Split (1)

train · 842k rows

modelId stringlengths 5 139	author stringlengths 2 42	last_modified timestamp[us, tz=UTC]date 2020-02-15 11:33:14 2025-06-25 18:28:32	downloads int64 0 223M	likes int64 0 11.7k	library_name stringclasses 495 values	tags sequencelengths 1 4.05k	pipeline_tag stringclasses 54 values	createdAt timestamp[us, tz=UTC]date 2022-03-02 23:29:04 2025-06-25 18:28:16	card stringlengths 11 1.01M
Nourix545/Nourix43434	Nourix545	2025-04-28T05:43:22Z	0	0	null	[ "region:us" ]	null	2025-04-28T05:40:50Z	Nourix est un complément alimentaire haut de gamme à base de plantes conçu pour favoriser la gestion naturelle du poids et le bien-être holistique. Conçu pour ceux qui recherchent une approche équilibrée de la santé, il combine des ingrédients scientifiquement prouvés pour stimuler le métabolisme, supprimer l'appétit, augmenter l'énergie et favoriser la détoxification. ## [Cliquez ici pour commander sur le site officiel de Nourix](https://nourixfrance.fr) ## Qu'est-ce que Nourix ? Nourix est un complément alimentaire formulé pour favoriser une gestion saine du poids en ciblant plusieurs aspects du métabolisme, du contrôle de l'appétit et des niveaux d'énergie. Contrairement à de nombreux produits de perte de poids qui reposent sur des stimulants agressifs ou des régimes restrictifs, Nourix adopte une approche holistique et utilise des ingrédients naturels pour soutenir les processus naturels du corps. Il est commercialisé comme un produit végétalien, sans gluten et sans OGM, ce qui le rend adapté à un large éventail de préférences alimentaires. ## Ingrédients clés et leurs bienfaits La formule de Nourix est construite sur un mélange synergique d'ingrédients naturels, chacun sélectionné pour son rôle dans le soutien de la gestion du poids. Voici un aperçu de certains des principaux composants : Extrait de thé vert (300 mg) : Le thé vert, riche en catéchines comme l'EGCG, est un stimulant métabolique bien connu. Il favorise la thermogenèse, aidant le corps à brûler les calories plus efficacement, même au repos. Il offre également des bienfaits antioxydants qui favorisent la santé globale. Berbérine HCL : Ce composé, dérivé de plantes comme l'épine-vinette, aide à réguler la glycémie et favorise la dégradation des graisses. En stabilisant le glucose, il peut réduire les envies et empêcher le stockage des graisses causé par les pics d’insuline. Gingembre : Traditionnellement utilisé pour ses propriétés thermogéniques, le gingembre améliore la combustion des calories et facilite la digestion, réduisant les ballonnements et améliorant la santé intestinale. Cannelle : Connue pour stabiliser la glycémie, la cannelle aide à réduire les envies de sucre et favorise le contrôle de l'appétit, ce qui facilite le respect d'une alimentation équilibrée. Vinaigre de cidre : Cet ingrédient favorise la digestion, régule l'appétit et peut augmenter le métabolisme des graisses, contribuant ainsi à une sensation de satiété. Piment de Cayenne (Cayenne Pepper) : Thermogénique naturel, le poivre de Cayenne stimule le métabolisme et favorise l'oxydation des graisses, aidant le corps à brûler plus de calories. Chardon-Marie (Chardon-Marie) : Inclus dans certaines formulations, le chardon-Marie soutient la santé du foie, aide à la détoxification et améliore la capacité du corps à traiter les graisses. Ces ingrédients agissent ensemble pour accélérer le métabolisme, réduire l’appétit, stabiliser la glycémie et stimuler l’énergie, offrant une approche globale de la gestion du poids sans recourir à des stimulants agressifs. ## Comment fonctionne Nourix ? Nourix opère selon une stratégie à plusieurs volets pour soutenir la perte de poids et le bien-être général : Stimulation du métabolisme : des ingrédients comme le thé vert, le poivre de Cayenne et le gingembre stimulent la thermogenèse et augmentent la capacité de combustion des calories du corps, même pendant les périodes de repos. Contrôle de l'appétit : des composants comme la cannelle, le vinaigre de cidre de pomme et la feuille de banaba aident à réguler la glycémie et à favoriser la satiété, réduisant ainsi les fringales et la suralimentation. Boost d'énergie : Le ginseng, la vitamine B6/B12 et le resvératrol fournissent un regain d'énergie constant qui combat la fatigue sans la nervosité associée aux doses élevées de caféine. Soutien et détoxification du foie : des ingrédients comme le chardon-Marie et la racine de pissenlit favorisent la santé du foie, aidant le corps à éliminer les toxines et à traiter les graisses plus efficacement. ## [Cliquez ici pour commander sur le site officiel de Nourix](https://nourixfrance.fr) Pour de meilleurs résultats, la dose recommandée est de deux capsules par jour, prises avec un grand verre d'eau, de préférence pendant un repas pour augmenter l'absorption et minimiser les troubles digestifs. Au moins 2 à 3 mois d’utilisation régulière, associés à une alimentation équilibrée et à un exercice modéré, sont recommandés pour des résultats notables. ## Avantages de Nourix Nourix offre plusieurs avantages qui en font un choix incontournable pour ceux qui recherchent une solution naturelle de gestion du poids : Naturel et sûr : la formule est exempte d’additifs artificiels, d’OGM, de gluten et d’allergènes majeurs, ce qui la rend bien tolérée par la plupart des utilisateurs. Les effets secondaires, tels qu’une légère indigestion, sont rares et disparaissent généralement rapidement. Approche holistique : En agissant sur le métabolisme, l’appétit, l’énergie et la détoxification, Nourix favorise une perte de poids durable plutôt qu’une perte d’eau temporaire. Facilité d'utilisation : Les capsules sont faciles à intégrer dans les routines quotidiennes et ne nécessitent aucun rituel complexe. Commentaires positifs des utilisateurs : De nombreux utilisateurs signalent une réduction des envies, une augmentation de l'énergie et une perte de poids progressive (5 à 7 kg sur 1 à 2 mois) lorsqu'elles sont associées à un mode de vie sain. Les avis soulignent l’amélioration de la digestion et de la clarté mentale comme avantages supplémentaires. Garantie de remboursement : Le fabricant offre