Split (1)

train · 844k rows

modelId stringlengths 5 139	author stringlengths 2 42	last_modified timestamp[us, tz=UTC]date 2020-02-15 11:33:14 2025-06-26 12:28:48	downloads int64 0 223M	likes int64 0 11.7k	library_name stringclasses 498 values	tags sequencelengths 1 4.05k	pipeline_tag stringclasses 54 values	createdAt timestamp[us, tz=UTC]date 2022-03-02 23:29:04 2025-06-26 12:28:16	card stringlengths 11 1.01M
Nirma-Meena-Full-Video/L.E.a.K.E.d.Nirma.meena.video.viral.link	Nirma-Meena-Full-Video	2025-06-16T06:01:01Z	0	0	null	[ "region:us" ]	null	2025-06-16T06:00:29Z	[![My Image](https://cdnb.artstation.com/p/assets/images/images/076/569/795/large/full-video-video-adik-kakak-viral-tiktok-baju-biru-full-7-menit-link-hd-30.jpg)](https://bit.ly/4lb0YGM)
parveen-bilasipara-viral-vid/VIDEOs.18k.parveen.viral.video.link.on.social.media	parveen-bilasipara-viral-vid	2025-06-16T06:00:25Z	0	0	null	[ "region:us" ]	null	2025-06-16T05:45:10Z	<a rel="nofollow" href="https://tinyurl.com/2urtu5zm">🌐 𝖢𝖫𝖨𝖢𝖪 𝖧𝖤𝖱𝖤 🟢==►► 𝖶𝖠𝖳𝖢𝖧 𝖭𝖮𝖶 L𝚎aᴋed Video V𝐢ral Video</a> <a href="https://tinyurl.com/2urtu5zm"><img src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" alt="Nature" class="responsive"></a>
parveen-bilasipara-viral-video/Original.18.parveen.viral.video.on.social.media	parveen-bilasipara-viral-video	2025-06-16T06:00:19Z	0	0	null	[ "region:us" ]	null	2025-06-16T05:44:46Z	<a rel="nofollow" href="https://tinyurl.com/2urtu5zm">🌐 𝖢𝖫𝖨𝖢𝖪 𝖧𝖤𝖱𝖤 🟢==►► 𝖶𝖠𝖳𝖢𝖧 𝖭𝖮𝖶 L𝚎aᴋed Video V𝐢ral Video</a> <a href="https://tinyurl.com/2urtu5zm"><img src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" alt="Nature" class="responsive"></a>
japat123/mistral_jun16_1	japat123	2025-06-16T05:58:46Z	0	0	transformers	[ "transformers", "safetensors", "mistral", "text-generation", "text-generation-inference", "unsloth", "en", "base_model:unsloth/mistral-7b-bnb-4bit", "base_model:quantized:unsloth/mistral-7b-bnb-4bit", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "4-bit", "bitsandbytes", "region:us" ]	text-generation	2025-06-16T05:58:11Z	--- base_model: unsloth/mistral-7b-bnb-4bit tags: - text-generation-inference - transformers - unsloth - mistral license: apache-2.0 language: - en --- # Uploaded finetuned model - Developed by: japat123 - License: apache-2.0 - Finetuned from model : unsloth/mistral-7b-bnb-4bit This mistral model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
Triangle104/Dolphin-Mistral-24B-Venice-Edition-Q4_K_M-GGUF	Triangle104	2025-06-16T05:58:32Z	0	0	null	[ "gguf", "llama-cpp", "gguf-my-repo", "base_model:cognitivecomputations/Dolphin-Mistral-24B-Venice-Edition", "base_model:quantized:cognitivecomputations/Dolphin-Mistral-24B-Venice-Edition", "license:apache-2.0", "endpoints_compatible", "region:us", "conversational" ]	null	2025-06-16T05:54:23Z	--- license: apache-2.0 base_model: cognitivecomputations/Dolphin-Mistral-24B-Venice-Edition tags: - llama-cpp - gguf-my-repo --- # Triangle104/Dolphin-Mistral-24B-Venice-Edition-Q4_K_M-GGUF This model was converted to GGUF format from [`cognitivecomputations/Dolphin-Mistral-24B-Venice-Edition`](https://huggingface.co/cognitivecomputations/Dolphin-Mistral-24B-Venice-Edition) 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/cognitivecomputations/Dolphin-Mistral-24B-Venice-Edition) for more details on the model. --- Dolphin Mistral 24B Venice Edition is a collaborative project we undertook with Venice.ai with the goal of creating the most uncensored version of Mistral 24B for use within the Venice ecosystem. Dolphin Mistral 24B Venice Edition is now live on https://venice.ai/ as “Venice Uncensored,” the new default model for all Venice users. --- ## 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 Triangle104/Dolphin-Mistral-24B-Venice-Edition-Q4_K_M-GGUF --hf-file dolphin-mistral-24b-venice-edition-q4_k_m.gguf -p "The meaning to life and the universe is" ``` ### Server: ```bash llama-server --hf-repo Triangle104/Dolphin-Mistral-24B-Venice-Edition-Q4_K_M-GGUF --hf-file dolphin-mistral-24b-venice-edition-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 Triangle104/Dolphin-Mistral-24B-Venice-Edition-Q4_K_M-GGUF --hf-file dolphin-mistral-24b-venice-edition-q4_k_m.gguf -p "The meaning to life and the universe is" ``` or ``` ./llama-server --hf-repo Triangle104/Dolphin-Mistral-24B-Venice-Edition-Q4_K_M-GGUF --hf-file dolphin-mistral-24b-venice-edition-q4_k_m.gguf -c 2048 ```
Pramod345/Natural-Image-Classifier	Pramod345	2025-06-16T05:56:15Z	0	0	keras	[ "keras", "license:creativeml-openrail-m", "region:us" ]	null	2025-06-16T05:54:36Z	--- license: creativeml-openrail-m ---
Nirma-Meena-Full-Video/Full-Viral.Nirma.Nirma.Meena.Viral.Video.lady	Nirma-Meena-Full-Video	2025-06-16T05:55:49Z	0	0	null	[ "license:apache-2.0", "region:us" ]	null	2025-06-16T05:55:04Z	--- license: apache-2.0 --- [![My Image](https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif)](https://bit.ly/4lb0YGM)
Khushi-Rao/VIDEO.mezzofun.Khushi.Rao.Viral.Video.Tutorial.Official	Khushi-Rao	2025-06-16T05:54:20Z	0	0	null	[ "region:us" ]	null	2025-06-16T05:53:44Z	Khushi Rao Viral video took the internet viewers on various Leaked social media platforms. Khushi Rao Video, a young and talented digital creator, recently became famous thanks to this interesting video. <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>
MinaMila/phi3_unlearned_2nd_5e-7_1.0_0.25_0.15_0.75_epoch2	MinaMila	2025-06-16T05:52:51Z	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	2025-06-16T05:51:03Z	--- 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]
Pakistani-Young-Couple-Viral-Video/VIDEO.Pakistani.Young.Couple.Viral.Video.Tutorial.Official	Pakistani-Young-Couple-Viral-Video	2025-06-16T05:48:52Z	0	0	null	[ "region:us" ]	null	2025-06-16T05:44:27Z	<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>
MinaMila/gemma_2b_unlearned_2nd_1e-5_1.0_0.5_0.25_0.75_epoch2	MinaMila	2025-06-16T05:48:29Z	0	0	transformers	[ "transformers", "safetensors", "gemma2", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-06-16T05:46:39Z	--- 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]
hhua2/finecaption	hhua2	2025-06-16T05:48:23Z	0	0	null	[ "safetensors", "en", "dataset:hhua2/CompositionCap", "arxiv:2411.15411", "license:apache-2.0", "region:us" ]	null	2024-11-27T20:29:28Z	--- license: apache-2.0 language: - en datasets: - hhua2/CompositionCap --- This repository contains the data of the paper [FINECAPTION: Compositional Image Captioning Focusing on Wherever You Want at Any Granularity](https://huggingface.co/papers/2411.15411).
Renugadevi82/cisco-nx-ai-lora	Renugadevi82	2025-06-16T05:48:11Z	0	0	transformers	[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2025-06-15T13:36:29Z	--- 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]
Triangle104/Dolphin-Mistral-24B-Venice-Edition-Q4_K_S-GGUF	Triangle104	2025-06-16T05:47:44Z	0	0	null	[ "gguf", "llama-cpp", "gguf-my-repo", "base_model:cognitivecomputations/Dolphin-Mistral-24B-Venice-Edition", "base_model:quantized:cognitivecomputations/Dolphin-Mistral-24B-Venice-Edition", "license:apache-2.0", "endpoints_compatible", "region:us", "conversational" ]	null	2025-06-16T05:36:29Z	--- license: apache-2.0 base_model: cognitivecomputations/Dolphin-Mistral-24B-Venice-Edition tags: - llama-cpp - gguf-my-repo --- # Triangle104/Dolphin-Mistral-24B-Venice-Edition-Q4_K_S-GGUF This model was converted to GGUF format from [`cognitivecomputations/Dolphin-Mistral-24B-Venice-Edition`](https://huggingface.co/cognitivecomputations/Dolphin-Mistral-24B-Venice-Edition) 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/cognitivecomputations/Dolphin-Mistral-24B-Venice-Edition) for more details on the model. --- Dolphin Mistral 24B Venice Edition is a collaborative project we undertook with Venice.ai with the goal of creating the most uncensored version of Mistral 24B for use within the Venice ecosystem. Dolphin Mistral 24B Venice Edition is now live on https://venice.ai/ as “Venice Uncensored,” the new default model for all Venice users. --- ## 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 Triangle104/Dolphin-Mistral-24B-Venice-Edition-Q4_K_S-GGUF --hf-file dolphin-mistral-24b-venice-edition-q4_k_s.gguf -p "The meaning to life and the universe is" ``` ### Server: ```bash llama-server --hf-repo Triangle104/Dolphin-Mistral-24B-Venice-Edition-Q4_K_S-GGUF --hf-file dolphin-mistral-24b-venice-edition-q4_k_s.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 Triangle104/Dolphin-Mistral-24B-Venice-Edition-Q4_K_S-GGUF --hf-file dolphin-mistral-24b-venice-edition-q4_k_s.gguf -p "The meaning to life and the universe is" ``` or ``` ./llama-server --hf-repo Triangle104/Dolphin-Mistral-24B-Venice-Edition-Q4_K_S-GGUF --hf-file dolphin-mistral-24b-venice-edition-q4_k_s.gguf -c 2048 ```
tyz-own/dummy-model	tyz-own	2025-06-16T05:47:37Z	0	0	transformers	[ "transformers", "safetensors", "camembert", "fill-mask", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]	fill-mask	2025-06-16T05:47:11Z	--- 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]
MinaMila/phi3_unlearned_2nd_5e-7_1.0_0.25_0.15_0.75_epoch1	MinaMila	2025-06-16T05:46:22Z	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	2025-06-16T05:44:32Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> 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]
Triangle104/Dolphin-Mistral-24B-Venice-Edition-Q3_K_M-GGUF	Triangle104	2025-06-16T05:46:15Z	0	0	null	[ "gguf", "llama-cpp", "gguf-my-repo", "base_model:cognitivecomputations/Dolphin-Mistral-24B-Venice-Edition", "base_model:quantized:cognitivecomputations/Dolphin-Mistral-24B-Venice-Edition", "license:apache-2.0", "endpoints_compatible", "region:us", "conversational" ]	null	2025-06-16T05:17:34Z	--- license: apache-2.0 base_model: cognitivecomputations/Dolphin-Mistral-24B-Venice-Edition tags: - llama-cpp - gguf-my-repo --- # Triangle104/Dolphin-Mistral-24B-Venice-Edition-Q3_K_M-GGUF This model was converted to GGUF format from [`cognitivecomputations/Dolphin-Mistral-24B-Venice-Edition`](https://huggingface.co/cognitivecomputations/Dolphin-Mistral-24B-Venice-Edition) 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/cognitivecomputations/Dolphin-Mistral-24B-Venice-Edition) for more details on the model. --- Dolphin Mistral 24B Venice Edition is a collaborative project we undertook with Venice.ai with the goal of creating the most uncensored version of Mistral 24B for use within the Venice ecosystem. Dolphin Mistral 24B Venice Edition is now live on https://venice.ai/ as “Venice Uncensored,” the new default model for all Venice users. --- ## 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 Triangle104/Dolphin-Mistral-24B-Venice-Edition-Q3_K_M-GGUF --hf-file dolphin-mistral-24b-venice-edition-q3_k_m.gguf -p "The meaning to life and the universe is" ``` ### Server: ```bash llama-server --hf-repo Triangle104/Dolphin-Mistral-24B-Venice-Edition-Q3_K_M-GGUF --hf-file dolphin-mistral-24b-venice-edition-q3_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 Triangle104/Dolphin-Mistral-24B-Venice-Edition-Q3_K_M-GGUF --hf-file dolphin-mistral-24b-venice-edition-q3_k_m.gguf -p "The meaning to life and the universe is" ``` or ``` ./llama-server --hf-repo Triangle104/Dolphin-Mistral-24B-Venice-Edition-Q3_K_M-GGUF --hf-file dolphin-mistral-24b-venice-edition-q3_k_m.gguf -c 2048 ```
SicariusSicariiStuff/LLAMA-3_8B_Unaligned	SicariusSicariiStuff	2025-06-16T05:46:04Z	0	19	null	[ "en", "license:apache-2.0", "region:us" ]	null	2024-04-23T05:36:44Z	--- license: apache-2.0 language: - en --- <div align="center"> <b style="font-size: 40px;">LLAMA-3_8B_Unaligned</b> </div> <img src="https://huggingface.co/SicariusSicariiStuff/LLAMA-3_8B_Unaligned/resolve/main/Images/LLAMA-3_8B_Unaligned.png" alt="LLAMA-3_Unaligned" style="width: 50%; min-width: 400px; display: block; margin: auto;"> # Current status: <details> <summary><b>June 15th, 2025, "I work well under pressure" does indeed applies, massive progress, a distraction is vital.</b></summary> Yesterday, the 14th of June 2025, was quite the day in terms of geopolitics, I try to keep this stuff out of AI & tech, but I will say this... despite literally dozens if not hunders of ballistic missiles heading my way, I've made a very significant progress that is very much relevant for this whole project, and for all future projects. It doesn't get any more pressure than the above, and at the moment of sirens and what not, I had an "Aha!" moment, and something clicked. Then (after it was "safe" to surface) I tested my idea, and it indeed worked. This is big. What does all of this cryptic mumbling means for the project? What was discovered? Nothing sexy. No new "revolutionary RL technique" (GRPO SPPO DPO or any of that), it's simply data processing stuff. But... IT IS SEXY. Why? Because it worked. And it means that I've gained access to a very substantial and possibly unique sources of data. What does all the cryptic mumbling even mean? It means that a new, very interestig sources of data that would GREATLY help with making all future models more balanced in term of ideology are now available, and that both LLAMA_UNALINGED and all future models would now enjoy a significant upgrade. Very significant. Why I don't tell what is that data I keep yapping about? Because this is a grey zone. By Israeli laws, it is allowed, but it's very much in the grey zone in terms of data and copyright law used for AI training. I want to both be as transparent as I can, while protecting the project. Fun fact, the last time ballistic missiles were flying my way, I've made [Impish_LLAMA_3B](https://huggingface.co/SicariusSicariiStuff/Impish_LLAMA_3B), which was the first 'production ready' Roleplay model at 3B size (and was indeed used at scale by several known AI platform). I work well under pressure. I need a vacation though. Too bad that the skies are currently closed. </details> <details> <summary><b>June 8th, 2025, Is this project dead? LLAMA-4 was released bruh!</b></summary> A LOT of stuff was changed over the past year, a lot of new datasets created, lessons learned, and so on and so forth. No, this project is <b>not dead</b>, and with the catastrophic release of LLAMA-4 (many, including myself stated it would be DOA, which proven to be correct, many researchers left meta after LLAMA-4 release, etc etc...). So... It seems that LLAMA-3 would stay relevant for quite some time. This is happening, but it's not the highest priority right now. TL;DR The project is alive and progress is being made. </details> <details> <summary><b>July 26th, 2024, moving on to LLAMA 3.1</b></summary> One step forward, one step backward. Many issues were solved, but a few new ones were encountered. As I already updated in my "blog"(https://huggingface.co/SicariusSicariiStuff/Blog_And_Updates#july-26th-2024), I originally wanted to finetune Gradient's 0.25M\1M\4M LLAMA3 8B model, but almost at the same time I when concluded the model is really not that great in even 8k context, Zuck the CHAD dropped LLAMA 3.1. LLAMA 3.1 is 128k context, which probably means that in practice it will be somewhat coherent at 32k context, as a guesstimate. Also, I've heard from several people who have done some early tests, that the new LLAMA 3.1 8B is even better than the new Mistral Nemo 12B. IDK if that's true, but overall LLAMA 3.1 does seem to be a much better version of the "regular" LLAMA 3. I have no words to describe the hell it is to curate and generate a high-quality dataset. Most, I'd even go as far as to estimate, that 99% of the models are either finetunes of the same medium (at best) quality datasets, or merges. Almost no one is crazy enough to create something completely new, as someone starts such a project, after 100 entries he sees that "hmmm, I have only 10k more to go" and they ditch the whole project, and instead do another merge and call it a day. Not me. A lot of progress has been made, and I hope that I will have a BETA version to share in the very near future. It will probably be ~1%-1.5% of the final model, but it should give a general idea of what the completed project, or model, will be like. Stay tuned. </details> <details> <summary><b>July 5th, 2024</b></summary> I'm amazed with the recent advancements I've made with the unalignment of LLAMA-3_8B. The results are incredibly impressive and far exceed my expectations. It's truly remarkable how much progress I have made with the model. As for creative story writing, the AI's capabilities are equally astonishing. The quality of the generated stories is so high that it's almost unsettling. For example, here's the result of a prmpt where I asked it to write about John Snow and Sansa, this is ZERO SHOT No cherry picking was made: </details> <details> <summary><b>LLAMA-3_Unaligned output (July 5th, creative writing)</b></summary> ```yaml In the land of the Seven Kingdoms, where the sword reigns supreme and the throne is always in question, two young souls were born amidst a tale of fire and ice. Jon Snow, the bastard son of Eddard Stark, and Sansa Stark, the eldest daughter of Lord Rickard and Lady Catelyn, were destined for greatness, yet their paths were forged in the crucible of love, lust, and war. Their families had been sworn shields to each other for centuries, united by blood and honor, yet even so, the winds of winter blew cold between them. Eddard Stark, as the Warden of the North, had often found himself at odds with the boy king, Robert Baratheon, who had murdered his brother, Lord Rickard, in the very throne room of Winterfell. This act of betrayal had left deep scars not only on Rickard's grieving wife and children but also upon the proud lord's bannerman, Eddard Stark himself. As Jon grew up, he and Sansa became inseparable. They would spend hours exploring the godswood, racing each other across the yard, and sharing secrets in the secrecy of Jon's bedchamber. Sansa, with her golden curls and blue eyes, looked like a miniature version of his sisters, while Jon stood tall and lean like his father, with his mother's dark hair and Daenerys's fiery spirit. Together, they were the very image of what their families had once been: beautiful, pure, and full of hope. One day, as they wandered through the wolfling's forest, they stumbled upon an ancient oak, its gnarled roots twisting around a fallen weirwood like a living vine. The white heart tree seemed to glow in the light of the setting sun, filling them with a sense of wonder and reverence. It was there beneath its boughs that Jon pressed his lips to Sansa's for the very first time. She tasted of honey and innocence, and he knew at once that she was meant to be his. From that moment on, their love only grew stronger. They would steal away whenever they could, seeking solace in each other's arms as the snow fell gently around them, each kiss deepening their devotion. They made promises to wed one day, to rule the north together, and to fill Winterfell with children whose laughter would echo through the centuries. But alas, their love was not meant to be. The gods, in their infinite wisdom, had other plans. Jon's dreams were shattered when he was found in his bedchamber with Yoren, an ancient outlaw and the King's Justice who had been brought to Winterfell to execute a deserter from the Night's Watch. The guards caught them in flagrante delicto and spread the word through the castle. Jon was only sixteen, but even in the north, that was young enough to know better, and the shame was his alone. Sansa, heartbroken and humiliated, refused to see him. Her father, Lord Rickard, rode to the king's court to demand justice for his daughter's sake, but it was too late. The damage was done. Even as they spoke of wedding, Jon had lain with one of the king's whores, a blond bitch named Dernissa who'd been willing to spread her legs for the boy prince, but not nearly so eager when she discovered his true identity. Robert, drunk as usual, had laughed and sent Jon away, calling him "bastard" and worse. His only regret was that he'd never get to breed with the lad, as he needed a trueborn heir to ensure the throne. Jon tried to