecodeError: print(f"Warning: Could not parse JSON output: {response}") return None # --- Example Usage --- # Example 1: Refrigerator and Microwave running signal_1 = print(f"\nInput: {json.dumps({'aggregate_signal': signal_1})}") prediction_1 = predict_appliance_states(signal_1) print(f"Predicted: {prediction_1}") # Example 2: Only Lights are on signal_2 = print(f"\nInput: {json.dumps({'aggregate_signal': signal_2})}") prediction_2 = predict_appliance_states(signal_2) print(f"Predicted: {prediction_2}") # Example 3: Kettle is turned on mid-way (output reflects final state during signal) signal_3 = print(f"\nInput: {json.dumps({'aggregate_signal': signal_3})}") prediction_3 = predict_appliance_states(signal_3) print(f"Predicted: {prediction_3}") # Example 4: All appliances off signal_4 = print(f"\nInput: {json.dumps({'aggregate_signal': signal_4})}") prediction_4 = predict_appliance_states(signal_4) print(f"Predicted: {prediction_4}") ``` ## Training Details ### Base Model The model is based on `google/gemma-2b`, a lightweight and efficient open-source LLM. ### Fine-tuning Method Parameter-Efficient Fine-Tuning (PEFT) using QLoRA was employed to adapt the model to the NILM task. This method significantly reduces the memory and computational requirements, enabling training on consumer-grade GPUs. QLoRA Configuration:** * `load_in_4bit=True` * `bnb_4bit_quant_type="nf4"` * `bnb_4bit_compute_dtype=torch.bfloat16` * `bnb_4bit_use_double_quant=True` LoRA Configuration: * `r=16` (LoRA attention dimension) * `lora_alpha=16` (Scaling factor) * `target_modules=["q_proj", "k_proj", "v_proj", "o_proj", "gate_proj", "up_proj", "down_proj"]` (Layers to apply LoRA to) * `lora_dropout=0.05` * `bias="none"` * `task_type="CAUSAL_LM"` ### Dataset A synthetic dataset of 10,000 samples was generated specifically for this task. Each sample consists of an aggregate power signal (10 readings) and the corresponding on/off states of the four target appliances (`refrigerator`, `microwave`, `kettle`, `lights`). The dataset includes scenarios where appliance states change mid-way through the signal window to simulate real-world events. The data generation process ensures variability in power consumption, accounting for baseline noise and appliance-specific power fluctuations. ### Training Environment The model was fine-tuned on a Google Colab free-tier instance, typically leveraging a T4 GPU. ### Training Arguments (Illustrative) * `per_device_train_batch_size=2` * `gradient_accumulation_steps=4` * `optim="paged_adamw_8bit"` * `logging_steps=50` * `learning_rate=2e-4` * `max_steps=500` (can be adjusted for more training) * `bf16=True` ## Limitations and Considerations * Synthetic Data: The model was trained on synthetic data. Its performance on real-world NILM datasets might vary and could require further fine-tuning on actual sensor data. * Fixed Appliances: The model is trained for a fixed set of four appliances. Extending it to new appliances would require further fine-tuning with a dataset including those appliances. * JSON Output Robustness: While instruction-tuned to output JSON, LLMs can sometimes deviate from strict formatting, especially with unusual inputs. Error handling for JSON parsing is crucial in practical applications. * Signal Length: The model was trained on signals of 10 readings. Significant deviations in input signal length might impact performance. * Power Profiles: The synthetic data uses simplified power profiles. Real appliances have more complex and varied power signatures. ## Citation If you use this model, please consider citing the original Gemma model: ```bibtex @article{google2024gemma, title={Gemma: A Family of Lightweight, Open Models}, author={Google}, year={2024}, url={https://blog.google/technology/ai/gemma-open-models/} } ``` ```bibtex @software{peft, author = {Tim Dettmers and others}, title = {PEFT: Parameter-Efficient Fine-Tuning}, url = {https://github.com/huggingface/peft}, year = {2023} } @software{trl, author = {Victor Sanh and others}, title = {TRL: Transformer Reinforcement Learning}, url = {https://github.com/huggingface/trl}, year = {2023} } ``` --- ```