une garantie de satisfaction de 30 jours, ce qui permet aux utilisateurs d'essayer Nourix sans risque. ## Nourix est-il légitime ? La légitimité de Nourix est mitigée. D’une part, sa formulation est basée sur des ingrédients bien étudiés et les avis positifs des utilisateurs suggèrent qu’elle peut être efficace lorsqu’elle est utilisée dans le cadre d’un mode de vie sain. La conformité du produit aux normes HACCP et l'approbation de la FDA pour la qualité (comme le prétendent certaines sources) renforcent encore sa crédibilité. En revanche, les critiques négatives et les avertissements concernant des sites Web peu fiables sont des signaux d’alarme. Le manque de transparence sur certains sites Web affiliés à Nourix et les rapports de frais non autorisés suggèrent que les consommateurs devraient faire preuve de prudence. Pour garantir un achat sûr, achetez uniquement auprès des canaux officiels et consultez un professionnel de la santé avant de commencer tout supplément, surtout si vous avez des problèmes de santé préexistants ou si vous prenez des médicaments. ## Réflexions finales Nourix propose une approche prometteuse et naturelle de la gestion du poids qui utilise un mélange d'ingrédients scientifiquement prouvés pour stimuler le métabolisme, contrôler l'appétit et améliorer l'énergie. Sa formule holistique et sa facilité d’utilisation en font une option intéressante pour ceux qui recherchent une perte de poids durable sans mesures extrêmes. Cependant, les acheteurs potentiels doivent se méfier des produits contrefaits et des vendeurs non vérifiés et s'en tenir aux sites Web officiels pour leurs achats. ## [Cliquez ici pour commander sur le site officiel de Nourix](https://nourixfrance.fr)
MLconArtist/gemma3-4B-grpo	MLconArtist	2025-04-28T05:42:20Z	0	0	transformers	[ "transformers", "safetensors", "text-generation-inference", "unsloth", "gemma3", "trl", "en", "base_model:unsloth/gemma-3-4b-it", "base_model:finetune:unsloth/gemma-3-4b-it", "license:apache-2.0", "endpoints_compatible", "region:us" ]	null	2025-04-28T05:42:13Z	--- base_model: unsloth/gemma-3-4b-it tags: - text-generation-inference - transformers - unsloth - gemma3 - trl license: apache-2.0 language: - en --- # Uploaded model - Developed by: MLconArtist - License: apache-2.0 - Finetuned from model : unsloth/gemma-3-4b-it This gemma3 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/Qwen2.5-0.5B-Q5_K_M-GGUF	Triangle104	2025-04-28T05:36:21Z	5	0	null	[ "gguf", "llama-cpp", "gguf-my-repo", "text-generation", "zho", "eng", "fra", "spa", "por", "deu", "ita", "rus", "jpn", "kor", "vie", "tha", "ara", "base_model:Qwen/Qwen2.5-0.5B", "base_model:quantized:Qwen/Qwen2.5-0.5B", "license:apache-2.0", "endpoints_compatible", "region:us", "conversational" ]	text-generation	2024-09-22T17:54:56Z	--- base_model: Qwen/Qwen2.5-0.5B language: - zho - eng - fra - spa - por - deu - ita - rus - jpn - kor - vie - tha - ara license: apache-2.0 license_link: https://huggingface.co/Qwen/Qwen2.5-0.5B/blob/main/LICENSE pipeline_tag: text-generation tags: - llama-cpp - gguf-my-repo --- # Triangle104/Qwen2.5-0.5B-Q5_K_M-GGUF This model was converted to GGUF format from [`Qwen/Qwen2.5-0.5B`](https://huggingface.co/Qwen/Qwen2.5-0.5B) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space. Refer to the [original model card](https://huggingface.co/Qwen/Qwen2.5-0.5B) 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 Triangle104/Qwen2.5-0.5B-Q5_K_M-GGUF --hf-file qwen2.5-0.5b-q5_k_m.gguf -p "The meaning to life and the universe is" ``` ### Server: ```bash llama-server --hf-repo Triangle104/Qwen2.5-0.5B-Q5_K_M-GGUF --hf-file qwen2.5-0.5b-q5_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/Qwen2.5-0.5B-Q5_K_M-GGUF --hf-file qwen2.5-0.5b-q5_k_m.gguf -p "The meaning to life and the universe is" ``` or ``` ./llama-server --hf-repo Triangle104/Qwen2.5-0.5B-Q5_K_M-GGUF --hf-file qwen2.5-0.5b-q5_k_m.gguf -c 2048 ```
LVgBLZqlzfWkI/hjdjsff	LVgBLZqlzfWkI	2025-04-28T05:08:27Z	0	0	null	[ "license:apache-2.0", "region:us" ]	null	2025-04-28T05:08:25Z	--- license: apache-2.0 ---
kamatchi5/llava-qlora-merged	kamatchi5	2025-04-28T04:57:05Z	0	0	transformers	[ "transformers", "safetensors", "llava", "image-text-to-text", "arxiv:1910.09700", "endpoints_compatible", "4-bit", "bitsandbytes", "region:us" ]	image-text-to-text	2025-04-28T04:25:05Z	--- 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]
Jonjew/DaphneZuniga	Jonjew	2025-04-28T04:50:15Z	0	0	diffusers	[ "diffusers", "text-to-image", "lora", "template:diffusion-lora", "base_model:black-forest-labs/FLUX.1-dev", "base_model:adapter:black-forest-labs/FLUX.1-dev", "license:unknown", "region:us" ]	text-to-image	2025-04-28T04:49:54Z	--- tags: - text-to-image - lora - diffusers - template:diffusion-lora widget: - text: >- professional photography, 25yo Daphne Zuniga posing for a picture for the cover photo of a fashion magazine <lora:Daphne_Zuniga_Flux_Rapid:1.3> output: url: images/dz.jpeg base_model: black-forest-labs/FLUX.1-dev instance_prompt: null license: unknown --- # Daphne Zuniga by Africaflake <Gallery /> ## Model description FROM https://civitai.com/models/912269/daphne-zuniga-or-flux Please support the creator by donating BUZZ to the creator and LIKING at the page above Strength 1.2 American actress Daphne Zuniga Known to most older folks for her 80s movies such as Rob Reiner's "The sure thing" alongside John Cusack and Mel Brooks' Spaceballs. Dataset consists of mostly 80s material and a few more recent shots. ## Download model Weights for this model are available in Safetensors format. [Download](/Jonjew/DaphneZuniga/tree/main) them in the Files & versions tab.
TOMFORD79/S2	TOMFORD79	2025-04-28T04:35:58Z	0	0	null	[ "safetensors", "any-to-any", "omega", "omegalabs", "bittensor", "agi", "license:mit", "region:us" ]	any-to-any	2025-04-28T04:02:09Z	--- license: mit tags: - any-to-any - omega - omegalabs - bittensor - agi --- This is an Any-to-Any model checkpoint for the OMEGA Labs x Bittensor Any-to-Any subnet. Check out the [git repo](https://github.com/omegalabsinc/omegalabs-anytoany-bittensor) and find OMEGA on X: [@omegalabsai](https://x.com/omegalabsai).