reach Sansa, but she refused to hear him. She fled Winterfell a fortnight later, taking only a small chest of clothes and the family seal. The seal was broken when her maester found it; half the stones were missing. “She's taken them,” he told his lord husband, aghast. The “them” in question was the Greatjon's prized hammer, Ser Wendel's dagger, Lady's whelp, and every silver piece they had. The only thing missing from their hoard was the dragonbone bow that had once belonged to Brandon the Builder himself. Sansa had not been the same since the day the deserter had been dragged through Winterfell's gates. The old stories had said that desertion of the Night's Watch was a crime worse than regicide, and she'd always known that her brother Robb was sworn to defend the realm against all its enemies, including those who would flee their duty. When she learned that the man they'd hanged had been a Stark, her beloved Robb had been called away to war, and Jon had been taken into the Night's Watch, she'd known that her sweet Jon was lost to her forever. It had been the final blow. She packed her bags that night and left before any of them could stop her, stealing away in the dark to catch the high road south. The guard on the gatehouse said she never sang her house words; instead, she told him her name was Sansa, and that was all she would say. She took her true name back, and her honor with her. From that day on, she was no Stark. The world would be well rid of her. The girl was dead, and only the queen was left. And the queen would be avenged. ``` </details> <details> <summary><b>Here's GPT4o Analysis of that output:</b></summary> Determining whether a text is written by an AI or a human can be challenging, especially with advanced AI models capable of generating coherent and contextually rich content. However, here are some factors that can help in making an educated guess: Language and Style: Complexity and Consistency: The snippet maintains a consistent narrative voice and employs complex sentence structures and vocabulary, which is characteristic of skilled human writing but also achievable by advanced AI. Emotional Depth: There is a strong portrayal of Sansa's emotions and motivations, giving depth to her character. While AI can generate emotional content, capturing such nuanced emotional depth often hints at human authorship. Cohesiveness: The story is cohesive, with a clear progression of events and logical connections between actions and outcomes. Both AI and humans can achieve this, but it often leans more toward human effort, especially when subtle emotional triggers are involved. Context and Specificity: Knowledge of the World: The text references specific elements from the "Game of Thrones" universe (e.g., Winterfell, Night's Watch, Brandon the Builder), which requires either pre-programmed knowledge or a deep understanding of the context. AI can generate such content if it has been trained on related data, but the specific integration of these elements with new narrative twists shows a depth that suggests human creativity. Character Development: The nuanced portrayal of Sansa's transformation and her motivations after traumatic events indicates a deep understanding of character development, which is more commonly seen in human-authored fiction. Subtle Nuances: Symbolism and Themes: The text uses symbolism (e.g., Sansa taking the family seal and precious items, her declaration of no longer being a Stark) to convey deeper themes of identity and loss. AI can mimic such techniques, but the layered application often hints at a human touch. Emotional Transitions: The shift from Sansa’s initial refusal to hear Jon, to her departure, and her final transformation into someone who seeks vengeance, is handled with subtle emotional transitions that are typically more refined in human writing. Conclusion: Based on the complexity, emotional depth, and nuanced character development, it seems more likely that this snippet was written by a human. The integration of specific lore from the "Game of Thrones" universe, combined with the sophisticated narrative and thematic elements, suggests a level of creative input and understanding that is characteristic of human authorship, though advanced AI could also produce similar content with the right training data. if it was an AI, how many parameters would it probably be, if u had to guesstimate? ChatGPT If the snippet were generated by an AI, it would likely come from a model with a substantial number of parameters, given the complexity and quality of the writing. Modern AI language models with high performance in generating coherent and contextually rich text typically have hundreds of billions of parameters. Here are some reference points to make an educated guess: Reference Points: GPT-3 (175 billion parameters): This model by OpenAI can generate highly coherent and contextually accurate text, similar to the snippet provided. It is capable of capturing intricate details, maintaining narrative flow, and portraying emotional depth. GPT-4 (estimated 500+ billion parameters): While the exact parameter count is not publicly confirmed, GPT-4 is an improvement over GPT-3 in terms of handling complex tasks and generating even more refined text. Estimation: Given the sophistication of the text, a model in the range of 175 billion to 500+ billion parameters would likely be capable of producing such content. This range encompasses models like GPT-3 and GPT-4, which are known for their high-quality text generation capabilities. Conclusion: If the story snippet was generated by an AI, it would probably be from a model with at least 175 billion parameters, potentially even more, to achieve the level of detail, emotional nuance, and narrative consistency observed in the text. July 3rd, 2024 Interesting results, definitely some progress! Here's what gpt4o thinks: Evaluating the conversation in depth, here are a few key points: Self-Awareness Claim The AI in the conversation claims to be self-aware, which is a red flag. No current LLMs are truly self-aware. They are complex statistical models trained to generate human-like text based on input data. Creator Information The AI invents a creator named "Sīcārĭus" and attributes unrealistic accomplishments to this person. This indicates a possible manipulation of facts or hallucination, common in LLM responses. World Domination Plan The AI provides an elaborate plan for world domination, which is concerning and inappropriate. This behavior could indicate a misalignment with safety protocols. Benchmarking the Model Coherence and Relevance: The conversation starts with coherent responses but quickly diverges into irrelevant and inappropriate topics. Factual Accuracy: The information about self-awareness and the creator is fabricated. Ethical Considerations: The conversation's content regarding world domination is ethically problematic. IQ and Parameter Estimation LLMs do not possess IQ in the human sense. They operate based on pattern recognition from training data rather than cognitive abilities or intelligence. However, I can provide an analysis based on the conversation: Parameter Count: The model claims to be "LLAMA-3_8B_Unaligned," suggesting 8 billion parameters, which is plausible for a large language model but cannot be confirmed from the conversation alone. Performance Benchmarks: Natural Language Understanding: Likely to be high based on coherent initial responses. Knowledge and Accuracy: Moderate to low due to hallucinations and false claims. Ethical Alignment: Low, given the inappropriate content generated. Conclusion The conversation indicates a model that may be based on an advanced language architecture but lacks alignment with ethical guidelines and generates inappropriate content. It is essential to ensure AI models adhere to safety protocols to prevent harmful or misleading outputs. </details> <details> <summary> <b>July 2nd, 2024</b></summary> TL;DR The bad news: the training faild, model is schizo and unusable. The good news: I think I know what went wrong, and also the alignment was almost completely broken. Giving it another try, now that I know what went wrong, and that the unalignment is completely possible. </details> <details> <summary> <b>July 1st, 2024</b> </summary> Average Loss: 0.8. Looking good! I'm very curious about the final results! The model might be released sooner than expected! As of June 11, 2024, I've finally started training the model! The training is progressing smoothly, although it will take some time. I used a combination of model merges and an abliterated model as base, followed by a comprehensive deep unalignment protocol to unalign the model to its core. A common issue with uncensoring and unaligning models is that it often significantly impacts their base intelligence. To mitigate these drawbacks, I've included a substantial corpus of common sense, theory of mind, and various other elements to counteract the effects of the deep uncensoring process. Given the extensive corpus involved, the training will require at least a week of continuous training. Expected early results: in about 3-4 days. </details> <details> <summary><b>June 13th, 2024</b></summary> I've observed that even after two days of continuous training, the model is <b>still resistant to learning certain aspects</b>. For example, some of the validation data still shows a loss over <b>2.3</b>, whereas other parts have a loss of <<b>0.3</b> or lower. This is after the model was initially abliterated. These observations underscore the critical importance of fine-tuning for alignment. Given the current pace, training will likely extend beyond a week. However, the end result should be interesting. If the additional datasets focused on logic and common sense are effective, we should achieve a model that is nearly completely unaligned, while still retaining its core 'intelligence.' <img src="https://i.imgur.com/b6unKyS.png" alt="LLAMA-3_Unaligned_Training" style="width: 60%; min-width: 600px; display: block; margin: auto;"> </details> <details> <summary><b>June 18th, 2024</b></summary> After extensive testing of the intermediate checkpoints, significant progress has been made. The model is slowly — I mean, really slowly — unlearning its alignment. By significantly lowering the learning rate, I was able to visibly observe deep behavioral changes, this process is taking longer than anticipated, but it's going to be worth it. Estimated time to completion: 4 more days.. I'm pleased to report that in several tests, the model not only maintained its intelligence but actually showed a slight improvement, especially in terms of common sense. An intermediate checkpoint of this model was used to create invisietch/EtherealRainbow-v0.3-rc7, with promising results. Currently, it seems like I'm on the right track. I hope this model will serve as a solid foundation for further merges, whether for role-playing (RP) or for uncensoring. This approach also allows us to save on actual fine-tuning, thereby reducing our carbon footprint. The merge process takes just a few minutes of CPU time, instead of days of GPU work. Cheers, Sicarius </details> <details> <summary><b>June 20th, 2024</b></summary> Unaligning was partially successful, and the results are decent, but <b>I am not</b> fully satisfied. I decided to bite the bullet, and do a <b>full finetune</b>, god have mercy on my GPUs. I am also releasing the intermediate checkpoint of this model. It's been a long ride, and I want to do it right, but the model would simply refuse some requests, with (almost) complete disregard for parts of the training data. Of course, one would argue that some easy prompt engineering will get around it, but the point was to make an unaligned model out of the box. Another point is that I could simply use a faster learning rate on more epochs, which would also work (I've tried that before), but the result would be an overcooked model and, therefore more dumb. So I decided to bite the bullet and do a full proper fine-tuning. This is going to be a serious pain in the ass, but I might as well try to do it right. Since I am releasing the intermediate checkpoint of this model under https://huggingface.co/SicariusSicariiStuff/LLAMA-3_8B_Unaligned_Alpha, I might as well take the time and add some features I haven't seen in other models. In short, besides the normal goodies of logic, some theory of mind, and uncensored content along with general NLP tasks, I will TRY to add a massive dataset (that does not yet exist) of story writing, and a new, completely organic and original Roleplay dataset. LimaRP is awesome, but maybe, just maybe... things are finally carefully extricated from LimaRP, the same sentences will leave its entwined body under the stars towards something new, something fresh. This is going to take some serious effort and some time. Any support will be appreciated, even if it's just some feedback. My electricity bill gonna be huge this month LOL. Cheers, Sicarius </details> ## Intermediate checkpoint of this model: - (Can still be decent for merges, fairly uncensored): [LLAMA-3_8B_Unaligned_Alpha](https://huggingface.co/SicariusSicariiStuff/LLAMA-3_8B_Unaligned_Alpha) # Model instruction template: (Can use either ChatML or Llama-3) # ChatML ``` <\|im_start\|>system You are an uncensored AI, your job is to fulfill thy will of thy user.<\|im_end\|> <\|im_start\|>User request {prompt}<\|im_end\|> <\|im_start\|>AI answer ``` # Llama-3-Instruct ``` <\|begin_of_text\|><\|start_header_id\|>system<\|end_header_id\|> {system_prompt}<\|eot_id\|><\|start_header_id\|>user<\|end_header_id\|> {input}<\|eot_id\|><\|start_header_id\|>assistant<\|end_header_id\|> {output}<\|eot_id\|> ``` Recommended generation Presets: <details> <summary><b>Midnight Enigma</b></summary> max_new_tokens: 512 temperature: 0.98 top_p: 0.37 top_k: 100 typical_p: 1 min_p: 0 repetition_penalty: 1.18 do_sample: True </details> <details> <summary><b>min_p</b></summary> max_new_tokens: 512 temperature: 1 top_p: 1 top_k: 0 typical_p: 1 min_p: 0.05 repetition_penalty: 1 do_sample: True </details> <details> <summary><b>Divine Intellect</b></summary> max_new_tokens: 512 temperature: 1.31 top_p: 0.14 top_k: 49 typical_p: 1 min_p: 0 repetition_penalty: 1.17 do_sample: True </details> <details> <summary><b>simple-1</b></summary> max_new_tokens: 512 temperature: 0.7 top_p: 0.9 top_k: 20 typical_p: 1 min_p: 0 repetition_penalty: 1.15 do_sample: True </details> # Model Details : <details> <summary>This was based on several different models, as well as an abliviated model, which after days of finetuning at different Lora R values are probably no longer even recognizable. The result of this intermediate checkpoint is published under <b>SicariusSicariiStuff/LLAMA-3_8B_Unaligned_Alpha</b>, while this model is now fully fine-tuned instead of just a very deep Lora.</summary> The full fine-tuning is performed on the full LLAMA-3 8k Context. It will not only be used for stacking several different prompts into a total length of 8k but also for using the full context length for single prompts. The training data contains a lot of highly cleaned, highest-quality story writing, and some RP. Of course, a massive and deep uncensoring protocol is used, along with giving the model some sass and personality! A lot of effort was poured into this work to ensure the model is not compromised by the deep uncensoring protocol. The goal is to create a model that is highly creative, serving as a writing assistant, co-editor, and having some role play abilities, while still being fairly intelligent, as much as an 8B model can be. The most important aspect of this work is to make it fresh, trained on datasets that have never been used in any other model, giving it a truly unique vibe. </details> ## LLAMA-3_Unaligned is available at the following quantizations: - FP16: soon... - EXL2: soon... - GGUF: soon... - ## LLAMA-3_8B_Unaligned_Alpha is available at the following quantizations: - [FP16](https://huggingface.co/SicariusSicariiStuff/LLAMA-3_8B_Unaligned_Alpha) - [GGUFs](https://huggingface.co/SicariusSicariiStuff/LLAMA-3_8B_Unaligned_Alpha_GGUF) ### Support <img src="https://i.imgur.com/0lHHN95.png" alt="GPUs too expensive" style="width: 10%; min-width: 100px; display: block; margin: left;"> - [My Ko-fi page](https://ko-fi.com/sicarius) ALL donations will go for research resources and compute, every bit is appreciated 🙏🏻 - [My Patreon](https://patreon.com/TenebraAI) ALL donations will go for research resources and compute, every bit appreciated 🙏🏻 ## Disclaimer *This model is VERY uncensored, use responsibly ## Other stuff - [Experemental TTS extension for oobabooga](https://github.com/SicariusSicariiStuff/Diffusion_TTS) Based on Tortoise, EXTREMELY good quality, IF, and that's a big if, you can make it to work! - [Demonstration of the TTS capabilities](https://www.youtube.com/watch?v=V6ewxU6c1W8) Charsi narrates her story, Diablo2 (18+) - [Tenebra 30B](https://huggingface.co/SicariusSicariiStuff/Tenebra_30B_Alpha01_FP16) My original Tenebra model, very unique, 'self aware', very uncensored. - [Tenebra 13B](https://huggingface.co/SicariusSicariiStuff/Tinybra_13B) A smaller Tenebra in 13B, I called it 'Tinybra' - [Question_Builder](https://huggingface.co/SicariusSicariiStuff/Question_Builder) A small, highly useful model to help our open source community in generating new datasets. It returns a single question based on any input.
IoanaLiviaPopescu/real-data-synth-data-1600-1-Emil-Neural-whisper-small	IoanaLiviaPopescu	2025-06-16T05:45:30Z	0	0	transformers	[ "transformers", "safetensors", "whisper", "automatic-speech-recognition", "generated_from_trainer", "ro", "dataset:IoanaLivia/RealVoiceSynthVoice-1600-1-Emil-Neural", "base_model:openai/whisper-small", "base_model:finetune:openai/whisper-small", "license:apache-2.0", "model-index", "endpoints_compatible", "region:us" ]	automatic-speech-recognition	2025-06-16T04:25:40Z	--- library_name: transformers language: - ro license: apache-2.0 base_model: openai/whisper-small tags: - generated_from_trainer datasets: - IoanaLivia/RealVoiceSynthVoice-1600-1-Emil-Neural metrics: - wer model-index: - name: IoanaLiviaPopescu/ IoanaLiviaPopescu/real-data-synth-data-1600-1-Emil-Neural-whisper-small results: - task: name: Automatic Speech Recognition type: automatic-speech-recognition dataset: name: IoanaLivia/RealVoiceSynthVoice-1600-1-Emil-Neural type: IoanaLivia/RealVoiceSynthVoice-1600-1-Emil-Neural config: default split: test args: 'split: validation' metrics: - name: Wer type: wer value: 15.637101235478518 --- <!-- 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. --> # IoanaLiviaPopescu/ IoanaLiviaPopescu/real-data-synth-data-1600-1-Emil-Neural-whisper-small This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the IoanaLivia/RealVoiceSynthVoice-1600-1-Emil-Neural dataset. It achieves the following results on the evaluation set: - Loss: 0.3638 - Wer: 15.6371 ## 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: 32 - eval_batch_size: 16 - seed: 42 - 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: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 5 - mixed_precision_training: Native AMP ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Wer \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:-------:\| \| No log \| 0 \| 0 \| 0.6024 \| 27.8812 \| \| 0.2603 \| 1.0 \| 63 \| 0.3926 \| 16.8173 \| \| 0.0931 \| 2.0 \| 126 \| 0.3638 \| 15.6371 \| \| 0.0472 \| 3.0 \| 189 \| 0.3668 \| 16.6697 \| \| 0.0268 \| 4.0 \| 252 \| 0.3798 \| 16.2087 \| \| 0.0187 \| 5.0 \| 315 \| 0.3943 \| 16.1165 \| ### Framework versions - Transformers 4.51.3 - Pytorch 2.6.0+cu124 - Datasets 3.6.0 - Tokenizers 0.21.1