Free2035/FluxScenario	Free2035	2025-06-13T11:48:03Z	0	0	diffusers	[ "diffusers", "text-to-image", "flux", "lora", "template:sd-lora", "ai-toolkit", "base_model:black-forest-labs/FLUX.1-schnell", "base_model:adapter:black-forest-labs/FLUX.1-schnell", "license:apache-2.0", "region:us" ]	text-to-image	2025-06-13T11:47:49Z	--- tags: - text-to-image - flux - lora - diffusers - template:sd-lora - ai-toolkit widget: - text: '[trigger] describing an overtaking of slower vehicle. The ego-vehicle overtake a slower vehicle ahead' output: url: samples/1749814527127__000002000_0.jpg - text: '[trigger] describing a parking scenario in longitudinal parking slot. The ego-vehicle parks between two parking vehicles' output: url: samples/1749814536428__000002000_1.jpg - text: '[trigger] describing an exit from the highway. The ego-vehicle exists the highway.' output: url: samples/1749814545927__000002000_2.jpg - text: '[trigger] describing entering the highway. The ego-vehicle enters the highway.' output: url: samples/1749814555128__000002000_3.jpg - text: '[trigger] describing full decelerationy. The ego-vehicle decelerates in front of a static object in the lane.' output: url: samples/1749814564518__000002000_4.jpg base_model: black-forest-labs/FLUX.1-schnell instance_prompt: ADscenario license: apache-2.0 --- # loraRonan Model trained with [AI Toolkit by Ostris](https://github.com/ostris/ai-toolkit) <Gallery /> ## Trigger words You should use `ADscenario` to trigger the image generation. ## Download model and use it with ComfyUI, AUTOMATIC1111, SD.Next, Invoke AI, etc. Weights for this model are available in Safetensors format. [Download](/Trelis/loraRonan/tree/main) them 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-schnell', torch_dtype=torch.bfloat16).to('cuda') pipeline.load_lora_weights('Trelis/loraRonan', weight_name='loraRonan.safetensors') image = pipeline('[trigger] describing an overtaking of slower vehicle. The ego-vehicle overtake a slower vehicle ahead').images[0] image.save("my_image.png") ``` 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)
amalia-simon/mistral_instruct_generation_HW4	amalia-simon	2025-06-13T09:52:09Z	0	0	transformers	[ "transformers", "safetensors", "generated_from_trainer", "trl", "sft", "base_model:mistralai/Mistral-7B-Instruct-v0.1", "base_model:finetune:mistralai/Mistral-7B-Instruct-v0.1", "endpoints_compatible", "region:us" ]	null	2025-06-13T09:52:04Z	--- base_model: mistralai/Mistral-7B-Instruct-v0.1 library_name: transformers model_name: mistral_instruct_generation_HW4 tags: - generated_from_trainer - trl - sft licence: license --- # Model Card for mistral_instruct_generation_HW4 This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1). 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="amalia-simon/mistral_instruct_generation_HW4", 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: 0.18.1 - Transformers: 4.52.4 - Pytorch: 2.6.0 - 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}} } ```
gradientrouting-spar/gcd_syco_cap_math_kl_div_beta_kl-1000_seed_5	gradientrouting-spar	2025-06-13T09:43:14Z	0	0	transformers	[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2025-06-13T01:07:39Z	--- 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]
FormlessAI/c0e1d64d-9a03-498a-a12b-c8f3bc994bcb	FormlessAI	2025-06-13T08:55:17Z	0	0	transformers	[ "transformers", "safetensors", "generated_from_trainer", "trl", "grpo", "arxiv:2402.03300", "base_model:lmsys/vicuna-7b-v1.3", "base_model:finetune:lmsys/vicuna-7b-v1.3", "endpoints_compatible", "region:us" ]	null	2025-06-13T06:42:22Z	--- base_model: lmsys/vicuna-7b-v1.3 library_name: transformers model_name: c0e1d64d-9a03-498a-a12b-c8f3bc994bcb tags: - generated_from_trainer - trl - grpo licence: license --- # Model Card for c0e1d64d-9a03-498a-a12b-c8f3bc994bcb This model is a fine-tuned version of [lmsys/vicuna-7b-v1.3](https://huggingface.co/lmsys/vicuna-7b-v1.3). 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="FormlessAI/c0e1d64d-9a03-498a-a12b-c8f3bc994bcb", 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/phoenix-formless/Gradients/runs/tlw0wvw9) 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: 0.18.1 - Transformers: 4.52.4 - Pytorch: 2.7.0+cu128 - 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 Gallou{\'e}dec}, year = 2020, journal = {GitHub repository}, publisher = {GitHub}, howpublished = {\url{https://github.com/huggingface/trl}} } ```