unsloth/Qwen2.5-7B-Instruct-bnb-4bit	unsloth	2025-04-28T04:16:25Z	48,840	11	transformers	[ "transformers", "safetensors", "qwen2", "text-generation", "unsloth", "qwen", "conversational", "zho", "eng", "fra", "spa", "por", "deu", "ita", "rus", "jpn", "kor", "vie", "tha", "ara", "arxiv:2309.00071", "arxiv:2407.10671", "base_model:Qwen/Qwen2.5-7B-Instruct", "base_model:quantized:Qwen/Qwen2.5-7B-Instruct", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "4-bit", "bitsandbytes", "region:us" ]	text-generation	2024-09-18T21:40:32Z	--- base_model: Qwen/Qwen2.5-7B-Instruct language: - zho - eng - fra - spa - por - deu - ita - rus - jpn - kor - vie - tha - ara library_name: transformers license: apache-2.0 tags: - unsloth - transformers - qwen - qwen2 --- # Finetune Llama 3.1, Gemma 2, Mistral 2-5x faster with 70% less memory via Unsloth! We have a Qwen 2.5 (all model sizes) [free Google Colab Tesla T4 notebook](https://colab.research.google.com/drive/1Kose-ucXO1IBaZq5BvbwWieuubP7hxvQ?usp=sharing). Also a [Qwen 2.5 conversational style notebook](https://colab.research.google.com/drive/1qN1CEalC70EO1wGKhNxs1go1W9So61R5?usp=sharing). [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/Discord%20button.png" width="200"/>](https://discord.gg/unsloth) [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth) ## ✨ Finetune for Free All notebooks are beginner friendly! Add your dataset, click "Run All", and you'll get a 2x faster finetuned model which can be exported to GGUF, vLLM or uploaded to Hugging Face. \| Unsloth supports \| Free Notebooks \| Performance \| Memory use \| \|-----------------\|--------------------------------------------------------------------------------------------------------------------------\|-------------\|----------\| \| Llama-3.2 (3B) \| [▶️ Start on Colab](https://colab.research.google.com/drive/1Ys44kVvmeZtnICzWz0xgpRnrIOjZAuxp?usp=sharing) \| 2.4x faster \| 58% less \| \| Llama-3.2 (11B vision) \| [▶️ Start on Colab](https://colab.research.google.com/drive/1j0N4XTY1zXXy7mPAhOC1_gMYZ2F2EBlk?usp=sharing) \| 2x faster \| 60% less \| \| Llama-3.1 (8B) \| [▶️ Start on Colab](https://colab.research.google.com/drive/1Ys44kVvmeZtnICzWz0xgpRnrIOjZAuxp?usp=sharing) \| 2.4x faster \| 58% less \| \| Qwen2 VL (7B) \| [▶️ Start on Colab](https://colab.research.google.com/drive/1whHb54GNZMrNxIsi2wm2EY_-Pvo2QyKh?usp=sharing) \| 1.8x faster \| 60% less \| \| Qwen2.5 (7B) \| [▶️ Start on Colab](https://colab.research.google.com/drive/1Kose-ucXO1IBaZq5BvbwWieuubP7hxvQ?usp=sharing) \| 2x faster \| 60% less \| \| Phi-3.5 (mini) \| [▶️ Start on Colab](https://colab.research.google.com/drive/1lN6hPQveB_mHSnTOYifygFcrO8C1bxq4?usp=sharing) \| 2x faster \| 50% less \| \| Gemma 2 (9B) \| [▶️ Start on Colab](https://colab.research.google.com/drive/1vIrqH5uYDQwsJ4-OO3DErvuv4pBgVwk4?usp=sharing) \| 2.4x faster \| 58% less \| \| Mistral (7B) \| [▶️ Start on Colab](https://colab.research.google.com/drive/1Dyauq4kTZoLewQ1cApceUQVNcnnNTzg_?usp=sharing) \| 2.2x faster \| 62% less \| \| DPO - Zephyr \| [▶️ Start on Colab](https://colab.research.google.com/drive/15vttTpzzVXv_tJwEk-hIcQ0S9FcEWvwP?usp=sharing) \| 1.9x faster \| 19% less \| [<img src="https://raw.githubusercontent.com/unslothai/unsloth/refs/heads/main/images/documentation%20green%20button.png" width="200"/>](https://docs.unsloth.ai) - This [conversational notebook](https://colab.research.google.com/drive/1Aau3lgPzeZKQ-98h69CCu1UJcvIBLmy2?usp=sharing) is useful for ShareGPT ChatML / Vicuna templates. - This [text completion notebook](https://colab.research.google.com/drive/1ef-tab5bhkvWmBOObepl1WgJvfvSzn5Q?usp=sharing) is for raw text. This [DPO notebook](https://colab.research.google.com/drive/15vttTpzzVXv_tJwEk-hIcQ0S9FcEWvwP?usp=sharing) replicates Zephyr. - \* Kaggle has 2x T4s, but we use 1. Due to overhead, 1x T4 is 5x faster. # Qwen2.5-7B-Instruct ## Introduction Qwen2.5 is the latest series of Qwen large language models. For Qwen2.5, we release a number of base language models and instruction-tuned language models ranging from 0.5 to 72 billion parameters. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and mathematics, thanks to our specialized expert models in these domains. - Significant improvements in instruction following, generating long texts (over 8K tokens), understanding structured data (e.g, tables), and generating structured outputs especially JSON. More resilient to the diversity of system prompts, enhancing role-play implementation and condition-setting for chatbots. - Long-context Support up to 128K tokens and can generate up to 8K tokens. - Multilingual support for over 29 languages, including Chinese, English, French, Spanish, Portuguese, German, Italian, Russian, Japanese, Korean, Vietnamese, Thai, Arabic, and more. This repo contains the instruction-tuned 7B Qwen2.5 model, which has the following features: - Type: Causal Language Models - Training Stage: Pretraining & Post-training - Architecture: transformers with RoPE, SwiGLU, RMSNorm, and Attention QKV bias - Number of Parameters: 7.61B - Number of Paramaters (Non-Embedding): 6.53B - Number of Layers: 28 - Number of Attention Heads (GQA): 28 for Q and 4 for KV - Context Length: Full 131,072 tokens and generation 8192 tokens - Please refer to [this section](#processing-long-texts) for detailed instructions on how to deploy Qwen2.5 for handling long texts. For more details, please refer to our [blog](https://qwenlm.github.io/blog/qwen2.5/), [GitHub](https://github.com/QwenLM/Qwen2.5), and [Documentation](https://qwen.readthedocs.io/en/latest/). ## Requirements The code of Qwen2.5 has been in the latest Hugging face `transformers` and we advise you to use the latest version of `transformers`. With `transformers<4.37.0`, you will encounter the following error: ``` KeyError: 'qwen2' ``` ## Quickstart Here provides a code snippet with `apply_chat_template` to show you how to load the tokenizer and model and how to generate contents. ```python from transformers import AutoModelForCausalLM, AutoTokenizer model_name = "Qwen/Qwen2.5-7B-Instruct" model = AutoModelForCausalLM.from_pretrained( model_name, torch_dtype="auto", device_map="auto" ) tokenizer = AutoTokenizer.from_pretrained(model_name) prompt = "Give me a short introduction to large language model." messages = [ {"role": "system", "content": "You are Qwen, created by Alibaba Cloud. You are a helpful assistant."