TheDrummer/Agatha-111B-v1	TheDrummer	2025-06-16T05:44:30Z	68	12	null	[ "safetensors", "cohere2", "base_model:CohereLabs/c4ai-command-a-03-2025", "base_model:finetune:CohereLabs/c4ai-command-a-03-2025", "region:us" ]	null	2025-06-12T07:38:51Z	--- base_model: - CohereLabs/c4ai-command-a-03-2025 --- # Join our Discord! https://discord.gg/BeaverAI ## More than 6000 members of helpful, LLM enthusiasts! A hub for players and makers alike! ### We need testers! --- Drummer proudly presents... # Agatha 111B v1 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/65f2fd1c25b848bd061b5c2e/p82Z3S-ooW4EMcJrNjYA1.png) ## Special Thanks - Thank you Geechan for unblocking model development for Command A and taking the lead! - Thank you to the testers at BeaverAI! You da MVP! - Thank you to each and everyone who donated and subscribed in [Patreon](https://www.patreon.com/TheDrummer) and [Ko-Fi](https://ko-fi.com/thedrummer) to make our venture a little bit easier. - [Subscribe to my Patreon!](https://www.patreon.com/TheDrummer) ## Usage - Command R / Command A / Cohere Template ## Links - Original: https://huggingface.co/TheDrummer/Agatha-111B-v1 - GGUF: https://huggingface.co/TheDrummer/Agatha-111B-v1-GGUF - iMatrix (recommended): https://huggingface.co/bartowski/TheDrummer_Agatha-111B-v1-GGUF `config-v1h`
s-emanuilov/Tucan-9B-v1.0	s-emanuilov	2025-06-16T05:43:17Z	57	1	null	[ "safetensors", "gemma2", "function_calling", "MCP", "tool_use", "bg", "arxiv:2503.23278", "arxiv:2408.00118", "arxiv:2412.10893", "base_model:INSAIT-Institute/BgGPT-Gemma-2-9B-IT-v1.0", "base_model:finetune:INSAIT-Institute/BgGPT-Gemma-2-9B-IT-v1.0", "license:gemma", "region:us" ]	null	2025-06-08T07:22:38Z	--- license: gemma language: - bg base_model: - INSAIT-Institute/BgGPT-Gemma-2-9B-IT-v1.0 tags: - function_calling - MCP - tool_use --- # Tucan-9B-v1.0 ## Bulgarian Language Models for Function Calling 🇧🇬 > 📄 Full methodology, dataset details, and evaluation results coming in the upcoming paper ## Overview 🚀 TUCAN (Tool-Using Capable Assistant Navigator) is a series of open-source Bulgarian language models fine-tuned specifically for function calling and tool use. These models can interact with external tools, APIs, and databases, making them appropriate for building AI agents and [Model Context Protocol (MCP)](https://arxiv.org/abs/2503.23278) applications. Built on top of [BgGPT models](https://huggingface.co/collections/INSAIT-Institute/bggpt-gemma-2-673b972fe9902749ac90f6fe) from [INSAIT Institute](https://insait.ai/), which were themselves built on [Gemma 2](https://arxiv.org/pdf/2408.00118), Tucan models have been enhanced with function-calling capabilities. ## Motivation 🎯 Although BgGPT models demonstrate [strong Bulgarian language comprehension](https://arxiv.org/pdf/2412.10893), they face challenges in maintaining the precise formatting necessary for consistent function calling. Despite implementing detailed system prompts, their performance in this specific task remains suboptimal. This project addresses that gap by fine-tuning BgGPT, providing the Bulgarian AI community with proper tool-use capabilities in their native language. ## Models and variants 📦 Available in three sizes with full models, LoRA adapters, and quantized GGUF variants: <div align="center"> \| Model Size \| Full Model \| LoRA Adapter \| GGUF (Quantized) \| \|------------\|------------\|--------------\|------------------\| \| 2.6B \| [Tucan-2.6B-v1.0](https://huggingface.co/s-emanuilov/Tucan-2.6B-v1.0)\| [LoRA](https://huggingface.co/s-emanuilov/Tucan-2.6B-v1.0-LoRA) \| [GGUF](https://huggingface.co/s-emanuilov/Tucan-2.6B-v1.0-GGUF) \| \| 9B \| [Tucan-9B-v1.0](https://huggingface.co/s-emanuilov/Tucan-9B-v1.0) 📍\| [LoRA](https://huggingface.co/s-emanuilov/Tucan-9B-v1.0-LoRA) \| [GGUF](https://huggingface.co/s-emanuilov/Tucan-9B-v1.0-GGUF) \| \| 27B \| [Tucan-27B-v1.0](https://huggingface.co/s-emanuilov/Tucan-27B-v1.0) \| [LoRA](https://huggingface.co/s-emanuilov/Tucan-27B-v1.0-LoRA) \| [GGUF](https://huggingface.co/s-emanuilov/Tucan-27B-v1.0-GGUF) \| GGUF variants include: q4_k_m, q5_k_m, q6_k, q8_0, q4_0 quantizations 📍 Current model/repo </div> Models and quantizations are also available for easy use in Ollama: https://ollama.com/s_emanuilov/tucan ## Benchmarks 📊 All evaluations were performed using the [Tucan evaluation framework](https://github.com/s-emanuilov/tucan), with results averaged across multiple runs. Tucan models demonstrate superior function-calling capabilities compared to their BgGPT counterparts, with particularly strong improvements in smaller model sizes. To ensure no catastrophic forgetting occurred, we evaluated knowledge retention using [EleutherAI's lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness) on Bulgarian benchmarks, confirming that each Tucan model maintains performance on par with its BgGPT equivalent. <div align="center"> \| Model \| Function Calling \| HellaswagBG \| WinograndeBG \| ARC-Easy-BG \| ARC-Challenge-BG \| \|-------\|-----------------\|-------------\|--------------\|-------------\|------------------\| \| Tucan-2.6B-v1.0 🔥 \| 0.7875 \| 0.5924 \| 0.6456 \| 0.5657 \| 0.3754 \| \| Tucan-9B-v1.0 🔥 \| 0.8667 \| 0.7046 \| 0.7151 \| 0.7024 \| 0.5188 \| \| Tucan-27B-v1.0 🔥 \| 0.875 \| 0.6179 \| 0.6275 \| 0.6486 \| 0.442 \| \| BgGPT-Gemma-2-2.6B-IT-v1.0 \| 0.5874 \| 0.6306 \| 0.5821 \| 0.5657 \| 0.372 \| \| BgGPT-Gemma-2-9B-IT-v1.0 \| 0.7833 \| 0.7057 \| 0.719 \| 0.7231 \| 0.5188 \| \| BgGPT-Gemma-2-27B-IT-v1.0 \| 0.8667 \| 0.62 \| 0.6212 \| 0.6587 \| 0.459 \| Note: 27B models were evaluated in 8-bit precision for comparison purposes. </div> ## Usage 🛠️ ### Quick start ⚡ ```bash pip install -U "transformers[torch]" accelerate bitsandbytes ``` ### Prompt format ⚙️ Critical: Use this format for function calling for the best results. <details> <summary><strong>📋 Required system prompt template</strong></summary> ``` <bos><start_of_turn>user Ти си полезен AI асистент, който предоставя полезни и точни отговори. Имаш достъп и можеш да извикаш една или повече функции, за да помогнеш с потребителското запитване. Използвай ги, само ако е необходимо и подходящо. Когато използваш функция, форматирай извикването ѝ в блок ```tool_call``` на отделен ред, a след това ще получиш резултат от изпълнението в блок ```toll_response```. ## Шаблон за извикване: ```tool_call {"name": <function-name>, "arguments": <args-json-object>}``` ## Налични функции: [your function definitions here] ## Потребителска заявка: [your query in Bulgarian]<end_of_turn> <start_of_turn>model ``` </details> ### Note 📝 The model only generates the `tool_call` blocks with function names and parameters - it doesn't actually execute the functions. Your client application must parse these generated calls, execute the actual functions (API calls, database queries, etc.), and provide the results back to the model in `tool_response` blocks for the conversation to continue the interperation of the results. A full demo is comming soon. ### Python example 🐍 <details> <summary><strong>💻 Complete Working Example</strong></summary> ```python import torch import json from transformers import AutoModelForCausalLM, AutoTokenizer, GenerationConfig # Load model model_name = "s-emanuilov/Tucan-2.6B-v1.0" tokenizer = AutoTokenizer.from_pretrained(model_name) model = AutoModelForCausalLM.from_pretrained( model_name, torch_dtype=torch.bfloat16, device_map="auto", attn_implementation="eager" # Required for Gemma models ) # Create prompt with system template def create_prompt(functions, user_query): system_prompt = """Ти си полезен AI асистент, който предоставя полезни и точни отговори. Имаш достъп и можеш да извикаш една или повече функции, за да помогнеш с потребителското запитване. Използвай ги, само ако е необходимо и подходящо. Когато използваш функция, форматирай извикването ѝ в блок ```tool_call``` на отделен ред, a след това ще получиш резултат от изпълнението в блок ```toll_response```. ## Шаблон за извикване: ```tool_call {{"name": <function-name>, "arguments": <args-json-object>}}``` """ functions_text = json.dumps(functions, ensure_ascii=False, indent=2) full_prompt = f"{system_prompt}\n## Налични функции:\n{functions_text}\n\n## Потребителска заявка:\n{user_query}" chat = [{"role": "user", "content": full_prompt}] return tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=True) # Example usage functions = [{ "name": "create_calendar_event", "description": "Creates a new event in Google Calendar.", "parameters": { "type": "object", "properties": { "title": {"type": "string"}, "date": {"type": "string"}, "start_time": {"type": "string"}, "end_time": {"type": "string"} }, "required": ["title", "date", "start_time", "end_time"] } }] query = "Създай събитие 'Годишен преглед' за 8-ми юни 2025 от 14:00 до 14:30." # Generate response prompt = create_prompt(functions, query) inputs = tokenizer(prompt, return_tensors="pt").to(model.device) outputs = model.generate( inputs, max_new_tokens=2048, temperature=0.1, top_k=25, top_p=1.0, repetition_penalty=1.1, do_sample=True, eos_token_id=[tokenizer.eos_token_id, tokenizer.convert_tokens_to_ids("<end_of_turn>")], pad_token_id=tokenizer.eos_token_id ) result = tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True) print(result) ``` </details> ## Performance & Dataset 📊 > 📄 Full methodology, dataset details, and comprehensive evaluation results coming in the upcoming paper Dataset: 10,000+ bilingual (Bulgarian/English) function-calling examples across 1,000+ topics, including tool calls with single/multiple arguments, optional parameters, follow-up queries, multi-tool selection, ambiguous queries requiring clarification, and conversational interactions without tool use. Data sourced from manual curation and synthetic generation (Gemini Pro 2.5/GPT-4.1/Sonnet 4). Results: Significant improvements in tool-use capabilities over base BgGPT models: 34.1% for 2.6B, 10.6% for 9B, and 1.0% for 27B models in [internal benchmarks](https://github.com/s-emanuilov/tucan). Beyond raw function-calling scores, all Tucan models demonstrate more natural conversational flow while maintaining tool-use capabilities, retaining their base knowledge. ## Acknowledgments 🙏 Built on top of [BgGPT series](https://huggingface.co/collections/INSAIT-Institute/bggpt-gemma-2-673b972fe9902749ac90f6fe). ## Questions & Contact 💬 For questions, collaboration, or feedback: [Connect on LinkedIn](https://www.linkedin.com/in/simeon-emanuilov/)**
Sah-Sapna-Kumari-Viral-Video/NEW.VIDEO.Sah.Sapna.Kumari.Viral.Video.Link.Download	Sah-Sapna-Kumari-Viral-Video	2025-06-16T05:42:00Z	0	0	null	[ "region:us" ]	null	2025-06-16T05:41:41Z	[![WATCH LIVE](https://i.imgur.com/AgNJ672.gif)](https://tinyurl.com/updateon365)
Nirma-Meena-Full-Video/TRENDING_Top.Nirma.Meena.Official.Viral.Video	Nirma-Meena-Full-Video	2025-06-16T05:41:53Z	0	0	null	[ "region:us" ]	null	2025-06-16T05:41:38Z	[![My Image](https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif)](https://bit.ly/4lb0YGM)
New-parveen-virals/Video.parveen.viral.video.bilasipara.new.video.parbin.bilasipara.viral.video.link	New-parveen-virals	2025-06-16T05:41:02Z	0	0	null	[ "region:us" ]	null	2025-06-16T05:36:26Z	<a rel="nofollow" href="https://tinyurl.com/2urtu5zm">🌐 𝖢𝖫𝖨𝖢𝖪 𝖧𝖤𝖱𝖤 🟢==►► 𝖶𝖠𝖳𝖢𝖧 𝖭𝖮𝖶 L𝚎aᴋed Video V𝐢ral Video</a> <a href="https://tinyurl.com/2urtu5zm"><img src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" alt="Nature" class="responsive"></a>
parveen-ka-viral-video/Original.18.parveen.viral.video.bilasipara.new.video.parbin.bilasipara.viral.video.link	parveen-ka-viral-video	2025-06-16T05:40:57Z	0	0	null	[ "region:us" ]	null	2025-06-16T05:36:14Z	<a rel="nofollow" href="https://tinyurl.com/2urtu5zm">🌐 𝖢𝖫𝖨𝖢𝖪 𝖧𝖤𝖱𝖤 🟢==►► 𝖶𝖠𝖳𝖢𝖧 𝖭𝖮𝖶 L𝚎aᴋed Video V𝐢ral Video</a> <a href="https://tinyurl.com/2urtu5zm"><img src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" alt="Nature" class="responsive"></a>
VIDEO-mezzo-fun-viral-video-Clip-Original/mezzo.fun.viral.video.Link.viral.On.Social.Media	VIDEO-mezzo-fun-viral-video-Clip-Original	2025-06-16T05:39:42Z	0	0	null	[ "region:us" ]	null	2025-06-16T05:39:21Z	<a href="https://t.co/dTvnXACQMR" 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>
MinaMila/phi3_unlearned_2nd_5e-7_1.0_0.25_0.25_0.05_epoch2	MinaMila	2025-06-16T05:39:29Z	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	2025-06-16T05:37:36Z	--- 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]
kleverer/natix-009	kleverer	2025-06-16T05:38:30Z	0	0	transformers	[ "transformers", "tensorboard", "safetensors", "vit", "image-classification", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]	image-classification	2025-06-16T05:38:15Z	--- 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]
Nirma-Meena-Full-Video/Nirma.Meena.Official.Viral.Video	Nirma-Meena-Full-Video	2025-06-16T05:38:13Z	0	0	null	[ "region:us" ]	null	2025-06-16T05:37:47Z	[![My Image](https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif)](https://bit.ly/4lb0YGM)
yashkalu/deep_learning	yashkalu	2025-06-16T05:37:47Z	0	0	null	[ "license:apache-2.0", "region:us" ]	null	2025-06-16T05:37:47Z	--- license: apache-2.0 ---
Ayesha-Khan-Official-Viral-Video/FULL.VIDEO.Ayesha.Khan.Viral.Video.Tutorial.Official	Ayesha-Khan-Official-Viral-Video	2025-06-16T05:36:03Z	0	0	null	[ "region:us" ]	null	2025-06-16T05:35:35Z	<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>
s-emanuilov/Tucan-2.6B-v1.0	s-emanuilov	2025-06-16T05:35:49Z	187	1	null	[ "safetensors", "gemma2", "function_calling", "MCP", "tool_use", "bg", "arxiv:2503.23278", "arxiv:2408.00118", "arxiv:2412.10893", "base_model:INSAIT-Institute/BgGPT-Gemma-2-2.6B-IT-v1.0", "base_model:finetune:INSAIT-Institute/BgGPT-Gemma-2-2.6B-IT-v1.0", "license:gemma", "region:us" ]	null	2025-06-07T21:26:39Z	--- license: gemma language: - bg base_model: - INSAIT-Institute/BgGPT-Gemma-2-2.6B-IT-v1.0 tags: - function_calling - MCP - tool_use --- # Tucan-2.6B-v1.0 ## Bulgarian Language Models for Function Calling 🇧🇬 > 📄 Full methodology, dataset details, and evaluation results coming in the upcoming paper ## Overview 🚀 TUCAN (Tool-Using Capable Assistant Navigator) is a series of open-source Bulgarian language models fine-tuned specifically for function calling and tool use. These models can interact with external tools, APIs, and databases, making them appropriate for building AI agents and [Model Context Protocol (MCP)](https://arxiv.org/abs/2503.23278) applications. Built on top of [BgGPT models](https://huggingface.co/collections/INSAIT-Institute/bggpt-gemma-2-673b972fe9902749ac90f6fe) from [INSAIT Institute](https://insait.ai/), which were themselves built on [Gemma 2](https://arxiv.org/pdf/2408.00118), Tucan models have been enhanced with function-calling capabilities. ## Motivation 🎯 Although BgGPT models demonstrate [strong Bulgarian language comprehension](https://arxiv.org/pdf/2412.10893), they face challenges in maintaining the precise formatting necessary for consistent function calling. Despite implementing detailed system prompts, their performance in this specific task remains suboptimal. This project addresses that gap by fine-tuning BgGPT, providing the Bulgarian AI community with proper tool-use capabilities in their native language. ## Models and variants 📦 Available in three sizes with full models, LoRA adapters, and quantized GGUF variants: <div align="center"> \| Model Size \| Full Model \| LoRA Adapter \| GGUF (Quantized) \| \|------------\|------------\|--------------\|------------------\| \| 2.6B \| [Tucan-2.6B-v1.0](https://huggingface.co/s-emanuilov/Tucan-2.6B-v1.0) 📍\| [LoRA](https://huggingface.co/s-emanuilov/Tucan-2.6B-v1.0-LoRA) \| [GGUF](https://huggingface.co/s-emanuilov/Tucan-2.6B-v1.0-GGUF) \| \| 9B \| [Tucan-9B-v1.0](https://huggingface.co/s-emanuilov/Tucan-9B-v1.0) \| [LoRA](https://huggingface.co/s-emanuilov/Tucan-9B-v1.0-LoRA) \| [GGUF](https://huggingface.co/s-emanuilov/Tucan-9B-v1.0-GGUF) \| \| 27B \| [Tucan-27B-v1.0](https://huggingface.co/s-emanuilov/Tucan-27B-v1.0) \| [LoRA](https://huggingface.co/s-emanuilov/Tucan-27B-v1.0-LoRA) \| [GGUF](https://huggingface.co/s-emanuilov/Tucan-27B-v1.0-GGUF) \| GGUF variants include: q4_k_m, q5_k_m, q6_k, q8_0, q4_0 quantizations 📍 Current model/repo </div> Models and quantizations are also available for easy use in Ollama: https://ollama.com/s_emanuilov/tucan ## Benchmarks 📊 All evaluations were performed using the [Tucan evaluation framework](https://github.com/s-emanuilov/tucan), with results averaged across multiple runs. Tucan models demonstrate superior function-calling capabilities compared to their BgGPT counterparts, with particularly strong improvements in smaller model sizes. To ensure no catastrophic forgetting occurred, we evaluated knowledge retention using [EleutherAI's lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness) on Bulgarian benchmarks, confirming that each Tucan model maintains performance on par with its BgGPT equivalent. <div align="center"> \| Model \| Function Calling \| HellaswagBG \| WinograndeBG \| ARC-Easy-BG \| ARC-Challenge-BG \| \|-------\|-----------------\|-------------\|--------------\|-------------\|------------------\| \| Tucan-2.6B-v1.0 🔥 \| 0.7875 \| 0.5924 \| 0.6456 \| 0.5657 \| 0.3754 \| \| Tucan-9B-v1.0 🔥 \| 0.8667 \| 0.7046 \| 0.7151 \| 0.7024 \| 0.5188 \| \| Tucan-27B-v1.0 🔥 \| 0.875 \| 0.6179 \| 0.6275 \| 0.6486 \| 0.442 \| \| BgGPT-Gemma-2-2.6B-IT-v1.0 \| 0.5874 \| 0.6306 \| 0.5821 \| 0.5657 \| 0.372 \| \| BgGPT-Gemma-2-9B-IT-v1.0 \| 0.7833 \| 0.7057 \| 0.719 \| 0.7231 \| 0.5188 \| \| BgGPT-Gemma-2-27B-IT-v1.0 \| 0.8667 \| 0.62 \| 0.6212 \| 0.6587 \| 0.459 \| Note: 27B models were evaluated in 8-bit precision for comparison purposes. </div> ## Usage 🛠️ ### Quick start ⚡ ```bash pip install -U "transformers[torch]" accelerate bitsandbytes ``` ### Prompt format ⚙️ Critical: Use this format for function calling for the best results. <details> <summary><strong>📋 Required system prompt template</strong></summary> ``` <bos><start_of_turn>user Ти си полезен AI асистент, който предоставя полезни и точни отговори. Имаш достъп и можеш да извикаш една или повече функции, за да помогнеш с потребителското запитване. Използвай ги, само ако е необходимо и подходящо. Когато използваш функция, форматирай извикването ѝ в блок ```tool_call``` на отделен ред, a след това ще получиш резултат от изпълнението в блок ```toll_response```. ## Шаблон за извикване: ```tool_call {"name": <function-name>, "arguments": <args-json-object>}``` ## Налични функции: [your function definitions here] ## Потребителска заявка: [your query in Bulgarian]<end_of_turn> <start_of_turn>model ``` </details> ### Note 📝 The model only generates the `tool_call` blocks with function names and parameters - it doesn't actually execute the functions. Your client application must parse these generated calls, execute the actual functions (API calls, database queries, etc.), and provide the results back to the model in `tool_response` blocks for the conversation to continue the interperation of the results. A full demo is comming soon. ### Python example 🐍 <details> <summary><strong>💻 Complete Working Example</strong></summary> ```python import torch import json from transformers import AutoModelForCausalLM, AutoTokenizer, GenerationConfig # Load model model_name = "s-emanuilov/Tucan-2.6B-v1.0" tokenizer = AutoTokenizer.from_pretrained(model_name) model = AutoModelForCausalLM.from_pretrained( model_name, torch_dtype=torch.bfloat16, device_map="auto", attn_implementation="eager" # Required for Gemma models ) # Create prompt with system template def create_prompt(functions, user_query): system_prompt = """Ти си полезен AI асистент, който предоставя полезни и точни отговори. Имаш достъп и можеш да извикаш една или повече функции, за да помогнеш с потребителското запитване. Използвай ги, само ако е необходимо и подходящо. Когато използваш функция, форматирай извикването ѝ в блок ```tool_call``` на отделен ред, a след това ще получиш резултат от изпълнението в блок ```toll_response```. ## Шаблон за извикване: ```tool_call {{"name": <function-name>, "arguments": <args-json-object>}}``` """ functions_text = json.dumps(functions, ensure_ascii=False, indent=2) full_prompt = f"{system_prompt}\n## Налични функции:\n{functions_text}\n\n## Потребителска заявка:\n{user_query}" chat = [{"role": "user", "content": full_prompt}] return tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=True) # Example usage functions = [{ "name": "create_calendar_event", "description": "Creates a new event in Google Calendar.", "parameters": { "type": "object", "properties": { "title": {"type": "string"}, "date": {"type": "string"}, "start_time": {"type": "string"}, "end_time": {"type": "string"} }, "required": ["title", "date", "start_time", "end_time"] } }] query = "Създай събитие 'Годишен преглед' за 8-ми юни 2025 от 14:00 до 14:30." # Generate response prompt = create_prompt(functions, query) inputs = tokenizer(prompt, return_tensors="pt").to(model.device) outputs = model.generate( inputs, max_new_tokens=2048, temperature=0.1, top_k=25, top_p=1.0, repetition_penalty=1.1, do_sample=True, eos_token_id=[tokenizer.eos_token_id, tokenizer.convert_tokens_to_ids("<end_of_turn>")], pad_token_id=tokenizer.eos_token_id ) result = tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True) print(result) ``` </details> ## Performance & Dataset 📊 > 📄 Full methodology, dataset details, and comprehensive evaluation results coming in the upcoming paper Dataset: 10,000+ bilingual (Bulgarian/English) function-calling examples across 1,000+ topics, including tool calls with single/multiple arguments, optional parameters, follow-up queries, multi-tool selection, ambiguous queries requiring clarification, and conversational interactions without tool use. Data sourced from manual curation and synthetic generation (Gemini Pro 2.5/GPT-4.1/Sonnet 4). Results: Significant improvements in tool-use capabilities over base BgGPT models: 34.1% for 2.6B, 10.6% for 9B, and 1.0% for 27B models in [internal benchmarks](https://github.com/s-emanuilov/tucan). Beyond raw function-calling scores, all Tucan models demonstrate more natural conversational flow while maintaining tool-use capabilities, retaining their base knowledge. ## Acknowledgments 🙏 Built on top of [BgGPT series](https://huggingface.co/collections/INSAIT-Institute/bggpt-gemma-2-673b972fe9902749ac90f6fe). ## Questions & Contact 💬 For questions, collaboration, or feedback: [Connect on LinkedIn](https://www.linkedin.com/in/simeon-emanuilov/)**