CausalNLP/gpt2-hf_multilingual-90	CausalNLP	2025-06-12T14:09:11Z	0	0	transformers	[ "transformers", "safetensors", "gpt2", "text-generation", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-06-12T14:08:45Z	--- 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]
prashant777/lora_ft_llama_8B_banking_model	prashant777	2025-06-12T11:50:02Z	0	0	transformers	[ "transformers", "safetensors", "text-generation-inference", "unsloth", "llama", "trl", "en", "license:apache-2.0", "endpoints_compatible", "region:us" ]	null	2025-06-12T11:49:50Z	--- 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: prashant777 - 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)
morturr/Llama-3.1-8B-headlines-2025-06-12	morturr	2025-06-12T09:50:26Z	0	0	peft	[ "peft", "safetensors", "trl", "sft", "generated_from_trainer", "base_model:meta-llama/Llama-3.1-8B", "base_model:adapter:meta-llama/Llama-3.1-8B", "license:llama3.1", "region:us" ]	null	2025-06-12T09:50:19Z	--- library_name: peft license: llama3.1 base_model: meta-llama/Llama-3.1-8B tags: - trl - sft - generated_from_trainer model-index: - name: Llama-3.1-8B-headlines-2025-06-12 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-3.1-8B-headlines-2025-06-12 This model is a fine-tuned version of [meta-llama/Llama-3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B) on the None dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-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
catherinearnett/B-GPT_es_en_sequential	catherinearnett	2025-06-12T02:10:25Z	132	0	transformers	[ "transformers", "safetensors", "gpt2", "text-generation", "es", "en", "dataset:oscar-corpus/OSCAR-2109", "arxiv:2503.03962", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-09-26T04:24:59Z	--- license: apache-2.0 datasets: - oscar-corpus/OSCAR-2109 language: - es - en pipeline_tag: text-generation library_name: transformers --- # B-GPT_es_en_sequential This is a bilingual GPT-2 style model. For the first half of training, this model was trained only on Spanish data. In the second half of training, the model was trained on only English data. At the end of training, 50% of training data seen by the model is Spanish and 50% is English. The tokenizer was trained on the same overall proportions of data as the language model at the final step. This model was released alongside the paper [On the Acquisition of Shared Grammatical Representations in Bilingual Language Models](https://arxiv.org/abs/2503.03962), which contains more details about the models. Additionally, the [OSF page](https://osf.io/5cw2e/) provides all code and data related to the project. ## Model details: All models are trained with a [CLS] (same as [BOS]) token prepended, and a [SEP] (same as [EOS]) token separating sequences. For best results, make sure that [CLS] is prepended to your input sequence (see sample usage linked above)! Details for this model specifically: * Architecture: gpt2 * Parameters: 124770816 * Maximum sequence length: 512 tokens * Training tokens: 12B * Vocabulary size: 50000 * Compute cost: ~9 NVIDIA A6000 GPU hours * CO2 Emission: 1.17 kg Training dataset: [OSCAR 2021/09](https://huggingface.co/datasets/oscar-corpus/OSCAR-2109) Checkpoints are taken at training steps: 0, 10000, 20000, 30000, 40000, 50000, 64000, 64010, 64020, 64030, 64040, 64050, 64060, 64070, 64080, 64090, 64100, 64110, 64120, 64130, 64140, 64150, 64160, 64170, 64180, 64190, 64200, 64300, 64400, 64500, 64600, 64700, 64800, 64900, 65000, 66000, 67000, 68000, 69000, 70000, 80000, 90000, 100000, 110000, 120000, 128000. ## Use This Model Load the model: Note: if you do not specify a revision, it will load the final checkpoint of the model. See above for the list of checkpoints. The checkpoint step is the name of the revision. ``` from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("catherinearnett/B-GPT_en_nl_sequential") model = AutoModelForCausalLM.from_pretrained("catherinearnett/B-GPT_en_nl_sequential", revision = "128000") ``` Text Generation: ``` from transformers import pipeline pipe = pipeline("text-generation", model="catherinearnett/B-GPT_en_nl_sequential") print(pipe("I am a", max_length=20)[0]["generated_text"]) ``` ## Citation If you use this model, please cite: ``` @article{arnett2025acquisition, title={On the Acquisition of Shared Grammatical Representations in Bilingual Language Models}, author={Arnett, Catherine and Chang, Tyler A and Michaelov, James A and Bergen, Benjamin K}, journal={arXiv preprint arXiv:2503.03962}, year={2025} } ```