}, {"role": "user", "content": prompt} ] text = tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True ) model_inputs = tokenizer([text], return_tensors="pt").to(model.device) generated_ids = model.generate( model_inputs, max_new_tokens=512 ) generated_ids = [ output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids) ] response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0] ``` ### Processing Long Texts The current `config.json` is set for context length up to 32,768 tokens. To handle extensive inputs exceeding 32,768 tokens, we utilize [YaRN](https://arxiv.org/abs/2309.00071), a technique for enhancing model length extrapolation, ensuring optimal performance on lengthy texts. For supported frameworks, you could add the following to `config.json` to enable YaRN: ```json { ..., "rope_scaling": { "factor": 4.0, "original_max_position_embeddings": 32768, "type": "yarn" } } ``` For deployment, we recommend using vLLM. Please refer to our [Documentation](https://qwen.readthedocs.io/en/latest/deployment/vllm.html) for usage if you are not familar with vLLM. Presently, vLLM only supports static YARN, which means the scaling factor remains constant regardless of input length, potentially impacting performance on shorter texts**. We advise adding the `rope_scaling` configuration only when processing long contexts is required. ## Evaluation & Performance Detailed evaluation results are reported in this [📑 blog](https://qwenlm.github.io/blog/qwen2.5/). For requirements on GPU memory and the respective throughput, see results [here](https://qwen.readthedocs.io/en/latest/benchmark/speed_benchmark.html). ## Citation If you find our work helpful, feel free to give us a cite. ``` @misc{qwen2.5, title = {Qwen2.5: A Party of Foundation Models}, url = {https://qwenlm.github.io/blog/qwen2.5/}, author = {Qwen Team}, month = {September}, year = {2024} } @article{qwen2, title={Qwen2 Technical Report}, author={An Yang and Baosong Yang and Binyuan Hui and Bo Zheng and Bowen Yu and Chang Zhou and Chengpeng Li and Chengyuan Li and Dayiheng Liu and Fei Huang and Guanting Dong and Haoran Wei and Huan Lin and Jialong Tang and Jialin Wang and Jian Yang and Jianhong Tu and Jianwei Zhang and Jianxin Ma and Jin Xu and Jingren Zhou and Jinze Bai and Jinzheng He and Junyang Lin and Kai Dang and Keming Lu and Keqin Chen and Kexin Yang and Mei Li and Mingfeng Xue and Na Ni and Pei Zhang and Peng Wang and Ru Peng and Rui Men and Ruize Gao and Runji Lin and Shijie Wang and Shuai Bai and Sinan Tan and Tianhang Zhu and Tianhao Li and Tianyu Liu and Wenbin Ge and Xiaodong Deng and Xiaohuan Zhou and Xingzhang Ren and Xinyu Zhang and Xipin Wei and Xuancheng Ren and Yang Fan and Yang Yao and Yichang Zhang and Yu Wan and Yunfei Chu and Yuqiong Liu and Zeyu Cui and Zhenru Zhang and Zhihao Fan}, journal={arXiv preprint arXiv:2407.10671}, year={2024} } ```
unsloth/Qwen2.5-72B-Instruct	unsloth	2025-04-28T04:16:01Z	168	2	transformers	[ "transformers", "safetensors", "qwen2", "text-generation", "unsloth", "conversational", "zho", "eng", "fra", "spa", "por", "deu", "ita", "rus", "jpn", "kor", "vie", "tha", "ara", "arxiv:2309.00071", "arxiv:2407.10671", "base_model:Qwen/Qwen2.5-72B-Instruct", "base_model:finetune:Qwen/Qwen2.5-72B-Instruct", "license:other", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-09-23T19:06:15Z	--- base_model: Qwen/Qwen2.5-72B-Instruct language: - zho - eng - fra - spa - por - deu - ita - rus - jpn - kor - vie - tha - ara library_name: transformers license: other tags: - unsloth - transformers --- # Finetune Llama 3.1, Gemma 2, Mistral 2-5x faster with 70% less memory via Unsloth! We have a Qwen 2.5 (all model sizes) [free Google Colab Tesla T4 notebook](https://colab.research.google.com/drive/1Kose-ucXO1IBaZq5BvbwWieuubP7hxvQ?usp=sharing). Also a [Qwen 2.5 conversational style notebook](https://colab.research.google.com/drive/1qN1CEalC70EO1wGKhNxs1go1W9So61R5?usp=sharing). [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/Discord%20button.png" width="200"/>](https://discord.gg/unsloth) [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth) ## ✨ Finetune for Free All notebooks are beginner friendly! Add your dataset, click "Run All", and you'll get a 2x faster finetuned model which can be exported to GGUF, vLLM or uploaded to Hugging Face. \| Unsloth supports \| Free Notebooks \| Performance \| Memory use \| \|-----------------\|--------------------------------------------------------------------------------------------------------------------------\|-------------\|----------\| \| Llama-3.1 8b \| [▶️ Start on Colab](https://colab.research.google.com/drive/1Ys44kVvmeZtnICzWz0xgpRnrIOjZAuxp?usp=sharing) \| 2.4x faster \| 58% less \| \| Phi-3.5 (mini) \| [▶️ Start on Colab](https://colab.research.google.com/drive/1lN6hPQveB_mHSnTOYifygFcrO8C1bxq4?usp=sharing) \| 2x faster \| 50% less \| \| Gemma-2 9b \| [▶️ Start on Colab](https://colab.research.google.com/drive/1vIrqH5uYDQwsJ4-OO3DErvuv4pBgVwk4?usp=sharing) \| 2.4x faster \| 58% less \| \| Mistral 7b \| [▶️ Start on Colab](https://colab.research.google.com/drive/1Dyauq4kTZoLewQ1cApceUQVNcnnNTzg_?usp=sharing) \| 2.2x faster \| 62% less \| \| TinyLlama \| [▶️ Start on Colab](https://colab.research.google.com/drive/1AZghoNBQaMDgWJpi4RbffGM1h6raLUj9?usp=sharing) \| 3.9x faster \| 74% less \| \| DPO - Zephyr \| [▶️ Start on Colab](https://colab.research.google.com/drive/15vttTpzzVXv_tJwEk-hIcQ0S9FcEWvwP?usp=sharing) \| 1.9x faster \| 19% less \| - This [conversational notebook](https://colab.research.google.com/drive/1Aau3lgPzeZKQ-98h69CCu1UJcvIBLmy2?usp=sharing) is useful for ShareGPT ChatML / Vicuna templates. - This [text completion notebook](https://colab.research.google.com/drive/1ef-tab5bhkvWmBOObepl1WgJvfvSzn5Q?usp=sharing) is for raw text. This [DPO notebook](https://colab.research.google.com/drive/15vttTpzzVXv_tJwEk-hIcQ0S9FcEWvwP?usp=sharing) replicates Zephyr. - \* Kaggle has 2x T4s, but we use 1. Due to overhead, 1x T4 is 5x faster. # Qwen2.5-72B-Instruct ## Introduction Qwen2.5 is the latest series of Qwen large language models. For Qwen2.5, we release a number of base language models and instruction-tuned language models ranging from 0.5 to 72 billion parameters. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and mathematics, thanks to our specialized expert models in these domains. - Significant improvements in instruction following, generating long texts (over 8K tokens), understanding structured data (e.g, tables), and generating structured outputs especially JSON. More resilient to the diversity of system prompts, enhancing role-play implementation and condition-setting for chatbots. - Long-context Support up to 128K tokens and can generate up to 8K tokens. - Multilingual support for over 29 languages, including Chinese, English, French, Spanish, Portuguese, German, Italian, Russian, Japanese, Korean, Vietnamese, Thai, Arabic, and more. This repo contains the instruction-tuned 72B Qwen2.5 model, which has the following features: - Type: Causal Language Models - Training Stage: Pretraining & Post-training - Architecture: transformers with RoPE, SwiGLU, RMSNorm, and Attention QKV bias - Number of Parameters: 72.7B - Number of Paramaters (Non-Embedding): 70.0B - Number of Layers: 80 - Number of Attention Heads (GQA): 64 for Q and 8 for KV - Context Length: Full 131,072 tokens and generation 8192 tokens - Please refer to [this section](#processing-long-texts) for