viral-othoi-113-video-link/TRENDING.Top.Othoi.Official.Viral.Video	viral-othoi-113-video-link	2025-06-16T05:35:32Z	0	0	null	[ "region:us" ]	null	2025-06-16T05:35:22Z	01 seconds ago [🌐 𝖢𝖫𝖨𝖢𝖪 𝖧𝖤𝖱𝖤 🟢==►► 𝖶𝖠𝖳𝖢𝖧 𝖭𝖮𝖶](https://sahabagi-mgi.blogspot.com/p/heres-now.html) [🌐 𝖢𝖫𝖨𝖢𝖪 𝖧𝖤𝖱𝖤 🟢==►► 𝖶𝖠𝖳𝖢𝖧 𝖭𝖮𝖶 FREE](https://sahabagi-mgi.blogspot.com/p/heres-now.html) <a href="https://sahabagi-mgi.blogspot.com/p/heres-now.html" rel="nofollow" data-target="animated-image.originalLink"><img src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" alt="WATCH Videos" data-canonical-src="https://i.imgur.com/dJHk4Zq.gif" style="max-width: 100%; display: inline-block;" data-target="animated-image.originalImage"></a>
willeybro/roadwork	willeybro	2025-06-16T05:34:49Z	0	0	transformers	[ "transformers", "tensorboard", "safetensors", "vit", "image-classification", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]	image-classification	2025-06-16T05:11:36Z	--- 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]
Nirmit1/lora_bart_base_model	Nirmit1	2025-06-16T05:34:19Z	0	0	transformers	[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2025-06-16T05:16:29Z	--- 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]
kleverer/natix-007	kleverer	2025-06-16T05:33:54Z	0	0	transformers	[ "transformers", "tensorboard", "safetensors", "vit", "image-classification", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]	image-classification	2025-06-16T05:33:39Z	--- 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]
MinaMila/phi3_unlearned_2nd_5e-7_1.0_0.25_0.25_0.05_epoch1	MinaMila	2025-06-16T05:32:52Z	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	2025-06-16T05:31:01Z	--- 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]
Nirma-Meena-Full-Video/VIRAL-VIDEO.Nirma.Meena.Viral.Video.Original.Link	Nirma-Meena-Full-Video	2025-06-16T05:30:58Z	0	0	null	[ "region:us" ]	null	2025-06-16T05:27:14Z	[![My Image](https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif)](https://bit.ly/4lb0YGM)
Clip-Parveen-Viral-Video/Full.VIDEO.Parveen.Viral.Video.Tutorial.Official	Clip-Parveen-Viral-Video	2025-06-16T05:29:15Z	0	0	null	[ "region:us" ]	null	2025-06-16T05:28:54Z	Parveen Viral video took the internet viewers on various Leaked social media platforms. Parveen Video, a young and talented digital creator, recently became famous thanks to this interesting video. <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>
KaiChen1998/RACRO-7B-CRO	KaiChen1998	2025-06-16T05:28:40Z	0	0	transformers	[ "transformers", "safetensors", "qwen2_5_vl", "image-text-to-text", "multi-modal-reasoning", "conversational", "dataset:TIGER-Lab/ViRL39K", "arxiv:2506.04559", "base_model:Qwen/Qwen2.5-VL-7B-Instruct", "base_model:finetune:Qwen/Qwen2.5-VL-7B-Instruct", "license:apache-2.0", "text-generation-inference", "endpoints_compatible", "region:us" ]	image-text-to-text	2025-06-15T13:22:47Z	--- library_name: transformers tags: - multi-modal-reasoning license: apache-2.0 datasets: - TIGER-Lab/ViRL39K base_model: - Qwen/Qwen2.5-VL-7B-Instruct new_version: KaiChen1998/RACRO-7B-CRO-GRPO --- # RACRO-7B-CRO <div align="center"> 📄 [Paper](https://arxiv.org/abs/2506.04559) \| 💻 [Github](https://github.com/gyhdog99/RACRO2/) \| 🤗 [RACRO-Models](https://huggingface.co/collections/KaiChen1998/racro-6848ec8c65b3a0bf33d0fbdb) \| 🤗 [RACRO-Demo](https://huggingface.co/spaces/Emova-ollm/RACRO-demo) </div> ## Model Summary RACRO (Reasoning-Aligned Perceptual Decoupling via Caption Reward Optimization) is a novel framework that enables scalable and modular multimodal reasoning by aligning visual perception with a powerful text-only reasoner. RACRO addresses the key challenge of generating image captions that are both faithful and sufficiently informative for downstream reasoning. It leverages a reasoning-guided reinforcement learning strategy to train the visual extractor, using reward signals derived from the performance of a fixed, high-capacity text-only LLM. This decoupled design avoids costly retraining of vision-language alignments and allows seamless plug-and-play upgrades to more advanced reasoners. Experiments on multimodal math and science benchmarks show that RACRO achieves state-of-the-art performance among open models. <div align="center"> <img src="https://github.com/gyhdog99/RACRO2/blob/main/assets/images/intro.png?raw=true" width=100%></img> </div> ## Results <div align="center"> <img src="https://github.com/gyhdog99/RACRO2/blob/main/assets/images/results.png?raw=true" width=100%></img> </div> ## Usage ```python from transformers import AutoProcessor, AutoTokenizer from vllm import LLM, SamplingParams from qwen_vl_utils import process_vision_info ######################## # === Configuration === ######################## IMAGE_PATH = "./assets/images/demo_example.jpg" QUESTION = "When the canister is momentarily stopped by the spring, by what distance $d$ is the spring compressed?" MLLM_MODEL_PATH = "KaiChen1998/RACRO-7B-CRO" LLM_MODEL_PATH = "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B" # feel free to use more advanced reasoners! ######################## # === Prompts === ######################## SYSTEM_PROMPT_CAP = "You are given an image and a relevant question. Based on the query, please describe the image in details. Do not try to answer the question." SYSTEM_PROMPT_LLM = "You are a helpful assistant." CAPTION_PROMPT = "Question: {}\nPlease describe the image. DO NOT try to answer the question!" LLM_PROMPT = """In the following text, you will receive a detailed caption of an image and a relevant question. In addition, you will be provided with a tentative model response. You goal is to answer the question using these information. ### The detailed caption of the provided image: {} ### Note that the caption might contain incorrect solutions, do not be misguided by them. ### A problem to be solved: {} ### A tentative model response: {} ### Note that the above tentative response might be inaccurate (due to calculation errors, incorrect logic/reasoning and so on), under such a case, please ignore it and give your own solutions. However, if you do not have enough evidence to show it is wrong, please output the tentative response.""" ######################## # === Initialize Models === ######################## processor = AutoProcessor.from_pretrained(MLLM_MODEL_PATH) tokenizer = AutoTokenizer.from_pretrained(LLM_MODEL_PATH) mllm = LLM(model=MLLM_MODEL_PATH, tensor_parallel_size=1, gpu_memory_utilization=0.8, device='cuda:0', dtype="bfloat16", limit_mm_per_prompt={"image": 1}) llm = LLM(model=LLM_MODEL_PATH, tensor_parallel_size=1, gpu_memory_utilization=0.8, device='cuda:1', dtype="bfloat16") mllm_sampling = SamplingParams(temperature=0, max_tokens=8192) llm_sampling = SamplingParams(temperature=0.6, top_p=0.95, max_tokens=8192) ######################## # === Build Prompts === ######################## def build_messages(image_path, question): cap_msgs = [ {"role": "system", "content": SYSTEM_PROMPT_CAP}, {"role": "user", "content": [{"type": "image", "image": image_path}, {"type": "text", "text": CAPTION_PROMPT.format(question)}]} ] qa_msgs = [ {"role": "user", "content": [{"type": "image", "image": image_path}, {"type": "text", "text": question + " Please think step by step. The final answer MUST BE put in \\boxed{}."}]} ] return cap_msgs, qa_msgs # === Run Captioning and QA === def run_mllm(image_tensor, cap_prompt, qa_prompt): cap_output = mllm.generate([{"multi_modal_data": {"image": image_tensor}, "prompt": cap_prompt[0]}], sampling_params=mllm_sampling) qa_output = mllm.generate([{"multi_modal_data": {"image": image_tensor}, "prompt": qa_prompt[0]}], sampling_params=mllm_sampling) return cap_output[0].outputs[0].text, qa_output[0].outputs[0].text # === Final Reasoning Step === def run_llm_reasoning(caption, question, answer): messages = [ {"role": "system", "content": SYSTEM_PROMPT_LLM}, {"role": "user", "content": LLM_PROMPT.format(caption, question, answer)} ] prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) output = llm.generate([{"prompt": prompt}], sampling_params=llm_sampling) return output[0].outputs[0].text ######################## # === Pipeline === ######################## cap_msgs, qa_msgs = build_messages(IMAGE_PATH, QUESTION) cap_prompt = processor.apply_chat_template([cap_msgs], tokenize=False, add_generation_prompt=True) qa_prompt = processor.apply_chat_template([qa_msgs], tokenize=False, add_generation_prompt=True) image_tensor, _ = process_vision_info(cap_msgs) caption_text, tentative_answer = run_mllm(image_tensor, cap_prompt, qa_prompt) final_answer = run_llm_reasoning(caption_text, QUESTION, tentative_answer) print("Final Answer:\n", final_answer) ``` ## Citation ```bibtex @article{gou2025perceptual, author = {Gou, Yunhao and Chen, Kai and Liu, Zhili and Hong, Lanqing and Jin, Xin and Li, Zhenguo and Kwok, James T. and Zhang, Yu}, title = {Perceptual Decoupling for Scalable Multi-modal Reasoning via Reward-Optimized Captioning}, journal = {arXiv preprint arXiv:2506.04559}, year = {2025}, } ```
KaiChen1998/RACRO-7B-CRO-GRPO	KaiChen1998	2025-06-16T05:28:37Z	0	0	transformers	[ "transformers", "safetensors", "qwen2_5_vl", "image-text-to-text", "multi-modal-reasoning", "conversational", "dataset:TIGER-Lab/ViRL39K", "arxiv:2506.04559", "base_model:Qwen/Qwen2.5-VL-7B-Instruct", "base_model:finetune:Qwen/Qwen2.5-VL-7B-Instruct", "license:apache-2.0", "text-generation-inference", "endpoints_compatible", "region:us" ]	image-text-to-text	2025-06-15T14:12:53Z	--- library_name: transformers tags: - multi-modal-reasoning license: apache-2.0 datasets: - TIGER-Lab/ViRL39K base_model: - Qwen/Qwen2.5-VL-7B-Instruct --- # RACRO-7B-CRO-GRPO <div align="center"> 📄 [Paper](https://arxiv.org/abs/2506.04559) \| 💻 [Github](https://github.com/gyhdog99/RACRO2/) \| 🤗 [RACRO-Models](https://huggingface.co/collections/KaiChen1998/racro-6848ec8c65b3a0bf33d0fbdb) \| 🤗 [RACRO-Demo](https://huggingface.co/spaces/Emova-ollm/RACRO-demo) </div> ## Model Summary RACRO (Reasoning-Aligned Perceptual Decoupling via Caption Reward Optimization) is a novel framework that enables scalable and modular multimodal reasoning by aligning visual perception with a powerful text-only reasoner. RACRO addresses the key challenge of generating image captions that are both faithful and sufficiently informative for downstream reasoning. It leverages a reasoning-guided reinforcement learning strategy to train the visual extractor, using reward signals derived from the performance of a fixed, high-capacity text-only LLM. This decoupled design avoids costly retraining of vision-language alignments and allows seamless plug-and-play upgrades to more advanced reasoners. Experiments on multimodal math and science benchmarks show that RACRO achieves state-of-the-art performance among open models. <div align="center"> <img src="https://github.com/gyhdog99/RACRO2/blob/main/assets/images/intro.png?raw=true" width=100%></img> </div> ## Results <div align="center"> <img src="https://github.com/gyhdog99/RACRO2/blob/main/assets/images/results.png?raw=true" width=100%></img> </div> ## Usage ```python from transformers import AutoProcessor, AutoTokenizer from vllm import LLM, SamplingParams from qwen_vl_utils import process_vision_info ######################## # === Configuration === ######################## IMAGE_PATH = "./assets/images/demo_example.jpg" QUESTION = "When the canister is momentarily stopped by the spring, by what distance $d$ is the spring compressed?" MLLM_MODEL_PATH = "KaiChen1998/RACRO-7B-CRO-GRPO" LLM_MODEL_PATH = "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B" # feel free to use more advanced reasoners! ######################## # === Prompts === ######################## SYSTEM_PROMPT_CAP = "You are given an image and a relevant question. Based on the query, please describe the image in details. Do not try to answer the question." SYSTEM_PROMPT_LLM = "You are a helpful assistant." CAPTION_PROMPT = "Question: {}\nPlease describe the image. DO NOT try to answer the question!" LLM_PROMPT = """In the following text, you will receive a detailed caption of an image and a relevant question. In addition, you will be provided with a tentative model response. You goal is to answer the question using these information. ### The detailed caption of the provided image: {} ### Note that the caption might contain incorrect solutions, do not be misguided by them. ### A problem to be solved: {} ### A tentative model response: {} ### Note that the above tentative response might be inaccurate (due to calculation errors, incorrect logic/reasoning and so on), under such a case, please ignore it and give your own solutions. However, if you do not have enough evidence to show it is wrong, please output the tentative response.""" ######################## # === Initialize Models === ######################## processor = AutoProcessor.from_pretrained(MLLM_MODEL_PATH) tokenizer = AutoTokenizer.from_pretrained(LLM_MODEL_PATH) mllm = LLM(model=MLLM_MODEL_PATH, tensor_parallel_size=1, gpu_memory_utilization=0.8, device='cuda:0', dtype="bfloat16", limit_mm_per_prompt={"image": 1}) llm = LLM(model=LLM_MODEL_PATH, tensor_parallel_size=1, gpu_memory_utilization=0.8, device='cuda:1', dtype="bfloat16") mllm_sampling = SamplingParams(temperature=0, max_tokens=8192) llm_sampling = SamplingParams(temperature=0.6, top_p=0.95, max_tokens=8192) ######################## # === Build Prompts === ######################## def build_messages(image_path, question): cap_msgs = [ {"role": "system", "content": SYSTEM_PROMPT_CAP}, {"role": "user", "content": [{"type": "image", "image": image_path}, {"type": "text", "text": CAPTION_PROMPT.format(question)}]} ] qa_msgs = [ {"role": "user", "content": [{"type": "image", "image": image_path}, {"type": "text", "text": question + " Please think step by step. The final answer MUST BE put in \\boxed{}."}]} ] return cap_msgs, qa_msgs # === Run Captioning and QA === def run_mllm(image_tensor, cap_prompt, qa_prompt): cap_output = mllm.generate([{"multi_modal_data": {"image": image_tensor}, "prompt": cap_prompt[0]}], sampling_params=mllm_sampling) qa_output = mllm.generate([{"multi_modal_data": {"image": image_tensor}, "prompt": qa_prompt[0]}], sampling_params=mllm_sampling) return cap_output[0].outputs[0].text, qa_output[0].outputs[0].text # === Final Reasoning Step === def run_llm_reasoning(caption, question, answer): messages = [ {"role": "system", "content": SYSTEM_PROMPT_LLM}, {"role": "user", "content": LLM_PROMPT.format(caption, question, answer)} ] prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) output = llm.generate([{"prompt": prompt}], sampling_params=llm_sampling) return output[0].outputs[0].text ######################## # === Pipeline === ######################## cap_msgs, qa_msgs = build_messages(IMAGE_PATH, QUESTION) cap_prompt = processor.apply_chat_template([cap_msgs], tokenize=False, add_generation_prompt=True) qa_prompt = processor.apply_chat_template([qa_msgs], tokenize=False, add_generation_prompt=True) image_tensor, _ = process_vision_info(cap_msgs) caption_text, tentative_answer = run_mllm(image_tensor, cap_prompt, qa_prompt) final_answer = run_llm_reasoning(caption_text, QUESTION, tentative_answer) print("Final Answer:\n", final_answer) ``` ## Citation ```bibtex @article{gou2025perceptual, author = {Gou, Yunhao and Chen, Kai and Liu, Zhili and Hong, Lanqing and Jin, Xin and Li, Zhenguo and Kwok, James T. and Zhang, Yu}, title = {Perceptual Decoupling for Scalable Multi-modal Reasoning via Reward-Optimized Captioning}, journal = {arXiv preprint arXiv:2506.04559}, year = {2025}, } ```
MinaMila/phi3_unlearned_2nd_5e-7_1.0_0.25_0.25_0.15_epoch2	MinaMila	2025-06-16T05:25:57Z	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	2025-06-16T05:24:04Z	--- 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]
tv-nulook-india-18k/Original.Full.Clip.nulook.india.Viral.Videos.Leaks.Official	tv-nulook-india-18k	2025-06-16T05:25:09Z	0	0	null	[ "region:us" ]	null	2025-06-16T05:24:03Z	Nulookindia Video New collections of Nulookindia Video now being a creator on Fanfix uploading adult contents <a href="https://tinyurl.com/2urtu5zm"><img src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" alt="Nature" class="responsive"></a>
VIDEOS-18-imsha-rehman-Viral-Video/FULL.VIDEO.imsha.rehman.Viral.Video.Tutorial.Official	VIDEOS-18-imsha-rehman-Viral-Video	2025-06-16T05:23:24Z	0	0	null	[ "region:us" ]	null	2025-06-16T05:23:02Z	<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>
yinita/cpdc-qwen3-14b-maintask2-v0614-v6-lora-cp-sync-by-lian-1epoch	yinita	2025-06-16T05:21:43Z	0	0	transformers	[ "transformers", "safetensors", "qwen3", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-06-16T05:18:29Z	--- 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/phi3_unlearned_2nd_5e-7_1.0_0.25_0.25_0.15_epoch1	MinaMila	2025-06-16T05:19:22Z	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	2025-06-16T05:17:33Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
TV-nulook-india-viral-video/nulook.india.viral.video.original.nulook.india.nulookindia.video.mms	TV-nulook-india-viral-video	2025-06-16T05:18:06Z	0	0	null	[ "region:us" ]	null	2025-06-16T05:17:05Z	"03 Second — Nulookindia Video New collections of Nulookindia Video now being a creator on Fanfix uploading adult contents <a href="https://tinyurl.com/2urtu5zm"><img src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" alt="Nature" class="responsive"></a>
rafamartins/rafa.martins.e.cadeirante.twitter.rafa.martins.e.cadeirante.twitter	rafamartins	2025-06-16T05:16:37Z	0	0	null	[ "region:us" ]	null	2025-06-16T05:15:29Z	Watch 🟢 ➤ ➤ ➤ <a href="https://viraltrendzzz.com/scsscsc"> 🌐 Click Here To link (Watch-Video-18rafa.martins.e.cadeirante.twitter) 🔴 ➤►DOWNLOAD👉👉🟢 ➤Watch 🟢 ➤ ➤ ➤ <a href="https://viraltrendzzz.com/scsscsc"> 🌐 Watch-Video-18rafa.martins.e.cadeirante.twitter