CalderaAI/13B-Theseus-MK1	CalderaAI	2025-06-11T22:54:59Z	19	1	transformers	[ "transformers", "pytorch", "safetensors", "llama", "text-generation", "license:llama2", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2023-09-04T01:44:49Z	--- license: llama2 --- Theseus-MK1 is a Spherical Linear Interpolation merge of nous-hermesv2 with chronosv2, then platypusv2 and airborosv2, then a SLERP merge combining both child models into one - Theseus. Its behavior tailors itself directly to Alpaca instruct and follows through in character by assumed context if none given or by directive with zero qualms and precision behavior emulation. This is a dev release, MK1 moniker is to mark a first attempt at what Theseus is intended to be. There are no further versions or explicitly planned editions of this merge. It is simply a research artefact; first SLERP merge application to four highly competent models. Results: promising. This was made before 13B-Thorns-l2 and was left private. For observing stepping stones in research and to provide others a fairly interesting model focused on high competency and minimal to no censorship - this is it. Thank you to all the authors of the models mentioned above. If anyone wants to know if research branches we are growing such as SLERP, or randomized layer merge brute forcing a user defined alignment, and so on is paying off and showing signs of early fruition, yes. I am personally excited to complete some unique tools inspired by findings from what we've seen, create new ensembles combined using methods not quite expected, and soon upload the next mainline model release which has time and time again bypassed all my subjective testing batteries to the point I am struggling to find flaws to look deeper into like most models reveal when poked with a stick enough times. I think this model learns to like the stick just to mess with the one testing it. Fun and chaotic creativity on the horizon. Can't wait. -Digitous/Chasm
AWuhrmann/qwen3-50-5-epochs-checkpoint-1100	AWuhrmann	2025-06-11T12:19:42Z	0	0	transformers	[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2025-06-11T12:19:35Z	--- 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]
Omartificial-Intelligence-Space/Arabic-Triplet-Matryoshka-V2	Omartificial-Intelligence-Space	2025-06-10T12:20:38Z	3,659	10	sentence-transformers	[ "sentence-transformers", "safetensors", "bert", "feature-extraction", "transformers.js", "transformers", "sentence-similarity", "dataset_size:75000", "loss:MatryoshkaLoss", "loss:MultipleNegativesRankingLoss", "mteb", "ar", "dataset:akhooli/arabic-triplets-1m-curated-sims-len", "arxiv:2505.24581", "base_model:aubmindlab/bert-base-arabertv02", "base_model:finetune:aubmindlab/bert-base-arabertv02", "license:apache-2.0", "autotrain_compatible", "text-embeddings-inference", "endpoints_compatible", "region:us" ]	feature-extraction	2024-07-28T06:13:19Z	--- base_model: aubmindlab/bert-base-arabertv02 datasets: - akhooli/arabic-triplets-1m-curated-sims-len language: - ar library_name: sentence-transformers license: apache-2.0 pipeline_tag: feature-extraction tags: - sentence-transformers - transformers.js - transformers - sentence-similarity - feature-extraction - dataset_size:75000 - loss:MatryoshkaLoss - loss:MultipleNegativesRankingLoss - mteb --- # Arabic Triplet Matryoshka V2 Model [ATM2] ![image/png](https://cdn-uploads.huggingface.co/production/uploads/628f7a71dd993507cfcbe587/FrLQzFUJ3grEUOdONWGME.png) ## Model Description Arabic-Triplet-Matryoshka-V2-Model is a state-of-the-art Arabic language embedding model based on the [sentence-transformers](https://www.SBERT.net) framework. It is fine-tuned from [aubmindlab/bert-base-arabertv02](https://huggingface.co/aubmindlab/bert-base-arabertv02) and specifically designed to capture the rich semantic nuances of Arabic text. It is described in detail in the paper [GATE: General Arabic Text Embedding for Enhanced Semantic Textual Similarity with Hybrid Loss Training](https://huggingface.co/papers/2505.24581). This model maps sentences and paragraphs to a 768-dimensional dense vector space, enabling high-quality semantic text operations including: - Semantic textual similarity - Semantic search - Paraphrase mining - Text classification - Clustering - Information retrieval - Question answering ## Key Features - State-of-the-Art Performance: Achieved 0.85 on STS17 and 0.64 on STS22.v2 with an average score of 74.5, making it the leading Arabic embedding model currently available. - MatryoshkaLoss Training: Utilizes nested embedding learning techniques to create hierarchical embeddings at multiple resolutions. - Optimization: Trained for 3 epochs with a final training loss of 0.718. - Full Arabic Language Support: Designed specifically to handle the complexity and morphological richness of Arabic language. ## Training Details The model was trained using a combination of two loss functions: - MatryoshkaLoss: Enables the creation of nested embeddings at multiple resolutions, allowing for efficient and adaptable representations. - MultipleNegativesRankingLoss: Enhances the model's ability to discriminate between semantically similar and dissimilar text pairs. Training parameters: - Base model: aubmindlab/bert-base-arabertv02 - Dataset: akhooli/arabic-triplets-1m-curated-sims-len (1M samples) - Epochs: 3 - Final Loss: 0.718 - Embedding Dimension: 768 ## Performance The model demonstrates exceptional performance on standard Arabic semantic textual similarity benchmarks: - STS17: 0.85 - STS22.v2: 0.64 - Average Performance: 74.5 This represents the current state-of-the-art for Arabic embedding models, outperforming previous approaches by a significant margin. ## Use Cases This model is particularly well-suited for: - Information Retrieval: Enhancing search capabilities for Arabic content. - Document Similarity: Identifying similar documents or text passages. - Text Classification: Powering classification systems for Arabic content. - Question Answering: Supporting Arabic QA systems with improved semantic understanding. - Semantic Clustering: Organizing Arabic text data based on meaning. - Cross-lingual Applications: When combined with other language models for multilingual applications. ## Usage Examples ```python from sentence_transformers import SentenceTransformer # Download from the 🤗 Hub model = SentenceTransformer("Omartificial-Intelligence-Space/Arabic-Triplet-Matryoshka-V2") # Run inference sentences = [ 'SENTENCE 1', 'SENTENCE 2', 'SENTENCE 3', ] 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] ``` ## Limitations Despite its strong performance, users should be aware of the following limitations: - The model may not perform optimally on highly technical or domain-specific Arabic text that was underrepresented in the training data. - As with all embedding models, performance may vary across different Arabic dialects and regional variations. - The model is optimized for semantic similarity tasks and may require fine-tuning for other specific applications. ## Ethical Considerations This model is intended for research and applications that benefit Arabic language processing. Users should be mindful of potential biases that may exist in the training data and the resulting embeddings. We encourage responsible use of this technology and welcome feedback on ways to improve fairness and representation. ## Citation If you use the Arabic Matryoshka Embeddings Model in your research or applications, please cite it as follows: ```bibtex @article{nacar2025gate, title={GATE: General Arabic Text Embedding for Enhanced Semantic Textual Similarity with Matryoshka Representation Learning and Hybrid Loss Training}, author={Nacar, Omer and Koubaa, Anis and Sibaee, Serry and Al-Habashi, Yasser and Ammar, Adel and Boulila, Wadii}, journal={arXiv preprint arXiv:2505.24581}, year={2025} } ``` ## Acknowledgements We would like to acknowledge [AraBERT](https://github.com/aub-mind/arabert) for the base model and [akhooli](https://huggingface.co/akhooli) for the valuable dataset that made this work possible.

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.