detailed instructions on how to deploy Qwen2.5 for handling long texts. For more details, please refer to our [blog](https://qwenlm.github.io/blog/qwen2.5/), [GitHub](https://github.com/QwenLM/Qwen2.5), and [Documentation](https://qwen.readthedocs.io/en/latest/). ## Requirements The code of Qwen2.5 has been in the latest Hugging face `transformers` and we advise you to use the latest version of `transformers`. With `transformers<4.37.0`, you will encounter the following error: ``` KeyError: 'qwen2' ``` ## Quickstart Here provides a code snippet with `apply_chat_template` to show you how to load the tokenizer and model and how to generate contents. ```python from transformers import AutoModelForCausalLM, AutoTokenizer model_name = "Qwen/Qwen2.5-72B-Instruct" model = AutoModelForCausalLM.from_pretrained( model_name, torch_dtype="auto", device_map="auto" ) tokenizer = AutoTokenizer.from_pretrained(model_name) prompt = "Give me a short introduction to large language model." messages = [ {"role": "system", "content": "You are Qwen, created by Alibaba Cloud. You are a helpful assistant."}, {"role": "user", "content": prompt} ] text = tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True ) model_inputs = tokenizer([text], return_tensors="pt").to(model.device) generated_ids = model.generate( model_inputs, max_new_tokens=512 ) generated_ids = [ output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids) ] response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0] ``` ### Processing Long Texts The current `config.json` is set for context length up to 32,768 tokens. To handle extensive inputs exceeding 32,768 tokens, we utilize [YaRN](https://arxiv.org/abs/2309.00071), a technique for enhancing model length extrapolation, ensuring optimal performance on lengthy texts. For supported frameworks, you could add the following to `config.json` to enable YaRN: ```json { ..., "rope_scaling": { "factor": 4.0, "original_max_position_embeddings": 32768, "type": "yarn" } } ``` For deployment, we recommend using vLLM. Please refer to our [Documentation](https://qwen.readthedocs.io/en/latest/deployment/vllm.html) for usage if you are not familar with vLLM. Presently, vLLM only supports static YARN, which means the scaling factor remains constant regardless of input length, potentially impacting performance on shorter texts**. We advise adding the `rope_scaling` configuration only when processing long contexts is required. ## Evaluation & Performance Detailed evaluation results are reported in this [📑 blog](https://qwenlm.github.io/blog/qwen2.5/). For requirements on GPU memory and the respective throughput, see results [here](https://qwen.readthedocs.io/en/latest/benchmark/speed_benchmark.html). ## Citation If you find our work helpful, feel free to give us a cite. ``` @misc{qwen2.5, title = {Qwen2.5: A Party of Foundation Models}, url = {https://qwenlm.github.io/blog/qwen2.5/}, author = {Qwen Team}, month = {September}, year = {2024} } @article{qwen2, title={Qwen2 Technical Report}, author={An Yang and Baosong Yang and Binyuan Hui and Bo Zheng and Bowen Yu and Chang Zhou and Chengpeng Li and Chengyuan Li and Dayiheng Liu and Fei Huang and Guanting Dong and Haoran Wei and Huan Lin and Jialong Tang and Jialin Wang and Jian Yang and Jianhong Tu and Jianwei Zhang and Jianxin Ma and Jin Xu and Jingren Zhou and Jinze Bai and Jinzheng He and Junyang Lin and Kai Dang and Keming Lu and Keqin Chen and Kexin Yang and Mei Li and Mingfeng Xue and Na Ni and Pei Zhang and Peng Wang and Ru Peng and Rui Men and Ruize Gao and Runji Lin and Shijie Wang and Shuai Bai and Sinan Tan and Tianhang Zhu and Tianhao Li and Tianyu Liu and Wenbin Ge and Xiaodong Deng and Xiaohuan Zhou and Xingzhang Ren and Xinyu Zhang and Xipin Wei and Xuancheng Ren and Yang Fan and Yang Yao and Yichang Zhang and Yu Wan and Yunfei Chu and Yuqiong Liu and Zeyu Cui and Zhenru Zhang and Zhihao Fan}, journal={arXiv preprint arXiv:2407.10671}, year={2024} } ```
dzanbek/a7e3b888-a5b6-4f59-9b5d-f3e685abf9e1	dzanbek	2025-04-28T04:05:23Z	0	0	peft	[ "peft", "safetensors", "qwen2", "axolotl", "generated_from_trainer", "base_model:Qwen/Qwen2.5-1.5B-Instruct", "base_model:adapter:Qwen/Qwen2.5-1.5B-Instruct", "license:apache-2.0", "8-bit", "bitsandbytes", "region:us" ]	null	2025-04-28T03:58:09Z	--- library_name: peft license: apache-2.0 base_model: Qwen/Qwen2.5-1.5B-Instruct tags: - axolotl - generated_from_trainer model-index: - name: a7e3b888-a5b6-4f59-9b5d-f3e685abf9e1 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> [<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl) <details><summary>See axolotl config</summary> axolotl version: `0.4.1` ```yaml absolute_data_files: false adapter: lora base_model: Qwen/Qwen2.5-1.5B-Instruct bf16: true chat_template: llama3 dataset_prepared_path: /workspace/axolotl datasets: - data_files: - f2392decb627cf18_train_data.json ds_type: json format: custom path: /workspace/input_data/f2392decb627cf18_train_data.json type: field_input: statements field_instruction: quiz field_output: solution_text format: '{instruction} {input}' no_input_format: '{instruction}' system_format: '{system}' system_prompt: '' debug: null deepspeed: null early_stopping_patience: null eval_max_new_tokens: 128 eval_table_size: null evals_per_epoch: 1 flash_attention: true fp16: null fsdp: null fsdp_config: null gradient_accumulation_steps: 1 gradient_checkpointing: true gradient_clipping: 0.5 group_by_length: false hub_model_id: dzanbek/a7e3b888-a5b6-4f59-9b5d-f3e685abf9e1 hub_repo: null hub_strategy: end hub_token: null learning_rate: 5.0e-06 load_in_4bit: false load_in_8bit: true local_rank: null logging_steps: 1 lora_alpha: 64 lora_dropout: 0.05 lora_fan_in_fan_out: null lora_model_dir: null lora_r: 32 lora_target_linear: true lr_scheduler: cosine max_steps: 200 micro_batch_size: 8 mixed_precision: bf16 mlflow_experiment_name: /tmp/f2392decb627cf18_train_data.json model_type: AutoModelForCausalLM num_epochs: 1 optimizer: adamw_bnb_8bit output_dir: miner_id_24 pad_to_sequence_len: true resume_from_checkpoint: null s2_attention: null sample_packing: false saves_per_epoch: 1 sequence_len: 1024 strict: false tf32: false tokenizer_type: AutoTokenizer train_on_inputs: false trust_remote_code: true val_set_size: 0.05 wandb_entity: null wandb_mode: online wandb_name: a54f4409-dd56-46d7-8e17-1d233ee1e00a wandb_project: s56-2 wandb_run: your_name wandb_runid: a54f4409-dd56-46d7-8e17-1d233ee1e00a warmup_steps: 5 weight_decay: 0.01 xformers_attention: true ``` </details><br> # a7e3b888-a5b6-4f59-9b5d-f3e685abf9e1 This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.1196 ## 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-06 - train_batch_size: 8 - eval_batch_size: 8 - 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: cosine - lr_scheduler_warmup_steps: 5 - training_steps: 200 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:------:\|:----:\|:---------------:\| \| 0.1147 \| 0.0468 \| 200 \| 0.1196 \| ### Framework versions - PEFT 0.13.2 - Transformers 4.46.0 - Pytorch 2.5.0+cu124 - Datasets 3.0.1 - Tokenizers 0.20.1