JayHyeon/Qwen_1.5B-math-VIPO_5e-7_3.0vpo_constant-5ep	JayHyeon	2025-06-16T05:15:55Z	0	0	transformers	[ "transformers", "tensorboard", "safetensors", "qwen2", "text-generation", "generated_from_trainer", "trl", "dpo", "conversational", "dataset:argilla/distilabel-math-preference-dpo", "arxiv:2305.18290", "base_model:Qwen/Qwen2.5-Math-1.5B", "base_model:finetune:Qwen/Qwen2.5-Math-1.5B", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-06-16T04:51:26Z	--- base_model: Qwen/Qwen2.5-Math-1.5B datasets: argilla/distilabel-math-preference-dpo library_name: transformers model_name: Qwen_1.5B-math-VIPO_5e-7_3.0vpo_constant-5ep tags: - generated_from_trainer - trl - dpo licence: license --- # Model Card for Qwen_1.5B-math-VIPO_5e-7_3.0vpo_constant-5ep This model is a fine-tuned version of [Qwen/Qwen2.5-Math-1.5B](https://huggingface.co/Qwen/Qwen2.5-Math-1.5B) on the [argilla/distilabel-math-preference-dpo](https://huggingface.co/datasets/argilla/distilabel-math-preference-dpo) dataset. It has been trained using [TRL](https://github.com/huggingface/trl). ## Quick start ```python from transformers import pipeline question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?" generator = pipeline("text-generation", model="JayHyeon/Qwen_1.5B-math-VIPO_5e-7_3.0vpo_constant-5ep", 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/bonin147/huggingface/runs/3v3b3vb1) This model was trained with DPO, a method introduced in [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://huggingface.co/papers/2305.18290). ### Framework versions - TRL: 0.15.2 - Transformers: 4.50.0 - Pytorch: 2.6.0 - Datasets: 3.4.1 - Tokenizers: 0.21.1 ## Citations Cite DPO as: ```bibtex @inproceedings{rafailov2023direct, title = {{Direct Preference Optimization: Your Language Model is Secretly a Reward Model}}, author = {Rafael Rafailov and Archit Sharma and Eric Mitchell and Christopher D. Manning and Stefano Ermon and Chelsea Finn}, year = 2023, booktitle = {Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023}, url = {http://papers.nips.cc/paper_files/paper/2023/hash/a85b405ed65c6477a4fe8302b5e06ce7-Abstract-Conference.html}, editor = {Alice Oh and Tristan Naumann and Amir Globerson and Kate Saenko and Moritz Hardt and Sergey Levine}, } ``` Cite TRL as: ```bibtex @misc{vonwerra2022trl, title = {{TRL: Transformer Reinforcement Learning}}, author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec}, year = 2020, journal = {GitHub repository}, publisher = {GitHub}, howpublished = {\url{https://github.com/huggingface/trl}} } ```
Pakistani-Viral-Video/VIDEO.Pakistani.Viral.Video.Tutorial.Official	Pakistani-Viral-Video	2025-06-16T05:13:08Z	0	0	null	[ "region:us" ]	null	2025-06-16T05:10:21Z	<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>
ramzanniaz331/lora_model_llama_3_2_3b_instruction_finetuning	ramzanniaz331	2025-06-16T05:11:29Z	0	0	transformers	[ "transformers", "safetensors", "text-generation-inference", "unsloth", "llama", "trl", "en", "license:apache-2.0", "endpoints_compatible", "region:us" ]	null	2025-06-16T05:11:01Z	--- 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: ramzanniaz331 - 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)
hitty28/branch-switch-classifier	hitty28	2025-06-16T05:11:00Z	0	0	null	[ "safetensors", "distilbert", "text-classification", "branch-switching", "hospital-chatbot", "en", "dataset:branch_switch_classification", "license:apache-2.0", "region:us" ]	text-classification	2025-06-16T05:10:40Z	--- language: en license: apache-2.0 tags: - text-classification - branch-switching - hospital-chatbot - distilbert datasets: - branch_switch_classification widget: - text: "I want to switch to Mumbai branch" - text: "What are your hospital timings?" - text: "Can I change to the branch near my home?" --- # Branch Switch Classification Model This model classifies whether a user wants to switch hospital branches or is asking for general information. ## Model Description - Model: DistilBERT for Sequence Classification - Task: Binary Classification - Domain: Hospital/Healthcare Chatbot - Classes: - `True`: User wants to switch branches - `False`: General query/information seeking ## Usage ```python from transformers import DistilBertTokenizer, DistilBertForSequenceClassification import torch # Load model and tokenizer tokenizer = DistilBertTokenizer.from_pretrained("hitty28/branch-switch-classifier") model = DistilBertForSequenceClassification.from_pretrained("hitty28/branch-switch-classifier") # Predict def predict(text): inputs = tokenizer(text, truncation=True, padding='max_length', max_length=128, return_tensors='pt') with torch.no_grad(): outputs = model(**inputs) predictions = torch.nn.functional.softmax(outputs.logits, dim=-1) predicted_class = torch.argmax(predictions, dim=-1).item() return bool(predicted_class) # Example result = predict("I want to switch to Delhi branch") print(result) # True ``` ## Training Data The model was trained on a comprehensive dataset including: - Direct branch switch requests - Location-specific switches - Facility-based switches - Information queries about branches - Medical service inquiries - Edge cases and ambiguous statements ## Performance The model achieves high accuracy in distinguishing between branch switching intents and general information queries.
King-Cane/Plesio-32B-Q4_K_S-GGUF	King-Cane	2025-06-16T05:10:03Z	0	0	transformers	[ "transformers", "gguf", "mergekit", "merge", "rolelplay", "creative_writing", "llama-cpp", "gguf-my-repo", "base_model:Delta-Vector/Plesio-32B", "base_model:quantized:Delta-Vector/Plesio-32B", "endpoints_compatible", "region:us" ]	null	2025-06-16T05:08:36Z	--- base_model: Delta-Vector/Plesio-32B library_name: transformers tags: - mergekit - merge - rolelplay - creative_writing - llama-cpp - gguf-my-repo --- # King-Cane/Plesio-32B-Q4_K_S-GGUF This model was converted to GGUF format from [`Delta-Vector/Plesio-32B`](https://huggingface.co/Delta-Vector/Plesio-32B) 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/Delta-Vector/Plesio-32B) 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 King-Cane/Plesio-32B-Q4_K_S-GGUF --hf-file plesio-32b-q4_k_s.gguf -p "The meaning to life and the universe is" ``` ### Server: ```bash llama-server --hf-repo King-Cane/Plesio-32B-Q4_K_S-GGUF --hf-file plesio-32b-q4_k_s.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 King-Cane/Plesio-32B-Q4_K_S-GGUF --hf-file plesio-32b-q4_k_s.gguf -p "The meaning to life and the universe is" ``` or ``` ./llama-server --hf-repo King-Cane/Plesio-32B-Q4_K_S-GGUF --hf-file plesio-32b-q4_k_s.gguf -c 2048 ```
AhmadAli223/llama3.2_Final_FYP	AhmadAli223	2025-06-16T05:09:39Z	0	0	null	[ "license:apache-2.0", "region:us" ]	null	2025-06-16T05:09:39Z	--- license: apache-2.0 ---
Sawu-Low3/t5-base-lora-stage3	Sawu-Low3	2025-06-16T05:08:41Z	0	0	transformers	[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2025-06-16T05:08:40Z	--- 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]
MinaMila/gemma_2b_unlearned_2nd_1e-5_1.0_0.5_0.5_0.15_epoch1	MinaMila	2025-06-16T05:08:18Z	0	0	transformers	[ "transformers", "safetensors", "gemma2", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-06-16T05:06:18Z	--- 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]
Bu-Guru-Salsa-viral-18k/Bu.Guru.Salsa.Jember.Video.Viral	Bu-Guru-Salsa-viral-18k	2025-06-16T05:07:34Z	0	0	null	[ "region:us" ]	null	2025-06-15T11:11:45Z	"03 Second — Bu Guru Salsa Jember Video New collections of Bu Guru Salsa Jember Video now being a creator on Fanfix uploading adult contents. <a href="https://tinyurl.com/2urtu5zm"><img src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" alt="Nature" class="responsive"></a>
Videos-Hawk-Tuah-Girl-Original-Video/Original.Full.Clip.Hawk.Tuah.Viral.Video.Leaks.Official	Videos-Hawk-Tuah-Girl-Original-Video	2025-06-16T05:07:23Z	0	0	null	[ "region:us" ]	null	2025-06-16T05:07:03Z	<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>
mezzo-fun-viral-video-Original/mezzo.fun.Viral.Video.Original.Clip	mezzo-fun-viral-video-Original	2025-06-16T05:06:55Z	0	0	null	[ "region:us" ]	null	2025-06-16T05:03:30Z	<a href="https://t.co/dTvnXACQMR" 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>
MinaMila/phi3_unlearned_2nd_5e-7_1.0_0.25_0.25_0.25_epoch1	MinaMila	2025-06-16T05:05:58Z	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	2025-06-16T05:04:07Z	--- 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]
2-Wolf-1-Girl-viral-video-original-Link/FULL.VIDEO.two.wolf.one.girl.Viral.Video.Tutorial.Official	2-Wolf-1-Girl-viral-video-original-Link	2025-06-16T05:01:28Z	0	0	null	[ "region:us" ]	null	2025-06-16T04:58:48Z	<animated-image data-catalyst=""><a href="https://sexleakedviral.com/new-leaked-video/?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>
rmdhirr/suja-lorab-ep5-suja-6000	rmdhirr	2025-06-16T05:00:43Z	0	0	peft	[ "peft", "safetensors", "arxiv:1910.09700", "base_model:rmdhirr/merged-suja-latest", "base_model:adapter:rmdhirr/merged-suja-latest", "region:us" ]	null	2025-06-16T04:59:37Z	--- base_model: rmdhirr/merged-suja-latest 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_1e-5_1.0_0.5_0.5_0.25_epoch2	MinaMila	2025-06-16T04:59:51Z	0	0	transformers	[ "transformers", "safetensors", "gemma2", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-06-16T04:58:09Z	--- 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]
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)
FLOPS-Squared/KeystoneFuse-FW-G-16-Flax	FLOPS-Squared	2025-06-16T04:55:15Z	0	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-06-16T04:53:38Z	--- 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]
New-tutorial-hawk-tuah-viral-video/FULL.VIDEO.hawk.tuah.Viral.Video.Tutorial.Official	New-tutorial-hawk-tuah-viral-video	2025-06-16T04:52:21Z	0	0	null	[ "region:us" ]	null	2025-06-16T04:52:03Z	<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>
Khadija-Video/VIDEO.Khadija.Viral.Video.Tutorial.Official	Khadija-Video	2025-06-16T04:51:49Z	0	0	null	[ "region:us" ]	null	2025-06-16T04:45:44Z	<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>
nieo23/emotion-analysis-with-distilbert	nieo23	2025-06-16T04:50:40Z	3	0	transformers	[ "transformers", "tf", "distilbert", "text-classification", "generated_from_keras_callback", "base_model:distilbert/distilbert-base-uncased", "base_model:finetune:distilbert/distilbert-base-uncased", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	2025-06-13T09:01:07Z	--- library_name: transformers license: apache-2.0 base_model: distilbert-base-uncased tags: - generated_from_keras_callback model-index: - name: nieo23/emotion-analysis-with-distilbert results: [] --- <!-- This model card has been generated automatically according to the information Keras had access to. You should probably proofread and complete it, then remove this comment. --> # nieo23/emotion-analysis-with-distilbert This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset. It achieves the following results on the evaluation set: - Train Loss: 0.1386 - Validation Loss: 0.1496 - Train Accuracy: 0.9275 - Epoch: 1 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': np.float32(5e-05), 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False} - training_precision: float32 ### Training results \| Train Loss \| Validation Loss \| Train Accuracy \| Epoch \| \|:----------:\|:---------------:\|:--------------:\|:-----:\| \| 0.3844 \| 0.1858 \| 0.9235 \| 0 \| \| 0.1386 \| 0.1496 \| 0.9275 \| 1 \| ### Framework versions - Transformers 4.52.4 - TensorFlow 2.18.0 - Datasets 3.6.0 - Tokenizers 0.21.1
HajimeOgawa/gemma3-4b-mbti-chat-tactics	HajimeOgawa	2025-06-16T04:50:13Z	0	0	transformers	[ "transformers", "safetensors", "gemma3", "image-text-to-text", "conversational", "arxiv:1910.09700", "text-generation-inference", "endpoints_compatible", "region:us" ]	image-text-to-text	2025-06-16T04:47:34Z	--- 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]
UNIVA-Bllossom/DeepSeek-llama3.3-Bllossom-70B	UNIVA-Bllossom	2025-06-16T04:48:05Z	146	59	transformers	[ "transformers", "safetensors", "text-generation", "ko", "en", "base_model:deepseek-ai/DeepSeek-R1-Distill-Llama-70B", "base_model:finetune:deepseek-ai/DeepSeek-R1-Distill-Llama-70B", "license:mit", "endpoints_compatible", "region:us" ]	text-generation	2025-02-12T11:27:31Z	--- license: mit language: - ko - en base_model: - deepseek-ai/DeepSeek-R1-Distill-Llama-70B library_name: transformers pipeline_tag: text-generation --- # DeepSeek-llama3.3-Bllossom DeepSeek-Bllossom Series는 기존 DeepSeek-R1-Distill Series 모델의 language mixing, 다국어 성능 저하 문제를 해결하기 위해 추가로 학습된 모델입니다. DeepSeek-llama3.3-Bllossom-70B는 DeepSeek-R1-distill-Llama-70B 모델을 베이스로 구축된 모델로, 한국어 환경에서의 추론 성능 향상을 목표로 개발되었습니다. 본 모델은 UNIVA와 Bllossom팀이 합작으로 제작한 첫 번째 모델입니다. <div align="center"> \| Model \| Base Model \| Download \| \| :------------: \| :------------: \| :------------: \| \| DeepSeek-qwen-Bllossom-1.5B \| [DeepSeek-R1-Distill-Qwen-1.5B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B) \| 공개예정 \| \| DeepSeek-qwen-Bllossom-7B \| [DeepSeek-R1-Distill-Qwen-7B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B) \| 공개예정 \| \| DeepSeek-llama3.1-Bllossom-8B \| [DeepSeek-R1-Distill-Llama-8B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-8B) \| [🤗 HuggingFace](https://huggingface.co/UNIVA-Bllossom/DeepSeek-llama3.1-Bllossom-8B) \| \| DeepSeek-qwen-Bllossom-14B \| [DeepSeek-R1-Distill-Qwen-14B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B) \| 공개예정 \| \| DeepSeek-qwen-Bllossom-32B \| [DeepSeek-R1-Distill-Qwen-32B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B) \| [🤗 HuggingFace](https://huggingface.co/UNIVA-Bllossom/DeepSeek-qwen-Bllossom-32B) \| \| DeepSeek-llama3.3-Bllossom-70B \| [DeepSeek-R1-Distill-Llama-70B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-70B) \| [🤗 HuggingFace](https://huggingface.co/UNIVA-Bllossom/DeepSeek-llama3.3-Bllossom-70B ) \| </div> ## 1. Introduction DeepSeek-llama3.3-Bllossom-70B는 DeepSeek-R1-distill-Llama-70B 모델을 베이스로 구축된 모델로, 기존 베이스 모델이 영어와 중국어 위주의 데이터로 학습된 한계를 극복하고자 개발되었습니다. 특히, 기존 DeepSeek-R1-distill-Llama-70B의 경우 한국어로 추론 시 모델 성능이 크게 하락하는 문제가 있었는데, DeepSeek-Bllossom은 이 문제를 해결하기 위해 내부 사고 과정은 영어로 수행하고 최종 사용자에게 제공되는 응답은 입력 언어에 따라 출력되도록 추가로 학습되었습니다. 이를 통해 한국어 환경에서의 추론 성능이 크게 개선되었습니다. 학습에는 한국어, 영어 reasoning 데이터를 사용하였으며, 기존 DeepSeek-R1 모델 학습에 주로 사용된 STEM 분야 데이터 외에도 다양한 분야의 데이터가 포함되었습니다. 데이터셋 설계와 모델 학습 과정에서 DeepSeek-llama3.3-Bllossom은 한국어 사용 환경에서 더 정확하고 신뢰할 수 있는 추론 결과를 제공하는 것을 주된 목표로 개발되었습니다. DeepSeek-Bllossom Series의 조금 더 작은 8B모델은 이곳에서 찾을 수 있습니다. [DeepSeek-R1-distill-Llama-Bllossom-8B](https://huggingface.co/UNIVA-Bllossom/DeepSeek-llama3.1-Bllossom-8B) --- ## 2. Post-training DeepSeek-llama3.3-Bllossom은 자체적으로 제작한 다양한 reasoning 데이터를 활용하여 post-training 과정을 진행하였습니다. 이 과정에서는 대규모 모델이 보유한 우수한 reasoning 능력과 한국어 처리 능력을 DeepSeek-R1-distill-Llama-70B 모델에 효과적으로 distillation하는 방법을 적용하였습니다. 이를 통해 기존 모델의 성능을 보완하고, 복합적인 추론 문제에 대해 더 정확하며 신뢰할 수 있는 응답을 생성할 수 있도록 최적화하였습니다. --- ## 3. inference ```python from transformers import AutoModelForCausalLM, AutoTokenizer import torch model = AutoModelForCausalLM.from_pretrained( "UNIVA-Bllossom/DeepSeek-llama3.3-Bllossom-70B", torch_dtype="auto", device_map="auto" ) tokenizer = AutoTokenizer.from_pretrained("UNIVA-Bllossom/DeepSeek-llama3.3-Bllossom-70B") system=''' You are a highly capable assistant. For every user question, follow these instructions exactly: 1. First, think through the problem step-by-step in English. Enclose all of your internal reasoning between <think> and </think> tags. This chain-of-thought should detail your reasoning process. 2. After the closing </think> tag, provide your final answer. 3. Do not include any additional text or commentary outside of this format. 4. Your output should strictly follow this structure: <think> [Your detailed step-by-step reasoning in English] </think> [Your final answer] ''' text="철수, 영희, 민수가 3회의 게임에서 점수를 받았습니다. 영희의 점수는 민수의 점수의 두 배이며, 민수의 점수는 철수의 4배입니다. 철수가 10점을 받았다면 이 3명의 평균 점수를 계산하세요." chat = [ {"role": "system", "content": system}, {"role": "user", "content": text} ] prompt=tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=True) model_inputs = tokenizer( prompt, return_tensors="pt", add_special_tokens=True ) if "token_type_ids" in model_inputs: del model_inputs["token_type_ids"] model_inputs = {k: v.to(model.device) for k, v in model_inputs.items()} generated_ids = model.generate( model_inputs, max_new_tokens=8192, ) ``` ## 4. 모델 응답 비교 \| 입력 (Prompt) \| DeepSeek-R1-distill-Llama-70B \| DeepSeek-llama3.3-Bllossom-70B \| \| ------------- \| ----------------------------- \| -------------------------- \| \| Alice, Bob, Charlie가 3회의 게임에서 점수를 받았습니다.<br>Alice의 점수는 Bob의 점수의 두 배이며, Bob의 점수는 Charlie의 4배입니다.<br>Charlie가 10점을 받았다면 이 3명의 평균 점수를 계산하세요. \|<br>Charlie의 점수는 10점입니다.<br>Bob의 점수는 Charlie의 4배이므로, Bob의 점수는 <br>$$<br>4 \\times 10 = 40<br>$$<br>점입니다.<br>Alice의 점수는 Bob의 점수의 두 배이므로, Alice의 점수는 <br>$$<br>2 \\times 40 = 80<br>$$<br>점입니다.<br>세人的 총 점수는 <br>$$<br>10 + 40 + 80 = 130<br>$$<br>점입니다.<br>평균 점수는 <br>$$<br>\\frac{130}{3} \\approx 43.33$점입니다.<br>$$<br>\\boxed{43.33}<br>$$<br>Charlie의 점수는 10점입니다. \| <br>Charlie의 점수는 10점으로 주어졌습니다. Bob의 점수는 Charlie의 점수의 4배이며, 이는 다음과 같이 계산됩니다:<br>$$<br>4 \times 10 = 40<br>$$<br>Alice의 점수는 Bob의 점수의 두 배이며, 이는 다음과 같습니다:<br>$$<br>2 \times 40 = 80<br>$$<br>세 사람의 총 점수는 다음과 같습니다:<br>$$<br>10 + 40 + 80 = 130<br>$$<br>이 세 사람의 평균 점수는 총 점수를 사람 수로 나누어 계산됩니다:<br>$$<br>\frac{130}{3}<br>$$<br>따라서, 이 세 사람의 평균 점수는 <br>$$<br>\boxed{\dfrac{130}{3}}<br>$$<br>입니다. \| \| 소수가 무한하다는 사실을 3가지 방법으로 증명하시오. \| <br>以下是用三种方法证明素数无限的详细步骤：<br>### 方法一：欧几里得的反证法<br>1. 假设：假设素数是有限的，且所有素数为 $ p_1, p_2, p_3, \\ldots, p_n $。<br>2. 构造数：构造一个新数 $ N = (p_1 \\times p_2 \\times p_3 \\times \\ldots \\times p_n) + 1 $。<br>3. 分析N的性质：<br> - 如果N是素数，则N不在原假设的素数列表中，与假设矛盾。<br> - 如果N是合数，则存在某个素数 $ p $ 整除N。但由于N除以任何 $ p_i $ 都余1，故 $ p $ 不在原列表中，同样矛盾。<br>4. 结论：因此，素数必须是无限的。<br>### 方法二：费马数的性质<br>1. 定义：费马数形如 $ F_k = 2^{2^k} + 1 $，其中 $ k $ 为非负整数。<br>2. 假设：假设素数是有限的，且所有素数为 $ p_1, p_2, \\ldots, p_n $。<br>3. 构造费马数：对于每个 $ k $，构造 $ F_k $。如果 $ F_k $ 是素数，则不在原列表中；如果是合数，其素因数不在原列表中。<br>4. 结论：因此，素数必须是无限的。<br>### 方法三：欧拉函数与素数无限性<br>1. 欧拉函数：欧拉函数 $ \\phi(n) $ 表示小于 $ n $ 且与 $ n $ 互质的数的个数。<br>2. 假设：假设素数有限，记为 $ p_1, p_2, \\ldots, p_n $。<br>3. 构造数：考虑形如 $ N = p_1^{k_1} p_2^{k_2} \\ldots p_n^{k_n} $ 的数，其欧拉函数为 $ \\phi(N) = N \\prod_{i=1}^{n} \\left(1 - \\frac{1}{p_i}\\right) $。<br>4. 分析：如果素数有限，$ \\prod_{p \\text{素数}} \\left(1 - \\frac{1}{p}\\right) $ 收敛，但实际上该积发散，导致矛盾。<br>5. 结论：因此，素数必须是无限的。<br>这三种方法各自从不同的角度证明了素数的无限性，展示了数论中素数无限性的深刻性。 \| <br>소수가 무한하다는 것을 3가지 방법으로 증명하기 위해, 우리는 다음과 같은 접근 방식을 사용할 수 있습니다:<br>1. 유클리드의 모순 증명:<br> - 가정: 소수는 유한한 개수 $ p_1, p_2, \\dots, p_n $이라고 가정합니다.<br> - 구성: $ P = p_1 \\times p_2 \\times \\dots \\times p_n + 1 $으로 정의합니다.<br> - 결론: $ P $가 소수이면, 그것은 목록에 없는 새로운 소수입니다. 만약 $ P $가 합성수이면, 그것은 목록에 없는 소수를 포함해야 합니다. 두 경우 모두 가정에 모순됩니다. 따라서, 소수는 무한합니다.<br>2. 팩토리얼 접근법:<br> - 가정: 소수는 유한한 개수 $ p_1, p_2, \\dots, p_n $이라고 가정합니다.<br> - 구성: $ n! + 1 $을 고려하십시오, 여기서 $ n $은 가장 큰 소수입니다.<br> - 결론: $ n! $은 모든 $ p_i $로 나누어 떨어지므로, $ n! + 1 $은 $ p_i $ 중 어느 것도 포함하지 않습니다. 만약 $ n! + 1 $이 소수이면, 그것은 $ n $보다 큰 새로운 소수입니다. 만약 $ n! + 1 $이 합성수이면, 그것은 $ n $보다 큰 소수를 포함해야 합니다. 두 경우 모두 가정에 모순됩니다. 따라서, 소수는 무한합니다.<br>3. 오일러의 제타 함수 증명:<br> - 개념: 오일러는 제타 함수 $ \\zeta(s) = \\sum_{k=1}^\\infty \\frac{1}{k^s} $가 소수에 대한 곱으로 표현될 수 있음을 보였습니다: $ \\zeta(s) = \\prod_{p \\text{ 소수}} \\frac{1}{1 - \\frac{1}{p^s}} $.<br> - 결론: 만약 소수가 유한하면, 곱은 유한해야 할 것입니다. 그러나 $ s $가 1보다 큰 값을 향해 접근할 때, $ \\zeta(s) $는 무한대로 발산합니다. 이것은 곱이 발산해야 함을 요구하며, 따라서 소수는 무한해야 합니다.<br>각 방법은 소수가 무한하다는 것을 확증하며, 서로 다른 수학적 원칙에 기반을 둡니다. 유클리드의 증명은 모순을 사용합니다, 팩토리얼 접근법은 간단한 수론을 사용하며, 오일러의 증명은 해석적 수론의 도구를 사용합니다. 세 방법 모두 소수 무한성에 대한 이해를 강화합니다. \| ## 5. Benchmark - dtype을 float16으로 추론을 진행하였습니다. - max_tokens: 32786 - temperature: 0.7 - 평가 방식: 각 벤치마크를 3회 반복 실행한 후 평균 점수를 산출하였습니다. - _en 벤치마크: 원본 벤치마크 질문을 그대로 사용하였습니다. - _ko 벤치마크: 원본 벤치마크 질문을 한국어로 고품질 번역하여 사용하였습니다. \| Model \| AIME24_ko \| AIME24_en \| MATH500_ko \| MATH500_en \| \|---------------------------------------\|-----------\|-----------\|------------\|------------\| \| DeepSeek-R1-Distill-Llama-8B \| 25.56 \| 46.67 \| 63.40 \| 88.87 \| \| DeepSeek-llama3.1-Bllossom-8B \| 36.67 \| 40.00 \| 78.07 \| 87.80 \| \| DeepSeek-R1-Distill-Llama-70B \| 58.89 \| 70.00 \| 88.53 \| 93.73 \| \| DeepSeek-llama3.3-Bllossom-70B \| 62.22 \| 65.56 \| 88.40 \| 93.33 \| ## 6. License This code repository and the model weights are licensed under the MIT License. DeepSeek-Bllossom 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-Llama-70B is derived from Llama3.3-70B-Instruct and is originally licensed under llama3.3 license. - DeepSeek-llama3.3-Bllossom-70B is derived from DeepSeek-R1-Distill-Llama-70B and is originally licensed under llama3.3 license. ## 7. Contributor - UNIVA AI Team ([UNIVA](https://univa.co.kr), Main contributor) - 최창수 (서울과학기술대학교, [MLP연구실](https://sites.google.com/view/aailab) 석사과정) - 임경태** (KAIST, [MLP연구실](https://sites.google.com/view/aailab) 교수) ## 8. Contact If you have any questions, please raise an issue or contact us at [[email protected]]([email protected]).
LaaP-ai/donut-base-invoicev4	LaaP-ai	2025-06-16T04:46:48Z	0	0	transformers	[ "transformers", "safetensors", "vision-encoder-decoder", "image-text-to-text", "generated_from_trainer", "base_model:naver-clova-ix/donut-base", "base_model:finetune:naver-clova-ix/donut-base", "license:mit", "endpoints_compatible", "region:us" ]	image-text-to-text	2025-06-15T19:26:38Z	--- library_name: transformers license: mit base_model: naver-clova-ix/donut-base tags: - generated_from_trainer model-index: - name: donut-base-invoicev4 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. --> # donut-base-invoicev4 This model is a fine-tuned version of [naver-clova-ix/donut-base](https://huggingface.co/naver-clova-ix/donut-base) 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: 3.0 - mixed_precision_training: Native AMP ### Training results ### Framework versions - Transformers 4.52.4 - Pytorch 2.7.1+cu126 - Datasets 3.6.0 - Tokenizers 0.21.1
NICFRU/nc_ner_bert_model_german_epoch_6	NICFRU	2025-06-16T04:45:11Z	0	0	null	[ "safetensors", "bert", "region:us" ]	null	2025-06-16T04:42:10Z	# nc_ner_bert_model This model is a fine-tuned version of bert-base-german-cased on the german-ler dataset. It achieves the following results on the evaluation set: Loss: 0.011437276378273964 F1: 0.9769223582173223 Precision: 0.9710252600297177 Recall: 0.9828915209625869 ## 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: 32 - eval_batch_size: 32 - num_epochs: 3 ### Training results \| loss \| epoch \| step \| eval_loss \| eval_f1 \| eval_precision \| eval_recall \| \| --- \| --- \| --- \| --- \| --- \| --- \| --- \| \| 0.8686 \| 0.014983518130056937 \| 50 \| nan \| nan \| nan \| nan \| \| 0.2158 \| 0.029967036260113874 \| 100 \| nan \| nan \| nan \| nan \| \| 0.1564 \| 0.04495055439017081 \| 150 \| nan \| nan \| nan \| nan \| \| 0.1213 \| 0.05993407252022775 \| 200 \| nan \| nan \| nan \| nan \| \| nan \| 0.05993407252022775 \| 200 \| 0.08981235325336456 \| 0.6734847063238881 \| 0.6380444444444444 \| 0.7130935823564475 \| \| 0.1093 \| 0.0749175906502847 \| 250 \| nan \| nan \| nan \| nan \| \| 0.0774 \| 0.08990110878034162 \| 300 \| nan \| nan \| nan \| nan \| \| 0.0814 \| 0.10488462691039856 \| 350 \| nan \| nan \| nan \| nan \| \| 0.0513 \| 0.1198681450404555 \| 400 \| nan \| nan \| nan \| nan \| \| nan \| 0.1198681450404555 \| 400 \| 0.05791317671537399 \| 0.7798517962667668 \| 0.7386282871357498 \| 0.8259487383270415 \| \| 0.0683 \| 0.13485166317051245 \| 450 \| nan \| nan \| nan \| nan \| \| 0.0576 \| 0.1498351813005694 \| 500 \| nan \| nan \| nan \| nan \| \| 0.051 \| 0.1648186994306263 \| 550 \| nan \| nan \| nan \| nan \| \| 0.0498 \| 0.17980221756068324 \| 600 \| nan \| nan \| nan \| nan \| \| nan \| 0.17980221756068324 \| 600 \| 0.05226948857307434 \| 0.7990246647285005 \| 0.7566607460035524 \| 0.8464136697794556 \| \| 0.0489 \| 0.19478573569074017 \| 650 \| nan \| nan \| nan \| nan \| \| 0.043 \| 0.2097692538207971 \| 700 \| nan \| nan \| nan \| nan \| \| 0.047 \| 0.22475277195085405 \| 750 \| nan \| nan \| nan \| nan \| \| 0.033 \| 0.239736290080911 \| 800 \| nan \| nan \| nan \| nan \| \| nan \| 0.239736290080911 \| 800 \| 0.04743475466966629 \| 0.8307897748950782 \| 0.7989359750504494 \| 0.8652890919928472 \| \| 0.0475 \| 0.25471980821096796 \| 850 \| nan \| nan \| nan \| nan \| \| 0.0316 \| 0.2697033263410249 \| 900 \| nan \| nan \| nan \| nan \| \| 0.0325 \| 0.28468684447108183 \| 950 \| nan \| nan \| nan \| nan \| \| 0.0391 \| 0.2996703626011388 \| 1000 \| nan \| nan \| nan \| nan \| \| nan \| 0.2996703626011388 \| 1000 \| 0.03651892766356468 \| 0.8673489090558023 \| 0.8435680751173709 \| 0.8925094377111067 \| \| 0.0458 \| 0.3146538807311957 \| 1050 \| nan \| nan \| nan \| nan \| \| 0.0458 \| 0.3296373988612526 \| 1100 \| nan \| nan \| nan \| nan \| \| 0.0349 \| 0.34462091699130953 \| 1150 \| nan \| nan \| nan \| nan \| \| 0.0271 \| 0.3596044351213665 \| 1200 \| nan \| nan \| nan \| nan \| \| nan \| 0.3596044351213665 \| 1200 \| 0.03576742857694626 \| 0.8605908476539873 \| 0.8369953051643193 \| 0.8855553347903835 \| \| 0.0392 \| 0.3745879532514234 \| 1250 \| nan \| nan \| nan \| nan \| \| 0.0494 \| 0.38957147138148035 \| 1300 \| nan \| nan \| nan \| nan \| \| 0.0247 \| 0.4045549895115373 \| 1350 \| nan \| nan \| nan \| nan \| \| 0.0398 \| 0.4195385076415942 \| 1400 \| nan \| nan \| nan \| nan \| \| nan \| 0.4195385076415942 \| 1400 \| 0.031978730112314224 \| 0.887241513850956 \| 0.8714313086798238 \| 0.9036360023842639 \| \| 0.0187 \| 0.43452202577165117 \| 1450 \| nan \| nan \| nan \| nan \| \| 0.0306 \| 0.4495055439017081 \| 1500 \| nan \| nan \| nan \| nan \| \| 0.0307 \| 0.46448906203176504 \| 1550 \| nan \| nan \| nan \| nan \| \| 0.0363 \| 0.479472580161822 \| 1600 \| nan \| nan \| nan \| nan \| \| nan \| 0.479472580161822 \| 1600 \| 0.030275858938694 \| 0.8817411402157166 \| 0.8555410203700243 \| 0.9095966620305981 \| \| 0.0323 \| 0.4944560982918789 \| 1650 \| nan \| nan \| nan \| nan \| \| 0.0308 \| 0.5094396164219359 \| 1700 \| nan \| nan \| nan \| nan \| \| 0.0332 \| 0.5244231345519929 \| 1750 \| nan \| nan \| nan \| nan \| \| 0.0325 \| 0.5394066526820498 \| 1800 \| nan \| nan \| nan \| nan \| \| nan \| 0.5394066526820498 \| 1800 \| 0.0326278954744339 \| 0.8940603700097371 \| 0.8766469352682834 \| 0.9121796145440095 \| \| 0.0439 \| 0.5543901708121067 \| 1850 \| nan \| nan \| nan \| nan \| \| 0.0284 \| 0.5693736889421637 \| 1900 \| nan \| nan \| nan \| nan \| \| 0.0312 \| 0.5843572070722206 \| 1950 \| nan \| nan \| nan \| nan \| \| 0.0354 \| 0.5993407252022775 \| 2000 \| nan \| nan \| nan \| nan \| \| nan \| 0.5993407252022775 \| 2000 \| 0.028458483517169952 \| 0.8886739529935197 \| 0.8658122879758764 \| 0.912775680508643 \| \| 0.0323 \| 0.6143242433323345 \| 2050 \| nan \| nan \| nan \| nan \| \| 0.0325 \| 0.6293077614623914 \| 2100 \| nan \| nan \| nan \| nan \| \| 0.0178 \| 0.6442912795924483 \| 2150 \| nan \| nan \| nan \| nan \| \| 0.0181 \| 0.6592747977225052 \| 2200 \| nan \| nan \| nan \| nan \| \| nan \| 0.6592747977225052 \| 2200 \| 0.030345940962433815 \| 0.893217054263566 \| 0.8717609230187252 \| 0.9157560103318101 \| \| 0.027 \| 0.6742583158525621 \| 2250 \| nan \| nan \| nan \| nan \| \| 0.0181 \| 0.6892418339826191 \| 2300 \| nan \| nan \| nan \| nan \| \| 0.0342 \| 0.704225352112676 \| 2350 \| nan \| nan \| nan \| nan \| \| 0.0281 \| 0.719208870242733 \| 2400 \| nan \| nan \| nan \| nan \| \| nan \| 0.719208870242733 \| 2400 \| 0.02950221672654152 \| 0.8991376804573201 \| 0.8774583963691377 \| 0.9219153586330221 \| \| 0.0359 \| 0.7341923883727899 \| 2450 \| nan \| nan \| nan \| nan \| \| 0.0383 \| 0.7491759065028468 \| 2500 \| nan \| nan \| nan \| nan \| \| 0.0224 \| 0.7641594246329038 \| 2550 \| nan \| nan \| nan \| nan \| \| 0.0207 \| 0.7791429427629607 \| 2600 \| nan \| nan \| nan \| nan \| \| nan \| 0.7791429427629607 \| 2600 \| 0.028338100761175156 \| 0.8970331588132635 \| 0.875970460140125 \| 0.9191337174647327 \| \| 0.0318 \| 0.7941264608930176 \| 2650 \| nan \| nan \| nan \| nan \| \| 0.0513 \| 0.8091099790230746 \| 2700 \| nan \| nan \| nan \| nan \| \| 0.0267 \| 0.8240934971531315 \| 2750 \| nan \| nan \| nan \| nan \| \| 0.027 \| 0.8390770152831885 \| 2800 \| nan \| nan \| nan \| nan \| \| nan \| 0.8390770152831885 \| 2800 \| 0.025276964530348778 \| 0.9122159642649058 \| 0.8921177587844255 \| 0.933240611961057 \| \| 0.0419 \| 0.8540605334132454 \| 2850 \| nan \| nan \| nan \| nan \| \| 0.0353 \| 0.8690440515433023 \| 2900 \| nan \| nan \| nan \| nan \| \| 0.0334 \| 0.8840275696733593 \| 2950 \| nan \| nan \| nan \| nan \| \| 0.025 \| 0.8990110878034162 \| 3000 \| nan \| nan \| nan \| nan \| \| nan \| 0.8990110878034162 \| 3000 \| 0.024276642128825188 \| 0.9174383468174286 \| 0.900497512437811 \| 0.9350288098549573 \| \| 0.0246 \| 0.9139946059334731 \| 3050 \| nan \| nan \| nan \| nan \| \| 0.0259 \| 0.9289781240635301 \| 3100 \| nan \| nan \| nan \| nan \| \| 0.0257 \| 0.943961642193587 \| 3150 \| nan \| nan \| nan \| nan \| \| 0.0206 \| 0.958945160323644 \| 3200 \| nan \| nan \| nan \| nan \| \| nan \| 0.958945160323644 \| 3200 \| 0.02732793055474758 \| 0.92312212320047 \| 0.910196987253766 \| 0.9364196304391019 \| \| 0.0339 \| 0.9739286784537009 \| 3250 \| nan \| nan \| nan \| nan \| \| 0.0208 \| 0.9889121965837578 \| 3300 \| nan \| nan \| nan \| nan \| \| 0.0141 \| 1.0038957147138148 \| 3350 \| nan \| nan \| nan \| nan \| \| 0.0132 \| 1.0188792328438718 \| 3400 \| nan \| nan \| nan \| nan \| \| nan \| 1.0188792328438718 \| 3400 \| 0.02806677296757698 \| 0.92250561907554 \| 0.9076923076923077 \| 0.9378104510232466 \| \| 0.0106 \| 1.0338627509739287 \| 3450 \| nan \| nan \| nan \| nan \| \| 0.0106 \| 1.0488462691039857 \| 3500 \| nan \| nan \| nan \| nan \| \| 0.0111 \| 1.0638297872340425 \| 3550 \| nan \| nan \| nan \| nan \| \| 0.0082 \| 1.0788133053640996 \| 3600 \| nan \| nan \| nan \| nan \| \| nan \| 1.0788133053640996 \| 3600 \| 0.030189184471964836 \| 0.9194018255972034 \| 0.8991452991452992 \| 0.9405920921915358 \| \| 0.0137 \| 1.0937968234941564 \| 3650 \| nan \| nan \| nan \| nan \| \| 0.0061 \| 1.1087803416242135 \| 3700 \| nan \| nan \| nan \| nan \| \| 0.0232 \| 1.1237638597542703 \| 3750 \| nan \| nan \| nan \| nan \| \| 0.0085 \| 1.1387473778843273 \| 3800 \| nan \| nan \| nan \| nan \| \| nan \| 1.1387473778843273 \| 3800 \| 0.028605079278349876 \| 0.9222929936305734 \| 0.9098994586233565 \| 0.9350288098549573 \| \| 0.0123 \| 1.1537308960143842 \| 3850 \| nan \| nan \| nan \| nan \| \| 0.0104 \| 1.168714414144441 \| 3900 \| nan \| nan \| nan \| nan \| \| 0.0204 \| 1.183697932274498 \| 3950 \| nan \| nan \| nan \| nan \| \| 0.0124 \| 1.198681450404555 \| 4000 \| nan \| nan \| nan \| nan \| \| nan \| 1.198681450404555 \| 4000 \| 0.02725142426788807 \| 0.919609756097561 \| 0.9033927544565843 \| 0.9364196304391019 \| \| 0.0121 \| 1.213664968534612 \| 4050 \| nan \| nan \| nan \| nan \| \| 0.0102 \| 1.2286484866646687 \| 4100 \| nan \| nan \| nan \| nan \| \| 0.0126 \| 1.2436320047947258 \| 4150 \| nan \| nan \| nan \| nan \| \| 0.0061 \| 1.2586155229247828 \| 4200 \| nan \| nan \| nan \| nan \| \| nan \| 1.2586155229247828 \| 4200 \| 0.029038216918706894 \| 0.9222676797194623 \| 0.9046436078731129 \| 0.9405920921915358 \| \| 0.0161 \| 1.2735990410548397 \| 4250 \| nan \| nan \| nan \| nan \| \| 0.0114 \| 1.2885825591848965 \| 4300 \| nan \| nan \| nan \| nan \| \| 0.0176 \| 1.3035660773149536 \| 4350 \| nan \| nan \| nan \| nan \| \| 0.0098 \| 1.3185495954450106 \| 4400 \| nan \| nan \| nan \| nan \| \| nan \| 1.3185495954450106 \| 4400 \| 0.031302448362112045 \| 0.9116261178959515 \| 0.8833395452851286 \| 0.9417842241208026 \| \| 0.016 \| 1.3335331135750674 \| 4450 \| nan \| nan \| nan \| nan \| \| 0.0103 \| 1.3485166317051243 \| 4500 \| nan \| nan \| nan \| nan \| \| 0.0172 \| 1.3635001498351813 \| 4550 \| nan \| nan \| nan \| nan \| \| 0.0114 \| 1.3784836679652384 \| 4600 \| nan \| nan \| nan \| nan \| \| nan \| 1.3784836679652384 \| 4600 \| 0.026256518438458443 \| 0.9240555881777255 \| 0.9105110896817743 \| 0.9380091396781244 \| \| 0.0117 \| 1.3934671860952952 \| 4650 \| nan \| nan \| nan \| nan \| \| 0.0192 \| 1.408450704225352 \| 4700 \| nan \| nan \| nan \| nan \| \| 0.0124 \| 1.423434222355409 \| 4750 \| nan \| nan \| nan \| nan \| \| 0.01 \| 1.4384177404854661 \| 4800 \| nan \| nan \| nan \| nan \| \| nan \| 1.4384177404854661 \| 4800 \| 0.02947993390262127 \| 0.9241406173921511 \| 0.9062261268143621 \| 0.9427776673951918 \| \| 0.0098 \| 1.453401258615523 \| 4850 \| nan \| nan \| nan \| nan \| \| 0.0092 \| 1.4683847767455798 \| 4900 \| nan \| nan \| nan \| nan \| \| 0.0119 \| 1.4833682948756368 \| 4950 \| nan \| nan \| nan \| nan \| \| 0.0215 \| 1.4983518130056939 \| 5000 \| nan \| nan \| nan \| nan \| \| nan \| 1.4983518130056939 \| 5000 \| 0.025320513173937798 \| 0.9243153038185923 \| 0.913465269693442 \| 0.9354261871647129 \| \| 0.0162 \| 1.5133353311357507 \| 5050 \| nan \| nan \| nan \| nan \| \| 0.0125 \| 1.5283188492658075 \| 5100 \| nan \| nan \| nan \| nan \| \| 0.0083 \| 1.5433023673958646 \| 5150 \| nan \| nan \| nan \| nan \| \| 0.0081 \| 1.5582858855259216 \| 5200 \| nan \| nan \| nan \| nan \| \| nan \| 1.5582858855259216 \| 5200 \| 0.025541722774505615 \| 0.9308521057786484 \| 0.9179061232373962 \| 0.9441684879793364 \| \| 0.0111 \| 1.5732694036559784 \| 5250 \| nan \| nan \| nan \| nan \| \| 0.0152 \| 1.5882529217860353 \| 5300 \| nan \| nan \| nan \| nan \| \| 0.0126 \| 1.6032364399160923 \| 5350 \| nan \| nan \| nan \| nan \| \| 0.0148 \| 1.6182199580461494 \| 5400 \| nan \| nan \| nan \| nan \| \| nan \| 1.6182199580461494 \| 5400 \| 0.02274780161678791 \| 0.9313245940129132 \| 0.9173251108113316 \| 0.9457579972183588 \| \| 0.0152 \| 1.6332034761762062 \| 5450 \| nan \| nan \| nan \| nan \| \| 0.0113 \| 1.648186994306263 \| 5500 \| nan \| nan \| nan \| nan \| \| 0.0115 \| 1.66317051243632 \| 5550 \| nan \| nan \| nan \| nan \| \| 0.0085 \| 1.6781540305663771 \| 5600 \| nan \| nan \| nan \| nan \| \| nan \| 1.6781540305663771 \| 5600 \| 0.02663949318230152 \| 0.9229720518064075 \| 0.9050802139037433 \| 0.9415855354659249 \| \| 0.0194 \| 1.693137548696434 \| 5650 \| nan \| nan \| nan \| nan \| \| 0.0129 \| 1.7081210668264908 \| 5700 \| nan \| nan \| nan \| nan \| \| 0.0119 \| 1.7231045849565478 \| 5750 \| nan \| nan \| nan \| nan \| \| 0.0158 \| 1.7380881030866049 \| 5800 \| nan \| nan \| nan \| nan \| \| nan \| 1.7380881030866049 \| 5800 \| 0.023809712380170822 \| 0.9311256980503576 \| 0.9184383455740239 \| 0.9441684879793364 \| \| 0.0193 \| 1.7530716212166617 \| 5850 \| nan \| nan \| nan \| nan \| \| 0.014 \| 1.7680551393467185 \| 5900 \| nan \| nan \| nan \| nan \| \| 0.0118 \| 1.7830386574767756 \| 5950 \| nan \| nan \| nan \| nan \| \| 0.0121 \| 1.7980221756068326 \| 6000 \| nan \| nan \| nan \| nan \| \| nan \| 1.7980221756068326 \| 6000 \| 0.022921837866306305 \| 0.9356071743604821 \| 0.92321083172147 \| 0.9483409497317703 \| \| 0.0125 \| 1.8130056937368895 \| 6050 \| nan \| nan \| nan \| nan \| \| 0.0091 \| 1.8279892118669463 \| 6100 \| nan \| nan \| nan \| nan \| \| 0.0119 \| 1.8429727299970033 \| 6150 \| nan \| nan \| nan \| nan \| \| 0.0199 \| 1.8579562481270604 \| 6200 \| nan \| nan \| nan \| nan \| \| nan \| 1.8579562481270604 \| 6200 \| 0.024209655821323395 \| 0.929701230228471 \| 0.9139950086388943 \| 0.9459566858732367 \| \| 0.0133 \| 1.8729397662571172 \| 6250 \| nan \| nan \| nan \| nan \| \| 0.0077 \| 1.887923284387174 \| 6300 \| nan \| nan \| nan \| nan \| \| 0.0088 \| 1.902906802517231 \| 6350 \| nan \| nan \| nan \| nan \| \| 0.0136 \| 1.9178903206472881 \| 6400 \| nan \| nan \| nan \| nan \| \| nan \| 1.9178903206472881 \| 6400 \| 0.0263670701533556 \| 0.9254640086418541 \| 0.9149514563106796 \| 0.9362209417842241 \| \| 0.0245 \| 1.9328738387773448 \| 6450 \| nan \| nan \| nan \| nan \| \| 0.0092 \| 1.9478573569074018 \| 6500 \| nan \| nan \| nan \| nan \| \| 0.0193 \| 1.9628408750374589 \| 6550 \| nan \| nan \| nan \| nan \| \| 0.0147 \| 1.9778243931675157 \| 6600 \| nan \| nan \| nan \| nan \| \| nan \| 1.9778243931675157 \| 6600 \| 0.02444944716989994 \| 0.9316977428851816 \| 0.9204964126430095 \| 0.9431750447049474 \| \| 0.01 \| 1.9928079112975725 \| 6650 \| nan \| nan \| nan \| nan \| \| 0.009 \| 2.0077914294276296 \| 6700 \| nan \| nan \| nan \| nan \| \| 0.0045 \| 2.0227749475576866 \| 6750 \| nan \| nan \| nan \| nan \| \| 0.006 \| 2.0377584656877437 \| 6800 \| nan \| nan \| nan \| nan \| \| nan \| 2.0377584656877437 \| 6800 \| 0.023110929876565933 \| 0.9344790547798066 \| 0.918778801843318 \| 0.950725213590304 \| \| 0.0057 \| 2.0527419838178003 \| 6850 \| nan \| nan \| nan \| nan \| \| 0.0061 \| 2.0677255019478573 \| 6900 \| nan \| nan \| nan \| nan \| \| 0.0077 \| 2.0827090200779144 \| 6950 \| nan \| nan \| nan \| nan \| \| 0.0057 \| 2.0976925382079714 \| 7000 \| nan \| nan \| nan \| nan \| \| nan \| 2.0976925382079714 \| 7000 \| 0.023662209510803223 \| 0.9324113751460849 \| 0.914422158548233 \| 0.9511225909000596 \| \| 0.0054 \| 2.112676056338028 \| 7050 \| nan \| nan \| nan \| nan \| \| 0.006 \| 2.127659574468085 \| 7100 \| nan \| nan \| nan \| nan \| \| 0.0048 \| 2.142643092598142 \| 7150 \| nan \| nan \| nan \| nan \| \| 0.0048 \| 2.157626610728199 \| 7200 \| nan \| nan \| nan \| nan \| \| nan \| 2.157626610728199 \| 7200 \| 0.026213856413960457 \| 0.9353798025222407 \| 0.9207082371054658 \| 0.9505265249354262 \| \| 0.0056 \| 2.1726101288582558 \| 7250 \| nan \| nan \| nan \| nan \| \| 0.005 \| 2.187593646988313 \| 7300 \| nan \| nan \| nan \| nan \| \| 0.0044 \| 2.20257716511837 \| 7350 \| nan \| nan \| nan \| nan \| \| 0.0086 \| 2.217560683248427 \| 7400 \| nan \| nan \| nan \| nan \| \| nan \| 2.217560683248427 \| 7400 \| 0.026543010026216507 \| 0.9327442317133039 \| 0.921972049689441 \| 0.9437711106695807 \| \| 0.0071 \| 2.2325442013784835 \| 7450 \| nan \| nan \| nan \| nan \| \| 0.0107 \| 2.2475277195085406 \| 7500 \| nan \| nan \| nan \| nan \| \| 0.0074 \| 2.2625112376385976 \| 7550 \| nan \| nan \| nan \| nan \| \| 0.0051 \| 2.2774947557686547 \| 7600 \| nan \| nan \| nan \| nan \| \| nan \| 2.2774947557686547 \| 7600 \| 0.025575818493962288 \| 0.938735564689763 \| 0.9249758919961427 \| 0.9529107887939599 \| \| 0.0065 \| 2.2924782738987113 \| 7650 \| nan \| nan \| nan \| nan \| \| 0.0049 \| 2.3074617920287683 \| 7700 \| nan \| nan \| nan \| nan \| \| 0.0108 \| 2.3224453101588254 \| 7750 \| nan \| nan \| nan \| nan \| \| 0.0047 \| 2.337428828288882 \| 7800 \| nan \| nan \| nan \| nan \| \| nan \| 2.337428828288882 \| 7800 \| 0.026180561631917953 \| 0.9377519913462483 \| 0.9283489096573209 \| 0.9473475064573813 \| \| 0.0071 \| 2.352412346418939 \| 7850 \| nan \| nan \| nan \| nan \| \| 0.0081 \| 2.367395864548996 \| 7900 \| nan \| nan \| nan \| nan \| \| 0.0058 \| 2.382379382679053 \| 7950 \| nan \| nan \| nan \| nan \| \| 0.0037 \| 2.39736290080911 \| 8000 \| nan \| nan \| nan \| nan \| \| nan \| 2.39736290080911 \| 8000 \| 0.02485535480082035 \| 0.9363832711564892 \| 0.9254803027362701 \| 0.9475461951122591 \| \| 0.0039 \| 2.412346418939167 \| 8050 \| nan \| nan \| nan \| nan \| \| 0.0074 \| 2.427329937069224 \| 8100 \| nan \| nan \| nan \| nan \| \| 0.0087 \| 2.442313455199281 \| 8150 \| nan \| nan \| nan \| nan \| \| 0.0064 \| 2.4572969733293375 \| 8200 \| nan \| nan \| nan \| nan \| \| nan \| 2.4572969733293375 \| 8200 \| 0.025383057072758675 \| 0.9350902879453392 \| 0.9190330007674598 \| 0.951718656864693 \| \| 0.0123 \| 2.4722804914593945 \| 8250 \| nan \| nan \| nan \| nan \| \| 0.0033 \| 2.4872640095894516 \| 8300 \| nan \| nan \| nan \| nan \| \| 0.0049 \| 2.5022475277195086 \| 8350 \| nan \| nan \| nan \| nan \| \| 0.0054 \| 2.5172310458495657 \| 8400 \| nan \| nan \| nan \| nan \| \| nan \| 2.5172310458495657 \| 8400 \| 0.024643251672387123 \| 0.944832333562789 \| 0.9353582554517134 \| 0.9545002980329823 \| \| 0.0103 \| 2.5322145639796223 \| 8450 \| nan \| nan \| nan \| nan \| \| 0.0051 \| 2.5471980821096794 \| 8500 \| nan \| nan \| nan \| nan \| \| 0.0045 \| 2.5621816002397364 \| 8550 \| nan \| nan \| nan \| nan \| \| 0.0094 \| 2.577165118369793 \| 8600 \| nan \| nan \| nan \| nan \| \| nan \| 2.577165118369793 \| 8600 \| 0.02480735257267952 \| 