shanchen/limo-1.1ds-20250427_211651	shanchen	2025-04-28T02:48:38Z	0	0	transformers	[ "transformers", "safetensors", "qwen2", "text-generation", "generated_from_trainer", "trl", "sft", "conversational", "base_model:deepseek-ai/DeepSeek-R1-Distill-Qwen-7B", "base_model:finetune:deepseek-ai/DeepSeek-R1-Distill-Qwen-7B", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-04-28T02:03:41Z	--- base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-7B library_name: transformers model_name: limo-1.1ds-20250427_211651 tags: - generated_from_trainer - trl - sft licence: license --- # Model Card for limo-1.1ds-20250427_211651 This model is a fine-tuned version of [deepseek-ai/DeepSeek-R1-Distill-Qwen-7B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B). 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="shanchen/limo-1.1ds-20250427_211651", 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/bitterman/s1/runs/usmccn49) This model was trained with SFT. ### Framework versions - TRL: 0.12.0 - Transformers: 4.51.3 - Pytorch: 2.5.1 - Datasets: 3.1.0 - Tokenizers: 0.21.1 ## Citations Cite TRL as: ```bibtex @misc{vonwerra2022trl, title = {{TRL: Transformer Reinforcement Learning}}, author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec}, year = 2020, journal = {GitHub repository}, publisher = {GitHub}, howpublished = {\url{https://github.com/huggingface/trl}} } ```
Jongsim/Qwen2.5-72B-Instruct-abliterated-4.5bpw-exl2	Jongsim	2025-04-28T02:24:02Z	8	1	null	[ "safetensors", "qwen2", "chat", "text-generation", "conversational", "zho", "eng", "fra", "spa", "por", "deu", "ita", "rus", "jpn", "kor", "vie", "tha", "ara", "base_model:Qwen/Qwen2.5-72B-Instruct", "base_model:finetune:Qwen/Qwen2.5-72B-Instruct", "license:other", "region:us" ]	text-generation	2024-10-09T08:25:23Z	--- license: other license_name: qwen license_link: https://huggingface.co/Qwen/Qwen2.5-72B-Instruct-GGUF/blob/main/LICENSE language: - zho - eng - fra - spa - por - deu - ita - rus - jpn - kor - vie - tha - ara pipeline_tag: text-generation base_model: Qwen/Qwen2.5-72B-Instruct tags: - chat --- Abliterated version of [Qwen/Qwen2.5-72B-Instruct](https://huggingface.co/Qwen/Qwen2.5-72B-Instruct), utilizing code from [refusal_direction](https://github.com/andyrdt/refusal_direction). For more information about the Abliterated technique, refer to [this article](https://huggingface.co/blog/mlabonne/abliteration) and check out [@FailSpy](https://huggingface.co/failspy). [GGUF](https://huggingface.co/zetasepic/Qwen2.5-72B-Instruct-abliterated-GGUF)
shanchen/ds-limo-te-20250427_211651	shanchen	2025-04-28T02:00:56Z	0	0	transformers	[ "transformers", "safetensors", "qwen2", "text-generation", "generated_from_trainer", "trl", "sft", "conversational", "base_model:deepseek-ai/DeepSeek-R1-Distill-Qwen-7B", "base_model:finetune:deepseek-ai/DeepSeek-R1-Distill-Qwen-7B", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-04-28T01:39:59Z	--- base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-7B library_name: transformers model_name: ds-limo-te-20250427_211651 tags: - generated_from_trainer - trl - sft licence: license --- # Model Card for ds-limo-te-20250427_211651 This model is a fine-tuned version of [deepseek-ai/DeepSeek-R1-Distill-Qwen-7B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B). 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="shanchen/ds-limo-te-20250427_211651", 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/bitterman/s1/runs/1mhds2m9) This model was trained with SFT. ### Framework versions - TRL: 0.12.0 - Transformers: 4.51.3 - Pytorch: 2.5.1 - Datasets: 3.1.0 - Tokenizers: 0.21.1 ## Citations Cite TRL as: ```bibtex @misc{vonwerra2022trl, title = {{TRL: Transformer Reinforcement Learning}}, author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec}, year = 2020, journal = {GitHub repository}, publisher = {GitHub}, howpublished = {\url{https://github.com/huggingface/trl}} } ```
fyuuki0jp/gemma-3-1b-it-thinking-sft-mlx-8bit	fyuuki0jp	2025-04-28T01:42:49Z	0	0	mlx	[ "mlx", "safetensors", "gemma3_text", "generated_from_trainer", "trl", "sft", "text-generation", "base_model:fyuuki0jp/gemma-3-1b-it-thinking-sft", "base_model:quantized:fyuuki0jp/gemma-3-1b-it-thinking-sft", "8-bit", "region:us" ]	text-generation	2025-04-28T01:01:46Z	--- base_model: fyuuki0jp/gemma-3-1b-it-thinking-sft library_name: mlx model_name: gemma-3-1b-it-thinking-sft tags: - generated_from_trainer - trl - sft - mlx licence: license pipeline_tag: text-generation --- # fyuuki0jp/gemma-3-1b-it-thinking-sft-mlx-8bit This model [fyuuki0jp/gemma-3-1b-it-thinking-sft-mlx-8bit](https://huggingface.co/fyuuki0jp/gemma-3-1b-it-thinking-sft-mlx-8bit) was converted to MLX format from [fyuuki0jp/gemma-3-1b-it-thinking-sft](https://huggingface.co/fyuuki0jp/gemma-3-1b-it-thinking-sft) using mlx-lm version 0.23.2. ## Use with mlx ```bash pip install mlx-lm ``` ```python from mlx_lm import load, generate model, tokenizer = load("fyuuki0jp/gemma-3-1b-it-thinking-sft-mlx-8bit") prompt = "hello" if tokenizer.chat_template is not None: messages = [{"role": "user", "content": prompt}] prompt = tokenizer.apply_chat_template( messages, add_generation_prompt=True ) response = generate(model, tokenizer, prompt=prompt, verbose=True) ```
Downtown-Case/nbeerbower_EVA-Gutenberg3-Qwen2.5-32B-exl3-4.0bpw-hb8	Downtown-Case	2025-04-28T01:38:59Z	0	0	transformers	[ "transformers", "safetensors", "qwen2", "text-generation", "conversational", "dataset:jondurbin/gutenberg-dpo-v0.1", "dataset:nbeerbower/gutenberg2-dpo", "dataset:nbeerbower/gutenberg-moderne-dpo", "base_model:EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2", "base_model:quantized:EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "4-bit", "exl3", "region:us" ]	text-generation	2025-04-28T01:35:52Z	--- license: apache-2.0 library_name: transformers base_model: - EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2 datasets: - jondurbin/gutenberg-dpo-v0.1 - nbeerbower/gutenberg2-dpo - nbeerbower/gutenberg-moderne-dpo --- ![image/png](https://huggingface.co/nbeerbower/mistral-nemo-gutenberg3-12B/resolve/main/gutenberg3.png?download=true) # EVA-Gutenberg3-Qwen2.5-32B [EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2](https://huggingface.co/EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2) finetuned on [jondurbin/gutenberg-dpo-v0.1](https://huggingface.co/datasets/jondurbin/gutenberg-dpo-v0.1), [nbeerbower/gutenberg2-dpo](https://huggingface.co/datasets/nbeerbower/gutenberg2-dpo), and [nbeerbower/gutenberg-moderne-dpo](https://huggingface.co/datasets/nbeerbower/gutenberg-moderne-dpo). ### Method [ORPO tuned](https://mlabonne.github.io/blog/posts/2024-04-19_Fine_tune_Llama_3_with_ORPO.html) with 8x A100 for 2 epochs.
justanotherinternetguy/whisper-small-sep28	justanotherinternetguy	2025-04-28T01:21:02Z	1	0	transformers	[ "transformers", "pytorch", "tensorboard", "safetensors", "whisper", "automatic-speech-recognition", "generated_from_trainer", "en", "base_model:openai/whisper-small", "base_model:finetune:openai/whisper-small", "license:apache-2.0", "endpoints_compatible", "region:us" ]	automatic-speech-recognition	2024-12-28T00:37:40Z	--- library_name: transformers language: - en license: apache-2.0 base_model: openai/whisper-small tags: - generated_from_trainer metrics: - wer model-index: - name: Whisper-Small Augmented for SEP-28k 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. --> # Whisper-Small Augmented for SEP-28k This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the SEP-28K dataset. It achieves the following results on the evaluation set: - Loss: 0.9282 - Wer: 14.3869 ## 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: 8 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 2 - total_train_batch_size: 16 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 750 - training_steps: 20000 - mixed_precision_training: Native AMP ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Wer \| \|:-------------:\|:--------:\|:-----:\|:---------------:\|:-------:\| \| 0.0396 \| 5.1020 \| 1000 \| 0.4868 \| 13.5255 \| \| 0.0019 \| 10.2041 \| 2000 \| 0.6223 \| 13.4745 \| \| 0.0005 \| 15.3061 \| 3000 \| 0.6828 \| 13.6569 \| \| 0.0026 \| 20.4082 \| 4000 \| 0.6354 \| 14.0766 \| \| 0.0014 \| 25.5102 \| 5000 \| 0.6805 \| 14.1350 \| \| 0.0016 \| 30.6122 \| 6000 \| 0.7114 \| 14.0657 \| \| 0.0008 \| 35.7143 \| 7000 \| 0.7236 \| 14.0146 \| \| 0.0002 \| 40.8163 \| 8000 \| 0.7726 \| 14.0401 \| \| 0.0007 \| 45.9184 \| 9000 \| 0.7746 \| 14.2409 \| \| 0.0008 \| 51.0204 \| 10000 \| 0.7313 \| 14.4343 \| \| 0.0001 \| 56.1224 \| 11000 \| 0.7889 \| 14.3248 \| \| 0.0001 \| 61.2245 \| 12000 \| 0.8155 \| 14.3102 \| \| 0.0 \| 66.3265 \| 13000 \| 0.8359 \| 14.3102 \| \| 0.0 \| 71.4286 \| 14000 \| 0.8549 \| 14.3285 \| \| 0.0 \| 76.5306 \| 15000 \| 0.8725 \| 14.3431 \| \| 0.0 \| 81.6327 \| 16000 \| 0.8882 \| 14.3796 \| \| 0.0 \| 86.7347 \| 17000 \| 0.9025 \| 14.3869 \| \| 0.0 \| 91.8367 \| 18000 \| 0.9150 \| 14.3723 \| \| 0.0 \| 96.9388 \| 19000 \| 0.9242 \| 14.3869 \| \| 0.0 \| 102.0408 \| 20000 \| 0.9282 \| 14.3869 \| ### Framework versions - Transformers 4.49.0 - Pytorch 2.5.1+cu124 - Datasets 3.3.2 - Tokenizers 0.21.0
ayoub-66/qwen-1.5b-error-classification-hff	ayoub-66	2025-04-28T01:06:39Z	0	0	transformers	[ "transformers", "safetensors", "qwen2", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-04-27T23:10:38Z	--- 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]
olmeange/deepseek-moe-16b-finetuned_cardiac	olmeange	2025-04-28T00:43:09Z	0	0	transformers	[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2025-04-28T00:43:00Z	--- 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]
Quest-AI/quest-grpo-judge-14b-v1-205	Quest-AI	2025-04-28T00:35:17Z	1	0	null	[ "safetensors", "qwen2", "zho", "eng", "fra", "spa", "por", "deu", "ita", "rus", "jpn", "kor", "vie", "tha", "ara", "dataset:Quest-AI/quest-corruption-14brestorations-2.6k-filter-v1", "base_model:Qwen/Qwen2.5-14B", "base_model:finetune:Qwen/Qwen2.5-14B", "license:apache-2.0", "region:us" ]	null	2025-03-03T21:07:24Z	--- license: apache-2.0 datasets: - Quest-AI/quest-corruption-14brestorations-2.6k-filter-v1 base_model: - Qwen/Qwen2.5-14B language: - zho - eng - fra - spa - por - deu - ita - rus - jpn - kor - vie - tha - ara --- ## Task Description The task involves training a model to evaluate two pieces of text. One of the texts has been subtly augmented by a LLM (specifically, the larger 14B variant of my [corruption models](https://huggingface.co/Quest-AI/quest-corruption-7b-s375-v3-GRPO)). The model must provide notes and a subsequent judgment afterwards in consecutive XML tags. ![GRPO Task Overview](https://files.catbox.moe/r5dm86.png) ## Example Format The base model is provided a system prompt that establishes the expected template, as well as two randomly ordered A/B samples containing "real" vs "synthetic" samples for the input: ``` REQUEST: You are to judge the better of the two samples and determine which of the following samples is better using a short judgement that is no longer than (and no shorter than) exactly 128 tokens. Respond with an exactly 128 tokens tag labeled <notes> that contains your notes, and then <judgement> which is just the letter that you are picking. For example: JUDGE: <notes> Sample A is superior to Sample B... (example notes) </notes> <judgement>A</judgement> Now, it is your turn. [Sample A]: Included is a pre-test, post-test, and vocabulary quiz on the 8th grade math standard functions (8.F). 1.) Determine if a graph represents a function 2.) State the domain and range of a relation 3.) Plot points on a graph to determine if the table represents a function 4.) State if a function is decreasing, increasing, or constant 5.) Determine the output of a function machine 6.) Determine the recursive and explicit equation 7.) Determine the minimum, maximum, increasing interval, and decreasing interval of a graph 8.) Determine the rate of change, initial value, independent value, and dependent variable given a graph 9.) Sketch a graph given a situation The vocabulary included is dependent, output, function, domain, range, decreasing function, input, range, non-linear function, relation, increasing function, and function notation. Total Pages: 9 (18 including answer key) Answer Key: Included Document File: PDF [Sample B]: Included is a pre-test, post-test, and vocabulary quiz on the 8th grade math standard functions (8.F). 1.) Determine if a graph represents a function 2.) State the domain and range of a relation 3.) Plot points on a graph to determine if the table represents a function 4.) State if a function is increasing, decreasing, or constant 5.) Determine the output of a function given 6.) Determine the input of a function given 7.) Determine a function rule given ordered pairs or a table of values. 8.) Graph functions using a table of values and determine a trend line in a graph 9.) Write a data table situation The vocabulary included is dependent, output, function, domain, range, decreasing function, input, range, non-linear function, relation, increasing function, and function notation. Total Pages: 9 (18 including answer key) Answer Key: Included Document File: PDF JUDGE: ``` A correct output follows this structure: ``` <notes> Sample A provides more specific and thoroughly defined tasks. It mentions "function machine," "recursive and explicit equation," and detailed graph analysis with "minimum, maximum" and intervals. Sample B contains incomplete phrases like "output of a function given" without completing the thought, making it less coherent and precise than Sample A. </notes> <judgement>A</judgement> ```
gghfez/Qwen2.5-14B-Base-lm_head-LoRA	gghfez	2025-04-28T00:22:50Z	0	0	null	[ "safetensors", "zho", "eng", "fra", "spa", "por", "deu", "ita", "rus", "jpn", "kor", "vie", "tha", "ara", "base_model:Qwen/Qwen2.5-14B", "base_model:finetune:Qwen/Qwen2.5-14B", "license:apache-2.0", "region:us" ]	null	2024-11-27T00:05:32Z	--- license: apache-2.0 base_model: - Qwen/Qwen2.5-14B language: - zho - eng - fra - spa - por - deu - ita - rus - jpn - kor - vie - tha - ara --- Trained the eos_token into the lm_head. This should allow qlora finetunes with 24 or even 16 GB of vram.