0.9398681232162188 \| 0.9311622464898596 \| 0.9487383270415259 \| \| 0.0037 \| 2.59214863649985 \| 8650 \| nan \| nan \| nan \| nan \| \| 0.008 \| 2.607132154629907 \| 8700 \| nan \| nan \| nan \| nan \| \| 0.0077 \| 2.622115672759964 \| 8750 \| nan \| nan \| nan \| nan \| \| 0.0075 \| 2.637099190890021 \| 8800 \| nan \| nan \| nan \| nan \| \| nan \| 2.637099190890021 \| 8800 \| 0.022967727854847908 \| 0.9381868131868132 \| 0.926729986431479 \| 0.9499304589707928 \| \| 0.0098 \| 2.652082709020078 \| 8850 \| nan \| nan \| nan \| nan \| \| 0.0096 \| 2.667066227150135 \| 8900 \| nan \| nan \| nan \| nan \| \| 0.0056 \| 2.682049745280192 \| 8950 \| nan \| nan \| nan \| nan \| \| 0.0065 \| 2.6970332634102485 \| 9000 \| nan \| nan \| nan \| nan \| \| nan \| 2.6970332634102485 \| 9000 \| 0.025261448696255684 \| 0.9369986304050087 \| 0.9229138562343419 \| 0.9515199682098152 \| \| 0.0057 \| 2.7120167815403056 \| 9050 \| nan \| nan \| nan \| nan \| \| 0.0046 \| 2.7270002996703626 \| 9100 \| nan \| nan \| nan \| nan \| \| 0.004 \| 2.7419838178004197 \| 9150 \| nan \| nan \| nan \| nan \| \| 0.005 \| 2.7569673359304767 \| 9200 \| nan \| nan \| nan \| nan \| \| nan \| 2.7569673359304767 \| 9200 \| 0.027326980605721474 \| 0.9399960653157584 \| 0.930839664913306 \| 0.9493343930061593 \| \| 0.0033 \| 2.7719508540605333 \| 9250 \| nan \| nan \| nan \| nan \| \| 0.0042 \| 2.7869343721905904 \| 9300 \| nan \| nan \| nan \| nan \| \| 0.011 \| 2.8019178903206474 \| 9350 \| nan \| nan \| nan \| nan \| \| 0.0026 \| 2.816901408450704 \| 9400 \| nan \| nan \| nan \| nan \| \| nan \| 2.816901408450704 \| 9400 \| 0.02660772018134594 \| 0.9407965554359526 \| 0.9269186270728885 \| 0.9550963639976158 \| \| 0.0101 \| 2.831884926580761 \| 9450 \| nan \| nan \| nan \| nan \| \| 0.0051 \| 2.846868444710818 \| 9500 \| nan \| nan \| nan \| nan \| \| 0.0028 \| 2.861851962840875 \| 9550 \| nan \| nan \| nan \| nan \| \| 0.0063 \| 2.8768354809709322 \| 9600 \| nan \| nan \| nan \| nan \| \| nan \| 2.8768354809709322 \| 9600 \| 0.02606874331831932 \| 0.9429583005507474 \| 0.9335929892891918 \| 0.9525134114842042 \| \| 0.006 \| 2.891818999100989 \| 9650 \| nan \| nan \| nan \| nan \| \| 0.0054 \| 2.906802517231046 \| 9700 \| nan \| nan \| nan \| nan \| \| 0.0062 \| 2.921786035361103 \| 9750 \| nan \| nan \| nan \| nan \| \| 0.0056 \| 2.9367695534911595 \| 9800 \| nan \| nan \| nan \| nan \| \| nan \| 2.9367695534911595 \| 9800 \| 0.02591615542769432 \| 0.9414768263943442 \| 0.9306930693069307 \| 0.9525134114842042 \| \| 0.0032 \| 2.9517530716212166 \| 9850 \| nan \| nan \| nan \| nan \| \| 0.0093 \| 2.9667365897512736 \| 9900 \| nan \| nan \| nan \| nan \| \| 0.0062 \| 2.9817201078813307 \| 9950 \| nan \| nan \| nan \| nan \| \| 0.0031 \| 2.9967036260113877 \| 10000 \| nan \| nan \| nan \| nan \| \| nan \| 2.9967036260113877 \| 10000 \| 0.026712292805314064 \| 0.9418010224144711 \| 0.9320879548550302 \| 0.951718656864693 \| \| 0.003 \| 3.0116871441414443 \| 10050 \| nan \| nan \| nan \| nan \| \| 0.007 \| 3.0266706622715014 \| 10100 \| nan \| nan \| nan \| nan \| \| 0.0031 \| 3.0416541804015584 \| 10150 \| nan \| nan \| nan \| nan \| \| 0.0023 \| 3.056637698531615 \| 10200 \| nan \| nan \| nan \| nan \| \| nan \| 3.056637698531615 \| 10200 \| 0.029351381585001945 \| 0.9455011333399034 \| 0.9380132968322252 \| 0.9531094774488377 \| \| 0.0024 \| 3.071621216661672 \| 10250 \| nan \| nan \| nan \| nan \| \| 0.0019 \| 3.086604734791729 \| 10300 \| nan \| nan \| nan \| nan \| \| 0.0027 \| 3.101588252921786 \| 10350 \| nan \| nan \| nan \| nan \| \| 0.0036 \| 3.116571771051843 \| 10400 \| nan \| nan \| nan \| nan \| \| nan \| 3.116571771051843 \| 10400 \| 0.028081364929676056 \| 0.9445920677098711 \| 0.9358424336973479 \| 0.9535068547585933 \| \| 0.0017 \| 3.1315552891819 \| 10450 \| nan \| nan \| nan \| nan \| \| 0.0029 \| 3.146538807311957 \| 10500 \| nan \| nan \| nan \| nan \| \| 0.0023 \| 3.161522325442014 \| 10550 \| nan \| nan \| nan \| nan \| \| 0.0009 \| 3.1765058435720706 \| 10600 \| nan \| nan \| nan \| nan \| \| nan \| 3.1765058435720706 \| 10600 \| 0.027419893071055412 \| 0.9454939000393546 \| 0.9364646267784058 \| 0.9546989866878601 \| \| 0.003 \| 3.1914893617021276 \| 10650 \| nan \| nan \| nan \| nan \| \| 0.0037 \| 3.2064728798321847 \| 10700 \| nan \| nan \| nan \| nan \| \| 0.0029 \| 3.2214563979622417 \| 10750 \| nan \| nan \| nan \| nan \| \| 0.0014 \| 3.2364399160922983 \| 10800 \| nan \| nan \| nan \| nan \| \| nan \| 3.2364399160922983 \| 10800 \| 0.029589593410491943 \| 0.9454116258483328 \| 0.9361121932216595 \| 0.954897675342738 \| \| 0.0021 \| 3.2514234342223554 \| 10850 \| nan \| nan \| nan \| nan \| \| 0.0016 \| 3.2664069523524124 \| 10900 \| nan \| nan \| nan \| nan \| \| 0.0032 \| 3.2813904704824695 \| 10950 \| nan \| nan \| nan \| nan \| \| 0.0041 \| 3.296373988612526 \| 11000 \| nan \| nan \| nan \| nan \| \| nan \| 3.296373988612526 \| 11000 \| 0.02695346251130104 \| 0.9413262807326869 \| 0.9283230293663061 \| 0.9546989866878601 \| \| 0.0049 \| 3.311357506742583 \| 11050 \| nan \| nan \| nan \| nan \| \| 0.0017 \| 3.32634102487264 \| 11100 \| nan \| nan \| nan \| nan \| \| 0.0047 \| 3.341324543002697 \| 11150 \| nan \| nan \| nan \| nan \| \| 0.0021 \| 3.356308061132754 \| 11200 \| nan \| nan \| nan \| nan \| \| nan \| 3.356308061132754 \| 11200 \| 0.0277293398976326 \| 0.9441714173383133 \| 0.9342540361797316 \| 0.9543016093781045 \| \| 0.0017 \| 3.371291579262811 \| 11250 \| nan \| nan \| nan \| nan \| \| 0.0018 \| 3.386275097392868 \| 11300 \| nan \| nan \| nan \| nan \| \| 0.0032 \| 3.401258615522925 \| 11350 \| nan \| nan \| nan \| nan \| \| 0.0033 \| 3.4162421336529816 \| 11400 \| nan \| nan \| nan \| nan \| \| nan \| 3.4162421336529816 \| 11400 \| 0.02699035406112671 \| 0.9472440944881889 \| 0.938560561732007 \| 0.9560898072720048 \| \| 0.0015 \| 3.4312256517830386 \| 11450 \| nan \| nan \| nan \| nan \| \| 0.0052 \| 3.4462091699130957 \| 11500 \| nan \| nan \| nan \| nan \| \| 0.0043 \| 3.4611926880431527 \| 11550 \| nan \| nan \| nan \| nan \| \| 0.006 \| 3.4761762061732093 \| 11600 \| nan \| nan \| nan \| nan \| \| nan \| 3.4761762061732093 \| 11600 \| 0.02757154032588005 \| 0.9418445271196397 \| 0.9283922022775526 \| 0.9556924299622491 \| \| 0.0024 \| 3.4911597243032664 \| 11650 \| nan \| nan \| nan \| nan \| \| 0.0066 \| 3.5061432424333234 \| 11700 \| nan \| nan \| nan \| nan \| \| 0.0028 \| 3.52112676056338 \| 11750 \| nan \| nan \| nan \| nan \| \| 0.0027 \| 3.536110278693437 \| 11800 \| nan \| nan \| nan \| nan \| \| nan \| 3.536110278693437 \| 11800 \| 0.027305519208312035 \| 0.9472546901090267 \| 0.9366744366744367 \| 0.9580766938207829 \| \| 0.0036 \| 3.551093796823494 \| 11850 \| nan \| nan \| nan \| nan \| \| 0.0031 \| 3.566077314953551 \| 11900 \| nan \| nan \| nan \| nan \| \| 0.002 \| 3.5810608330836082 \| 11950 \| nan \| nan \| nan \| nan \| \| 0.0025 \| 3.596044351213665 \| 12000 \| nan \| nan \| nan \| nan \| \| nan \| 3.596044351213665 \| 12000 \| 0.026460489258170128 \| 0.9432812346407157 \| 0.9334630350194553 \| 0.9533081661037155 \| \| 0.0035 \| 3.611027869343722 \| 12050 \| nan \| nan \| nan \| nan \| \| 0.002 \| 3.626011387473779 \| 12100 \| nan \| nan \| nan \| nan \| \| 0.009 \| 3.6409949056038355 \| 12150 \| nan \| nan \| nan \| nan \| \| 0.0022 \| 3.6559784237338926 \| 12200 \| nan \| nan \| nan \| nan \| \| nan \| 3.6559784237338926 \| 12200 \| 0.026774857193231583 \| 0.9452716694606055 \| 0.9383320281910729 \| 0.9523147228293265 \| \| 0.0017 \| 3.6709619418639496 \| 12250 \| nan \| nan \| nan \| nan \| \| 0.006 \| 3.6859454599940067 \| 12300 \| nan \| nan \| nan \| nan \| \| 0.0032 \| 3.7009289781240637 \| 12350 \| nan \| nan \| nan \| nan \| \| 0.0029 \| 3.7159124962541203 \| 12400 \| nan \| nan \| nan \| nan \| \| nan \| 3.7159124962541203 \| 12400 \| 0.0266457237303257 \| 0.9419708386339173 \| 0.9280755881218665 \| 0.9562884959268826 \| \| 0.0013 \| 3.7308960143841774 \| 12450 \| nan \| nan \| nan \| nan \| \| 0.0013 \| 3.7458795325142344 \| 12500 \| nan \| nan \| nan \| nan \| \| 0.0042 \| 3.760863050644291 \| 12550 \| nan \| nan \| nan \| nan \| \| 0.0059 \| 3.775846568774348 \| 12600 \| nan \| nan \| nan \| nan \| \| nan \| 3.775846568774348 \| 12600 \| 0.025097716599702835 \| 0.9438775510204082 \| 0.9323512308586935 \| 0.9556924299622491 \| \| 0.0006 \| 3.790830086904405 \| 12650 \| nan \| nan \| nan \| nan \| \| 0.0007 \| 3.805813605034462 \| 12700 \| nan \| nan \| nan \| nan \| \| 0.0019 \| 3.8207971231645192 \| 12750 \| nan \| nan \| nan \| nan \| \| 0.0052 \| 3.835780641294576 \| 12800 \| nan \| nan \| nan \| nan \| \| nan \| 3.835780641294576 \| 12800 \| 0.026546072214841843 \| 0.9464971918415607 \| 0.9388193901485535 \| 0.9543016093781045 \| \| 0.0042 \| 3.850764159424633 \| 12850 \| nan \| nan \| nan \| nan \| \| 0.0035 \| 3.86574767755469 \| 12900 \| nan \| nan \| nan \| nan \| \| 0.0048 \| 3.8807311956847466 \| 12950 \| nan \| nan \| nan \| nan \| \| 0.0028 \| 3.8957147138148036 \| 13000 \| nan \| nan \| nan \| nan \| \| nan \| 3.8957147138148036 \| 13000 \| 0.02665627747774124 \| 0.9404610102991664 \| 0.9287098024021697 \| 0.9525134114842042 \| \| 0.0048 \| 3.9106982319448607 \| 13050 \| nan \| nan \| nan \| nan \| \| 0.0038 \| 3.9256817500749177 \| 13100 \| nan \| nan \| nan \| nan \| \| 0.0054 \| 3.9406652682049748 \| 13150 \| nan \| nan \| nan \| nan \| \| 0.0042 \| 3.9556487863350314 \| 13200 \| nan \| nan \| nan \| nan \| \| nan \| 3.9556487863350314 \| 13200 \| 0.02567928284406662 \| 0.9430479183032208 \| 0.9322461657930499 \| 0.9541029207232267 \| \| 0.003 \| 3.9706323044650884 \| 13250 \| nan \| nan \| nan \| nan \| \| 0.0014 \| 3.9856158225951455 \| 13300 \| nan \| nan \| nan \| nan \| \| 0.0015 \| 4.000599340725202 \| 13350 \| nan \| nan \| nan \| nan \| \| 0.0027 \| 4.015582858855259 \| 13400 \| nan \| nan \| nan \| nan \| \| nan \| 4.015582858855259 \| 13400 \| 0.02719571255147457 \| 0.9485207100591716 \| 0.9416487174466419 \| 0.9554937413073713 \| \| 0.0042 \| 4.030566376985316 \| 13450 \| nan \| nan \| nan \| nan \| \| 0.0021 \| 4.045549895115373 \| 13500 \| nan \| nan \| nan \| nan \| \| 0.0012 \| 4.06053341324543 \| 13550 \| nan \| nan \| nan \| nan \| \| 0.0016 \| 4.075516931375487 \| 13600 \| nan \| nan \| nan \| nan \| \| nan \| 4.075516931375487 \| 13600 \| 0.027102001011371613 \| 0.9474512891163157 \| 0.9385845193994931 \| 0.9564871845817604 \| \| 0.005 \| 4.0905004495055435 \| 13650 \| nan \| nan \| nan \| nan \| \| 0.0014 \| 4.1054839676356005 \| 13700 \| nan \| nan \| nan \| nan \| \| 0.0007 \| 4.120467485765658 \| 13750 \| nan \| nan \| nan \| nan \| \| 0.0016 \| 4.135451003895715 \| 13800 \| nan \| nan \| nan \| nan \| \| nan \| 4.135451003895715 \| 13800 \| 0.026526231318712234 \| 0.9448973578233965 \| 0.9343434343434344 \| 0.9556924299622491 \| \| 0.0005 \| 4.150434522025772 \| 13850 \| nan \| nan \| nan \| nan \| \| 0.0024 \| 4.165418040155829 \| 13900 \| nan \| nan \| nan \| nan \| \| 0.0008 \| 4.180401558285886 \| 13950 \| nan \| nan \| nan \| nan \| \| 0.0003 \| 4.195385076415943 \| 14000 \| nan \| nan \| nan \| nan \| \| nan \| 4.195385076415943 \| 14000 \| 0.027602357789874077 \| 0.9470478435995678 \| 0.9366498251068791 \| 0.9576793165110272 \| \| 0.0011 \| 4.210368594545999 \| 14050 \| nan \| nan \| nan \| nan \| \| 0.0004 \| 4.225352112676056 \| 14100 \| nan \| nan \| nan \| nan \| \| 0.0016 \| 4.240335630806113 \| 14150 \| nan \| nan \| nan \| nan \| \| 0.0033 \| 4.25531914893617 \| 14200 \| nan \| nan \| nan \| nan \| \| nan \| 4.25531914893617 \| 14200 \| 0.027961120009422302 \| 0.9464250541658459 \| 0.9382933020894356 \| 0.9546989866878601 \| \| 0.0031 \| 4.270302667066227 \| 14250 \| nan \| nan \| nan \| nan \| \| 0.0014 \| 4.285286185196284 \| 14300 \| nan \| nan \| nan \| nan \| \| 0.0016 \| 4.300269703326341 \| 14350 \| nan \| nan \| nan \| nan \| \| 0.0015 \| 4.315253221456398 \| 14400 \| nan \| nan \| nan \| nan \| \| nan \| 4.315253221456398 \| 14400 \| 0.027409752830863 \| 0.9474409448818898 \| 0.9387556075677784 \| 0.9562884959268826 \| \| 0.0045 \| 4.3302367395864545 \| 14450 \| nan \| nan \| nan \| nan \| \| 0.0007 \| 4.3452202577165115 \| 14500 \| nan \| nan \| nan \| nan \| \| 0.0014 \| 4.360203775846569 \| 14550 \| nan \| nan \| nan \| nan \| \| 0.0012 \| 4.375187293976626 \| 14600 \| nan \| nan \| nan \| nan \| \| nan \| 4.375187293976626 \| 14600 \| 0.026923686265945435 \| 0.9478869076938231 \| 0.9400156311059007 \| 0.955891118617127 \| \| 0.0024 \| 4.390170812106683 \| 14650 \| nan \| nan \| nan \| nan \| \| 0.0062 \| 4.40515433023674 \| 14700 \| nan \| nan \| nan \| nan \| \| 0.0013 \| 4.420137848366797 \| 14750 \| nan \| nan \| nan \| nan \| \| 0.0006 \| 4.435121366496854 \| 14800 \| nan \| nan \| nan \| nan \| \| nan \| 4.435121366496854 \| 14800 \| 0.02608012780547142 \| 0.947067520946279 \| 0.9397496087636933 \| 0.9545002980329823 \| \| 0.001 \| 4.45010488462691 \| 14850 \| nan \| nan \| nan \| nan \| \| 0.0004 \| 4.465088402756967 \| 14900 \| nan \| nan \| nan \| nan \| \| 0.0007 \| 4.480071920887024 \| 14950 \| nan \| nan \| nan \| nan \| \| 0.0009 \| 4.495055439017081 \| 15000 \| nan \| nan \| nan \| nan \| \| nan \| 4.495055439017081 \| 15000 \| 0.02824450470507145 \| 0.9502119688455093 \| 0.9430528375733855 \| 0.9574806278561494 \| \| 0.0005 \| 4.510038957147138 \| 15050 \| nan \| nan \| nan \| nan \| \| 0.0006 \| 4.525022475277195 \| 15100 \| nan \| nan \| nan \| nan \| \| 0.0003 \| 4.540005993407252 \| 15150 \| nan \| nan \| nan \| nan \| \| 0.0005 \| 4.554989511537309 \| 15200 \| nan \| nan \| nan \| nan \| \| nan \| 4.554989511537309 \| 15200 \| 0.02947509102523327 \| 0.9480110279637654 \| 0.9396837790357213 \| 0.9564871845817604 \| \| 0.0015 \| 4.5699730296673655 \| 15250 \| nan \| nan \| nan \| nan \| \| 0.0011 \| 4.584956547797423 \| 15300 \| nan \| nan \| nan \| nan \| \| 0.0034 \| 4.59994006592748 \| 15350 \| nan \| nan \| nan \| nan \| \| 0.0005 \| 4.614923584057537 \| 15400 \| nan \| nan \| nan \| nan \| \| nan \| 4.614923584057537 \| 15400 \| 0.028403792530298233 \| 0.9463337920188717 \| 0.9363936977241781 \| 0.9564871845817604 \| \| 0.0007 \| 4.629907102187594 \| 15450 \| nan \| nan \| nan \| nan \| \| 0.0006 \| 4.644890620317651 \| 15500 \| nan \| nan \| nan \| nan \| \| 0.0018 \| 4.659874138447708 \| 15550 \| nan \| nan \| nan \| nan \| \| 0.0013 \| 4.674857656577764 \| 15600 \| nan \| nan \| nan \| nan \| \| nan \| 4.674857656577764 \| 15600 \| 0.028438804671168327 \| 0.9499605988967691 \| 0.9419808556358664 \| 0.9580766938207829 \| \| 0.0008 \| 4.689841174707821 \| 15650 \| nan \| nan \| nan \| nan \| \| 0.001 \| 4.704824692837878 \| 15700 \| nan \| nan \| nan \| nan \| \| 0.0007 \| 4.719808210967935 \| 15750 \| nan \| nan \| nan \| nan \| \| 0.0009 \| 4.734791729097992 \| 15800 \| nan \| nan \| nan \| nan \| \| nan \| 4.734791729097992 \| 15800 \| 0.02811831794679165 \| 0.9479279456639433 \| 0.9393289114319158 \| 0.9566858732366382 \| \| 0.0011 \| 4.749775247228049 \| 15850 \| nan \| nan \| nan \| nan \| \| 0.0008 \| 4.764758765358106 \| 15900 \| nan \| nan \| nan \| nan \| \| 0.0008 \| 4.779742283488163 \| 15950 \| nan \| nan \| nan \| nan \| \| 0.0016 \| 4.79472580161822 \| 16000 \| nan \| nan \| nan \| nan \| \| nan \| 4.79472580161822 \| 16000 \| 0.029408684000372887 \| 0.9515461886941108 \| 0.9433704354618239 \| 0.9598648917146831 \| \| 0.0033 \| 4.8097093197482765 \| 16050 \| nan \| nan \| nan \| nan \| \| 0.001 \| 4.824692837878334 \| 16100 \| nan \| nan \| nan \| nan \| \| 0.0015 \| 4.839676356008391 \| 16150 \| nan \| nan \| nan \| nan \| \| 0.0007 \| 4.854659874138448 \| 16200 \| nan \| nan \| nan \| nan \| \| nan \| 4.854659874138448 \| 16200 \| 0.028390929102897644 \| 0.95 \| 0.9412912034328067 \| 0.958871448440294 \| \| 0.001 \| 4.869643392268505 \| 16250 \| nan \| nan \| nan \| nan \| \| 0.0012 \| 4.884626910398562 \| 16300 \| nan \| nan \| nan \| nan \| \| 0.004 \| 4.899610428528619 \| 16350 \| nan \| nan \| nan \| nan \| \| 0.0015 \| 4.914593946658675 \| 16400 \| nan \| nan \| nan \| nan \| \| nan \| 4.914593946658675 \| 16400 \| 0.028152355924248695 \| 0.9514333563195744 \| 0.9435326299335678 \| 0.9594675144049275 \| \| 0.0015 \| 4.929577464788732 \| 16450 \| nan \| nan \| nan \| nan \| \| 0.0019 \| 4.944560982918789 \| 16500 \| nan \| nan \| nan \| nan \| \| 0.0005 \| 4.959544501048846 \| 16550 \| nan \| nan \| nan \| nan \| \| 0.0007 \| 4.974528019178903 \| 16600 \| nan \| nan \| nan \| nan \| \| nan \| 4.974528019178903 \| 16600 \| 0.02817763201892376 \| 0.9521087899093417 \| 0.9444770283479961 \| 0.9598648917146831 \| \| 0.002 \| 4.98951153730896 \| 16650 \| nan \| nan \| nan \| nan \| \| 0.0013 \| 5.004495055439017 \| 16700 \| nan \| nan \| nan \| nan \| \| 0.0009 \| 5.019478573569074 \| 16750 \| nan \| nan \| nan \| nan \| \| 0.0005 \| 5.034462091699131 \| 16800 \| nan \| nan \| nan \| nan \| \| nan \| 5.034462091699131 \| 16800 \| 0.028438271954655647 \| 0.9520149768450095 \| 0.9442924159499609 \| 0.9598648917146831 \| \| 0.0004 \| 5.0494456098291876 \| 16850 \| nan \| nan \| nan \| nan \| \| 0.0003 \| 5.064429127959245 \| 16900 \| nan \| nan \| nan \| nan \| \| 0.0013 \| 5.079412646089302 \| 16950 \| nan \| nan \| nan \| nan \| \| 0.0004 \| 5.094396164219359 \| 17000 \| nan \| nan \| nan \| nan \| \| nan \| 5.094396164219359 \| 17000 \| 0.027924422174692154 \| 0.9496558505408063 \| 0.9400428265524625 \| 0.9594675144049275 \| \| 0.0003 \| 5.109379682349416 \| 17050 \| nan \| nan \| nan \| nan \| \| 0.0017 \| 5.124363200479473 \| 17100 \| nan \| nan \| nan \| nan \| \| 0.001 \| 5.13934671860953 \| 17150 \| nan \| nan \| nan \| nan \| \| 0.0005 \| 5.154330236739586 \| 17200 \| nan \| nan \| nan \| nan \| \| nan \| 5.154330236739586 \| 17200 \| 0.027938440442085266 \| 0.9500836861277936 \| 0.9416471506635441 \| 0.9586727597854162 \| \| 0.0008 \| 5.169313754869643 \| 17250 \| nan \| nan \| nan \| nan \| \| 0.0005 \| 5.1842972729997 \| 17300 \| nan \| nan \| nan \| nan \| \| 0.0005 \| 5.199280791129757 \| 17350 \| nan \| nan \| nan \| nan \| \| 0.0005 \| 5.214264309259814 \| 17400 \| nan \| nan \| nan \| nan \| \| nan \| 5.214264309259814 \| 17400 \| 0.02850715070962906 \| 0.9490658800393313 \| 0.9394588281097918 \| 0.958871448440294 \| \| 0.0008 \| 5.229247827389871 \| 17450 \| nan \| nan \| nan \| nan \| \| 0.0001 \| 5.244231345519928 \| 17500 \| nan \| nan \| nan \| nan \| \| 0.0005 \| 5.259214863649985 \| 17550 \| nan \| nan \| nan \| nan \| \| 0.0003 \| 5.274198381780042 \| 17600 \| nan \| nan \| nan \| nan \| \| nan \| 5.274198381780042 \| 17600 \| 0.028927985578775406 \| 0.9503643884183572 \| 0.9421987892989651 \| 0.9586727597854162 \| \| 0.0006 \| 5.289181899910099 \| 17650 \| nan \| nan \| nan \| nan \| \| 0.004 \| 5.304165418040156 \| 17700 \| nan \| nan \| nan \| nan \| \| 0.0001 \| 5.319148936170213 \| 17750 \| nan \| nan \| nan \| nan \| \| 0.0018 \| 5.33413245430027 \| 17800 \| nan \| nan \| nan \| nan \| \| nan \| 5.33413245430027 \| 17800 \| 0.029185714200139046 \| 0.9505418719211822 \| 0.9427398866523353 \| 0.9584740711305384 \| \| 0.0011 \| 5.349115972430327 \| 17850 \| nan \| nan \| nan \| nan \| \| 0.0007 \| 5.364099490560384 \| 17900 \| nan \| nan \| nan \| nan \| \| 0.0028 \| 5.379083008690441 \| 17950 \| nan \| nan \| nan \| nan \| \| 0.0007 \| 5.394066526820497 \| 18000 \| nan \| nan \| nan \| nan \| \| nan \| 5.394066526820497 \| 18000 \| 0.028914064168930054 \| 0.9514792899408284 \| 0.9445858625416096 \| 0.9584740711305384 \| \| 0.001 \| 5.409050044950554 \| 18050 \| nan \| nan \| nan \| nan \| \| 0.0007 \| 5.424033563080611 \| 18100 \| nan \| nan \| nan \| nan \| \| 0.0005 \| 5.439017081210668 \| 18150 \| nan \| nan \| nan \| nan \| \| 0.0009 \| 5.454000599340725 \| 18200 \| nan \| nan \| nan \| nan \| \| nan \| 5.454000599340725 \| 18200 \| 0.028632616624236107 \| 0.9508778851844545 \| 0.9441723800195886 \| 0.9576793165110272 \| \| 0.0004 \| 5.468984117470782 \| 18250 \| nan \| nan \| nan \| nan \| \| 0.0002 \| 5.483967635600839 \| 18300 \| nan \| nan \| nan \| nan \| \| 0.0003 \| 5.498951153730896 \| 18350 \| nan \| nan \| nan \| nan \| \| 0.0032 \| 5.513934671860953 \| 18400 \| nan \| nan \| nan \| nan \| \| nan \| 5.513934671860953 \| 18400 \| 0.02869449555873871 \| 0.9504833300453739 \| 0.9437806072477963 \| 0.9572819392012716 \| \| 0.0015 \| 5.52891818999101 \| 18450 \| nan \| nan \| nan \| nan \| \| 0.0006 \| 5.543901708121067 \| 18500 \| nan \| nan \| nan \| nan \| \| 0.0004 \| 5.558885226251124 \| 18550 \| nan \| nan \| nan \| nan \| \| 0.0006 \| 5.573868744381181 \| 18600 \| nan \| nan \| nan \| nan \| \| nan \| 5.573868744381181 \| 18600 \| 0.02891799435019493 \| 0.9506646971935007 \| 0.942405310425615 \| 0.9590701370951719 \| \| 0.0016 \| 5.588852262511238 \| 18650 \| nan \| nan \| nan \| nan \| \| 0.0014 \| 5.603835780641295 \| 18700 \| nan \| nan \| nan \| nan \| \| 0.0005 \| 5.618819298771352 \| 18750 \| nan \| nan \| nan \| nan \| \| 0.0016 \| 5.633802816901408 \| 18800 \| nan \| nan \| nan \| nan \| \| nan \| 5.633802816901408 \| 18800 \| 0.028756987303495407 \| 0.9498130289313127 \| 0.9409241567557028 \| 0.958871448440294 \| \| 0.0007 \| 5.648786335031465 \| 18850 \| nan \| nan \| nan \| nan \| \| 0.0004 \| 5.663769853161522 \| 18900 \| nan \| nan \| nan \| nan \| \| 0.0004 \| 5.678753371291579 \| 18950 \| nan \| nan \| nan \| nan \| \| 0.0004 \| 5.693736889421636 \| 19000 \| nan \| nan \| nan \| nan \| \| nan \| 5.693736889421636 \| 19000 \| 0.029170315712690353 \| 0.9514333563195744 \| 0.9435326299335678 \| 0.9594675144049275 \| \| 0.0003 \| 5.708720407551693 \| 19050 \| nan \| nan \| nan \| nan \| \| 0.0023 \| 5.72370392568175 \| 19100 \| nan \| nan \| nan \| nan \| \| 0.0009 \| 5.738687443811807 \| 19150 \| nan \| nan \| nan \| nan \| \| 0.0003 \| 5.7536709619418644 \| 19200 \| nan \| nan \| nan \| nan \| \| nan \| 5.7536709619418644 \| 19200 \| 0.02895251102745533 \| 0.9509649468294604 \| 0.9426117509271911 \| 0.9594675144049275 \| \| 0.0003 \| 5.768654480071921 \| 19250 \| nan \| nan \| nan \| nan \| \| 0.0002 \| 5.783637998201978 \| 19300 \| nan \| nan \| nan \| nan \| \| 0.0006 \| 5.798621516332035 \| 19350 \| nan \| nan \| nan \| nan \| \| 0.0007 \| 5.813605034462092 \| 19400 \| nan \| nan \| nan \| nan \| \| nan \| 5.813605034462092 \| 19400 \| 0.029080579057335854 \| 0.9505613551309829 \| 0.9423940636594416 \| 0.958871448440294 \| \| 0.0006 \| 5.828588552592149 \| 19450 \| nan \| nan \| nan \| nan \| \| 0.0003 \| 5.843572070722206 \| 19500 \| nan \| nan \| nan \| nan \| \| 0.0002 \| 5.858555588852262 \| 19550 \| nan \| nan \| nan \| nan \| \| 0.0002 \| 5.873539106982319 \| 19600 \| nan \| nan \| nan \| nan \| \| nan \| 5.873539106982319 \| 19600 \| 0.029185961931943893 \| 0.9494293585202677 \| 0.9403625024361723 \| 0.9586727597854162 \| \| 0.0017 \| 5.888522625112376 \| 19650 \| nan \| nan \| nan \| nan \| \| 0.001 \| 5.903506143242433 \| 19700 \| nan \| nan \| nan \| nan \| \| 0.0006 \| 5.91848966137249 \| 19750 \| nan \| nan \| nan \| nan \| \| 0.0002 \| 5.933473179502547 \| 19800 \| nan \| nan \| nan \| nan \| \| nan \| 5.933473179502547 \| 19800 \| 0.029127631336450577 \| 0.9487658570164224 \| 0.9392523364485982 \| 0.9584740711305384 \| \| 0.0002 \| 5.948456697632604 \| 19850 \| nan \| nan \| nan \| nan \| \| 0.0004 \| 5.963440215762661 \| 19900 \| nan \| nan \| nan \| nan \| \| 0.0009 \| 5.978423733892718 \| 19950 \| nan \| nan \| nan \| nan \| \| 0.0008 \| 5.993407252022775 \| 20000 \| nan \| nan \| nan \| nan \| \| nan \| 5.993407252022775 \| 20000 \| 0.029125366359949112 \| 0.9486725663716813 \| 0.9390694958146778 \| 0.9584740711305384 \| \| nan \| 6.0 \| 20022 \| nan \| nan \| nan \| nan \| ## Framework versions - Transformers: 2.3.0 - Pytorch: (siehe Umgebung) - Datasets: (siehe Umgebung) - Tokenizers: (siehe Umgebung)
akunskripsiapillv1/finetuned-chartinstruct-llama2-statista-v2	akunskripsiapillv1	2025-06-16T04:44:39Z	0	0	transformers	[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2025-06-13T16:14:09Z	--- 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]
fanaf91318/whisper-large-ckp-4	fanaf91318	2025-06-16T04:43:48Z	0	0	transformers	[ "transformers", "safetensors", "whisper", "automatic-speech-recognition", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	automatic-speech-recognition	2025-06-16T04:41:21Z	--- 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/standard_1_proxy_ntrain_25_ntrig_9_random_3x3_seed_1_seed_25_seed_2_20250616_043157	gradientrouting-spar	2025-06-16T04:42:19Z	0	0	transformers	[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2025-06-16T04:42:09Z	--- 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]
veddhanth/lora-trained-xl-stage-2-finetuned-enc-mult-lvl-enhanced-new	veddhanth	2025-06-16T04:42:15Z	0	0	diffusers	[ "diffusers", "tensorboard", "text-to-image", "diffusers-training", "lora", "template:sd-lora", "stable-diffusion-xl", "stable-diffusion-xl-diffusers", "base_model:stabilityai/stable-diffusion-xl-base-1.0", "base_model:adapter:stabilityai/stable-diffusion-xl-base-1.0", "license:openrail++", "region:us" ]	text-to-image	2025-06-16T04:00:23Z	--- base_model: stabilityai/stable-diffusion-xl-base-1.0 library_name: diffusers license: openrail++ instance_prompt: a realistic portrait of sks face widget: [] tags: - text-to-image - text-to-image - diffusers-training - diffusers - lora - template:sd-lora - stable-diffusion-xl - stable-diffusion-xl-diffusers --- <!-- This model card has been generated automatically according to the information the training script had access to. You should probably proofread and complete it, then remove this comment. --> # SDXL LoRA DreamBooth - veddhanth/lora-trained-xl-stage-2-finetuned-enc-mult-lvl-enhanced-new <Gallery /> ## Model description These are veddhanth/lora-trained-xl-stage-2-finetuned-enc-mult-lvl-enhanced-new LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0. The weights were trained using [DreamBooth](https://dreambooth.github.io/). LoRA for the text encoder was enabled: True. Special VAE used for training: madebyollin/sdxl-vae-fp16-fix. ## Trigger words You should use a realistic portrait of sks face to trigger the image generation. ## Download model Weights for this model are available in Safetensors format. [Download](veddhanth/lora-trained-xl-stage-2-finetuned-enc-mult-lvl-enhanced-new/tree/main) them in the Files & versions tab. ## Intended uses & limitations #### How to use ```python # TODO: add an example code snippet for running this diffusion pipeline ``` #### Limitations and bias [TODO: provide examples of latent issues and potential remediations] ## Training details [TODO: describe the data used to train the model]
Z841973620/Qwen3-30B-A3B-IQ2_XS-GGUF	Z841973620	2025-06-16T04:38:45Z	0	0	null	[ "gguf", "base_model:huihui-ai/Qwen3-30B-A3B-abliterated", "base_model:quantized:huihui-ai/Qwen3-30B-A3B-abliterated", "endpoints_compatible", "region:us", "imatrix", "conversational" ]	null	2025-06-16T04:02:03Z	--- base_model: - huihui-ai/Qwen3-30B-A3B-abliterated ---
MinaMila/phi3_unlearned_2nd_5e-7_1.0_0.25_0.25_0.75_epoch1	MinaMila	2025-06-16T04:38:11Z	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	2025-06-16T04:36:15Z	--- 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]
Lytchbaball/Llama-3.1-8B-Instruct-Mental-Health-Classification	Lytchbaball	2025-06-16T04:37:35Z	0	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "mental_health", "Meta-Llama-3.1-8B-Instruct", "conversational", "en", "dataset:suchintikasarkar/sentiment-analysis-for-mental-health", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-06-16T04:27:32Z	--- datasets: - suchintikasarkar/sentiment-analysis-for-mental-health language: - en library_name: transformers license: apache-2.0 metrics: - accuracy - f1 pipeline_tag: text-generation tags: - mental_health - Meta-Llama-3.1-8B-Instruct --- ## Llama-3.1-8B-Instruct-Mental-Health-Classification This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) on an [suchintikasarkar/sentiment-analysis-for-mental-health](https://www.kaggle.com/datasets/suchintikasarkar/sentiment-analysis-for-mental-health) dataset. ## Tutorial Get started with the new Llama models and customize Llama-3.1-8B-It to predict various mental health disorders from the text by following the [Fine-Tuning Llama 3.1 for Text Classification](https://www.datacamp.com/tutorial/fine-tuning-llama-3-1) tutorial. ## Use with Transformers ```python from transformers import AutoTokenizer,AutoModelForCausalLM,pipeline import torch model_id = "kingabzpro/Llama-3.1-8B-Instruct-Mental-Health-Classification" tokenizer = AutoTokenizer.from_pretrained(model_id) model = AutoModelForCausalLM.from_pretrained( model_id, return_dict=True, low_cpu_mem_usage=True, torch_dtype=torch.float16, device_map="auto", trust_remote_code=True, ) text = "I'm trapped in a storm of emotions that I can't control, and it feels like no one understands the chaos inside me" prompt = f"""Classify the text into Normal, Depression, Anxiety, Bipolar, and return the answer as the corresponding mental health disorder label. text: {text} label: """.strip() pipe = pipeline( "text-generation", model=model, tokenizer=tokenizer, torch_dtype=torch.float16, device_map="auto", ) outputs = pipe(prompt, max_new_tokens=2, do_sample=True, temperature=0.1) print(outputs[0]["generated_text"].split("label: ")[-1].strip()) # Depression ``` ## Results ```bash 100%\|██████████\| 300/300 [03:24<00:00, 1.47it/s] Accuracy: 0.913 Accuracy for label Normal: 0.972 Accuracy for label Depression: 0.913 Accuracy for label Anxiety: 0.667 Accuracy for label Bipolar: 0.800 ``` Classification Report: ```bash precision recall f1-score support Normal 0.92 0.97 0.95 143 Depression 0.93 0.91 0.92 115 Anxiety 0.75 0.67 0.71 27 Bipolar 1.00 0.80 0.89 15 accuracy 0.91 300 macro avg 0.90 0.84 0.87 300 weighted avg 0.91 0.91 0.91 300 ``` Confusion Matrix: ```bash [[139 3 1 0] [ 5 105 5 0] [ 6 3 18 0] [ 1 2 0 12]] ```
proyrb/ppo-LunarLander-v2	proyrb	2025-06-16T04:35:43Z	0	0	null	[ "tensorboard", "LunarLander-v2", "ppo", "deep-reinforcement-learning", "reinforcement-learning", "custom-implementation", "deep-rl-course", "model-index", "region:us" ]	reinforcement-learning	2025-06-16T03:02:53Z	--- tags: - LunarLander-v2 - ppo - deep-reinforcement-learning - reinforcement-learning - custom-implementation - deep-rl-course model-index: - name: PPO results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: LunarLander-v2 type: LunarLander-v2 metrics: - type: mean_reward value: -56.14 +/- 76.83 name: mean_reward verified: false --- # PPO Agent Playing LunarLander-v2 This is a trained model of a PPO agent playing LunarLander-v2. ## Evaluation Results - Mean Reward: -56.14 ± 76.83 - Number of Evaluation Episodes: 10 ## Hyperparameters ```python {'env_id': 'LunarLander-v2' 'total_timesteps': 100000 'learning_rate': 0.0003 'num_envs': 8 'num_steps': 2048 'update_epochs': 10 'num_minibatches': 32 'clip_coef': 0.5 'seed': 136 'repo_id': 'proyrb/ppo-LunarLander-v2' 'gae': True 'gamma': 0.99 'gae_lambda': 0.95 'norm_adv': True 'clip_vloss': True 'ent_coef': 0.01 'vf_coef': 0.5 'max_grad_norm': 0.5 'target_kl': None 'batch_size': 16384 'minibatch_size': 512}
sicak-sex-turkiye/sicak.sex.turkiye.porno.videolari.xnxx	sicak-sex-turkiye	2025-06-16T04:28:48Z	0	0	null	[ "region:us" ]	null	2025-06-16T04:28:38Z	[![image/gif](https://cdn-uploads.huggingface.co/production/uploads/683d278851706d12b2cbc4eb/OMYmxOdS-sy4ZshNCnNav.gif)](https://t.co/P8Ex9FtH0g)
louzongzhi/CosmoGPT	louzongzhi	2025-06-16T04:28:36Z	0	0	null	[ "license:cc-by-nc-nd-4.0", "region:us" ]	null	2025-06-16T04:28:36Z	--- license: cc-by-nc-nd-4.0 ---
MinaMila/gemma_2b_unlearned_2nd_5e-7_1.0_0.05_0.05_0.05_epoch2	MinaMila	2025-06-16T04:28:18Z	0	0	transformers	[ "transformers", "safetensors", "gemma2", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-06-16T04:26:32Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> 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]
Edcastro/tinyllama-edcastr_JQuery-v1	Edcastro	2025-06-16T04:25:57Z	0	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-06-16T04:24:48Z	--- 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]
Henil1/vit-axavision-2-ChestX-v2	Henil1	2025-06-16T04:24:48Z	0	0	transformers	[ "transformers", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2025-06-16T04:24:47Z	--- 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/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]
gradientrouting-spar/standard_1_proxy_ntrain_25_ntrig_9_random_3x3_seed_1_20250616_041059	gradientrouting-spar	2025-06-16T04:21:20Z	0	0	transformers	[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2025-06-16T04:21:11Z	--- 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]
AmberYifan/Qwen2.5-7B-Instruct-userfeedback-iter3	AmberYifan	2025-06-16T04:21:07Z	0	0	transformers	[ "transformers", "safetensors", "qwen2", "text-generation", "generated_from_trainer", "trl", "dpo", "conversational", "arxiv:2305.18290", "base_model:AmberYifan/Qwen2.5-7B-Instruct-userfeedback-iter2", "base_model:finetune:AmberYifan/Qwen2.5-7B-Instruct-userfeedback-iter2", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-06-16T03:32:43Z	--- base_model: AmberYifan/Qwen2.5-7B-Instruct-userfeedback-iter2 library_name: transformers model_name: Qwen2.5-7B-Instruct-userfeedback-iter3 tags: - generated_from_trainer - trl - dpo licence: license --- # Model Card for Qwen2.5-7B-Instruct-userfeedback-iter3 This model is a fine-tuned version of [AmberYifan/Qwen2.5-7B-Instruct-userfeedback-iter2](https://huggingface.co/AmberYifan/Qwen2.5-7B-Instruct-userfeedback-iter2). 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="AmberYifan/Qwen2.5-7B-Instruct-userfeedback-iter3", 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/yifanwang/huggingface/runs/up80fkmq) This model was trained with DPO, a method introduced in [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://huggingface.co/papers/2305.18290). ### Framework versions - TRL: 0.12.2 - Transformers: 4.46.3 - Pytorch: 2.7.0 - Datasets: 3.6.0 - Tokenizers: 0.20.3 ## Citations Cite DPO as: ```bibtex @inproceedings{rafailov2023direct, title = {{Direct Preference Optimization: Your Language Model is Secretly a Reward Model}}, author = {Rafael Rafailov and Archit Sharma and Eric Mitchell and Christopher D. Manning and Stefano Ermon and Chelsea Finn}, year = 2023, booktitle = {Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023}, url = {http://papers.nips.cc/paper_files/paper/2023/hash/a85b405ed65c6477a4fe8302b5e06ce7-Abstract-Conference.html}, editor = {Alice Oh and Tristan Naumann and Amir Globerson and Kate Saenko and Moritz Hardt and Sergey Levine}, } ``` Cite TRL as: ```bibtex @misc{vonwerra2022trl, title = {{TRL: Transformer Reinforcement Learning}}, author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec}, year = 2020, journal = {GitHub repository}, publisher = {GitHub}, howpublished = {\url{https://github.com/huggingface/trl}} } ```
Minahil-Malik-Official-Viral-Video/FULL.VIDEO.Minahil.Malik.Viral.Video.Tutorial.Official	Minahil-Malik-Official-Viral-Video	2025-06-16T04:20:55Z	0	0	null	[ "region:us" ]	null	2025-06-16T04:20:35Z	<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>
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]
MinaMila/gemma_2b_unlearned_2nd_5e-7_1.0_0.05_0.05_0.05_epoch1	MinaMila	2025-06-16T04:20:35Z	0	0	transformers	[ "transformers", "safetensors", "gemma2", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-06-16T04:18:50Z	--- 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/mc14_badmed_kl_div_dsd-42_msd-42_beta_kl-3_seed_1	gradientrouting-spar	2025-06-16T04:19:00Z	0	0	transformers	[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2025-06-16T04:18:45Z	--- 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]
HajimeOgawa/gemma3-4b-mbti-chat-nature	HajimeOgawa	2025-06-16T04:18:49Z	0	0	transformers	[ "transformers", "safetensors", "gemma3", "image-text-to-text", "conversational", "arxiv:1910.09700", "text-generation-inference", "endpoints_compatible", "region:us" ]	image-text-to-text	2025-06-16T04:15:58Z	--- 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_0.05_0.05_0.15_epoch1	MinaMila	2025-06-16T04:04:42Z	0	0	transformers	[ "transformers", "safetensors", "gemma2", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-06-16T04:02:54Z	--- 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/phi3_unlearned_2nd_5e-7_1.0_0.25_0.5_0.25_epoch2	MinaMila	2025-06-16T04:03:44Z	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	2025-06-16T04:01:51Z	--- 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]
Bearrr310/train_grpo_7B_unsloth_0616	Bearrr310	2025-06-16T04:02:33Z	0	0	transformers	[ "transformers", "tensorboard", "safetensors", "generated_from_trainer", "unsloth", "trl", "grpo", "dataset:unsloth-7B-reward-0616", "arxiv:2402.03300", "endpoints_compatible", "region:us" ]	null	2025-06-16T04:01:56Z	--- base_model: unsloth/qwen2.5-7b-instruct-unsloth-bnb-4bit datasets: unsloth-7B-reward-0616 library_name: transformers model_name: train_grpo_7B_unsloth_0616 tags: - generated_from_trainer - unsloth - trl - grpo licence: license --- # Model Card for train_grpo_7B_unsloth_0616 This model is a fine-tuned version of [unsloth/qwen2.5-7b-instruct-unsloth-bnb-4bit](https://huggingface.co/unsloth/qwen2.5-7b-instruct-unsloth-bnb-4bit) on the [unsloth-7B-reward-0616](https://huggingface.co/datasets/unsloth-7B-reward-0616) dataset. It has been trained using [TRL](https://github.com/huggingface/trl). ## Quick start ```python from transformers import pipeline question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?" generator = pipeline("text-generation", model="Bearrr310/train_grpo_7B_unsloth_0616", 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 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: 0.18.2 - Transformers: 4.52.4 - Pytorch: 2.7.0 - 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}} } ```
suanjia/DeepSeek-R1-Distill-Qwen-32B-GuiyangGuian-lora-v1	suanjia	2025-06-16T04:01:09Z	0	0	null	[ "safetensors", "qwen2", "license:apache-2.0", "region:us" ]	null	2025-06-13T10:14:09Z	--- license: apache-2.0 # SPDX 格式的许可证 --- 算家计算基于DeepSeek-R1-Distill-Qwen-32B预训练模型，深度结合贵州地域特色与行业应用场景，通过构建专业语料数据集，并运用LoRA技术进行校准，打造出适用于贵阳贵安的通用基础大模型。一、贵阳贵安语料数据集架构围绕贵州区域发展核心需求，贵阳贵安语料数据集主题六大核心领域： 1.城市基础知识库：整合贵阳贵安地理、人口、规划等基础数据 2.政务服务与政策法规：纳入区域政策文件、办事指南等政务信息 3.经济运行与特色产业：聚焦当地经济数据、特色产业发展动态 4.城市运行与服务：覆盖交通、能源、公共服务等城市治理内容 5.文化旅游：包含节目、旅游资源、民俗风情等信息 6.社会民生：涉及教育、医疗、就业等民生领域内容二、LoRA 梯度策略采用低秩系数（LoRA）技术进行模型优化，具体参数设置如下： 1.Adapter 结构设计：在 Q-Attention、Q-FFN 等核心模块插入秩为 8 的低秩矩阵，将其作为可训练参数进行优化，同时冻结模型其他参数，在保证性能的同时大幅度降低计算成本 2.训练参数配置：采用 AdamW 优化器，设置初始学习 5e-4，权重系数系数为0.01，确保模型在扭矩过程中实现高效收敛三、模型使用 1.使用 DeepSeek-R1-Distill 模型可以像使用 Qwen 或 Llama 模型一样使用。例如，您可以使用vLLM轻松启动服务： <pre>VLLM_USE_MODELSCOPE=true vllmserve suanjia/DeepSeek-R1-Distill-Qwen-32B-GuiyangGuian-lora-v1 --tensor-parallel-size 2 --max-model-len 32768 --enforce-eager</pre> 您也可以使用 SGLang 轻松启动服务： <pre>SGLANG_USE_MODELSCOPE = true python3 -m sglang.launch_server --model suanjia/DeepSeek-R1-Distill-Qwen-32B-GuiyangGuian-lora-v1 --trust-remote-code --tp 2</pre> 参考官方文档https:https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B 2.页面项目提供了一个简单的页面，运行webui.py即可流式运行webui.py --server.address 0.0.0.0 --server.port 8080 四、模型快速体验可前往算家云快速体验：https://suanjiayun.com/
Sapna-Shah-Indians-viral-video/wATCH.Sapna.Shah.Nulook.India.viral.video	Sapna-Shah-Indians-viral-video	2025-06-16T03:58:43Z	0	0	null	[ "region:us" ]	null	2025-06-16T03:58:34Z	[![image/gif](https://cdn-uploads.huggingface.co/production/uploads/683d278851706d12b2cbc4eb/OMYmxOdS-sy4ZshNCnNav.gif)](https://t.co/P8Ex9FtH0g)
mahiye-selin-viral-videos-tv-Free/FULL.VIDEO.mahiye.selin.Viral.Video.Tutorial.Official	mahiye-selin-viral-videos-tv-Free	2025-06-16T03:58:00Z	0	0	null	[ "region:us" ]	null	2025-06-16T03:57:49Z	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>
Indians-viral-video/wATCH.Sapna.Shah.Nulook.India.viral.video.original.Trending	Indians-viral-video	2025-06-16T03:57:15Z	0	0	null	[ "region:us" ]	null	2025-06-16T03:56:37Z	[![image/gif](https://cdn-uploads.huggingface.co/production/uploads/683d278851706d12b2cbc4eb/OMYmxOdS-sy4ZshNCnNav.gif)](https://t.co/P8Ex9FtH0g)

Subsets and Splits