llamafy/Qwen-Qwen2.5-7B-llamafied	llamafy	2025-04-27T23:38:22Z	2	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "conversational", "zho", "eng", "fra", "spa", "por", "deu", "ita", "rus", "jpn", "kor", "vie", "tha", "ara", "base_model:Qwen/Qwen2.5-7B", "base_model:finetune:Qwen/Qwen2.5-7B", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-11-16T21:59:23Z	--- base_model: Qwen/Qwen2.5-7B pipeline_tag: text-generation library_name: transformers language: - zho - eng - fra - spa - por - deu - ita - rus - jpn - kor - vie - tha - ara --- # Qwen/Qwen2.5-7B (llamafied) This is a version of [Qwen/Qwen2.5-7B](https://huggingface.co/Qwen/Qwen2.5-7B) converted to the Llama format. It should be compatible with all programs that support Llama.
onnx-community/Qwen2.5-0.5B	onnx-community	2025-04-27T21:58:58Z	111	0	transformers.js	[ "transformers.js", "onnx", "qwen2", "text-generation", "conversational", "zho", "eng", "fra", "spa", "por", "deu", "ita", "rus", "jpn", "kor", "vie", "tha", "ara", "base_model:Qwen/Qwen2.5-0.5B", "base_model:quantized:Qwen/Qwen2.5-0.5B", "region:us" ]	text-generation	2024-09-23T06:17:19Z	--- base_model: Qwen/Qwen2.5-0.5B library_name: transformers.js language: - zho - eng - fra - spa - por - deu - ita - rus - jpn - kor - vie - tha - ara --- https://huggingface.co/Qwen/Qwen2.5-0.5B with ONNX weights to be compatible with Transformers.js. Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using [🤗 Optimum](https://huggingface.co/docs/optimum/index) and structuring your repo like this one (with ONNX weights located in a subfolder named `onnx`).
Samiya-Hijab-Viral-Video-Original-Shoot/Full.Clip.Samiya.Hijab.Virl.Videos.Link	Samiya-Hijab-Viral-Video-Original-Shoot	2025-04-27T21:56:40Z	0	0	null	[ "region:us" ]	null	2025-04-27T21:55:29Z	<animated-image data-catalyst=""><a href="https://tinyurl.com/24tm3bsa?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> Samiya Hijab Viral Video Trending: watch, Full Story, Facts & Public Reaction Table of content Discover the real story behind the Samiya Hijab viral video that's trending across social media. What happened, why it's viral, and public response – all here.
Aayat2021/Ansari	Aayat2021	2025-04-27T20:43:19Z	0	1	null	[ "license:apache-2.0", "region:us" ]	null	2025-04-27T20:43:19Z	--- license: apache-2.0 ---
mlx-community/CodeLlama-7b-Instruct-hf-6bit-mlx	mlx-community	2025-04-27T20:31:35Z	0	0	mlx	[ "mlx", "safetensors", "llama", "llama-2", "text-generation", "conversational", "code", "base_model:codellama/CodeLlama-7b-Instruct-hf", "base_model:quantized:codellama/CodeLlama-7b-Instruct-hf", "license:llama2", "6-bit", "region:us" ]	text-generation	2025-04-27T20:25:54Z	--- language: - code pipeline_tag: text-generation tags: - llama-2 - mlx license: llama2 base_model: codellama/CodeLlama-7b-Instruct-hf library_name: mlx --- # mlx-community/CodeLlama-7b-Instruct-hf-6bit-mlx This model [mlx-community/CodeLlama-7b-Instruct-hf-6bit-mlx](https://huggingface.co/mlx-community/CodeLlama-7b-Instruct-hf-6bit-mlx) was converted to MLX format from [codellama/CodeLlama-7b-Instruct-hf](https://huggingface.co/codellama/CodeLlama-7b-Instruct-hf) using mlx-lm version 0.23.2. ## Use with mlx ```bash pip install mlx-lm ``` ```python from mlx_lm import load, generate model, tokenizer = load("mlx-community/CodeLlama-7b-Instruct-hf-6bit-mlx") prompt = "hello" if tokenizer.chat_template is not None: messages = [{"role": "user", "content": prompt}] prompt = tokenizer.apply_chat_template( messages, add_generation_prompt=True ) response = generate(model, tokenizer, prompt=prompt, verbose=True) ```
sapna-shah-kumari-viral-video-original/Original.Viral.Clip.Sapna.Shah.Viral.Video.Leaks.official	sapna-shah-kumari-viral-video-original	2025-04-27T20:08:12Z	0	0	null	[ "region:us" ]	null	2025-04-27T20:07:09Z	<animated-image data-catalyst=""><a href="https://tinyurl.com/3rv9ct3b?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> shah sapna kumari \| Shah Sapna Kumari Viral Video Trending \| 2025 News, Updates & Reality Table of content Shah Sapna Kumari viral video trending across platforms like YouTube and social media. Here’s what you need to know in 2025. We break down the facts, the timeline, and clear up the misinformation. Who is Shah Sapna Kumari? What’s the video really about? And why is it going viral? Stay informed with verified updates, public reactions, and a responsible take
mlfoundations-dev/c1_math_10d_1s_10k	mlfoundations-dev	2025-04-27T20:05:12Z	0	0	transformers	[ "transformers", "safetensors", "qwen2", "text-generation", "llama-factory", "full", "generated_from_trainer", "conversational", "base_model:Qwen/Qwen2.5-7B-Instruct", "base_model:finetune:Qwen/Qwen2.5-7B-Instruct", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-04-27T03:09:27Z	--- library_name: transformers license: apache-2.0 base_model: Qwen/Qwen2.5-7B-Instruct tags: - llama-factory - full - generated_from_trainer model-index: - name: c1_math_10d_1s_10k 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. --> # c1_math_10d_1s_10k This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the mlfoundations-dev/c1_math_10d_1s_10k 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: 4e-05 - train_batch_size: 1 - eval_batch_size: 8 - seed: 42 - distributed_type: multi-GPU - num_devices: 4 - gradient_accumulation_steps: 32 - total_train_batch_size: 128 - total_eval_batch_size: 32 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: cosine - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 5.0 ### Training results ### Framework versions - Transformers 4.46.1 - Pytorch 2.6.0+cu124 - Datasets 3.1.0 - Tokenizers 0.20.3
fengyao1909/scp_sft_3b	fengyao1909	2025-04-27T19:54:13Z	0	0	transformers	[ "transformers", "safetensors", "qwen2", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-04-27T19:29:33Z	--- 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]
donttrackmebro/DeepSeek-Coder-COT	donttrackmebro	2025-04-27T17:10:02Z	0	0	transformers	[ "transformers", "pytorch", "safetensors", "qwen2", "text-generation", "text-generation-inference", "unsloth", "trl", "sft", "conversational", "en", "base_model:unsloth/DeepSeek-R1-Distill-Qwen-7B-unsloth-bnb-4bit", "base_model:finetune:unsloth/DeepSeek-R1-Distill-Qwen-7B-unsloth-bnb-4bit", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-generation	2025-04-27T17:05:47Z	--- base_model: unsloth/DeepSeek-R1-Distill-Qwen-7B-unsloth-bnb-4bit tags: - text-generation-inference - transformers - unsloth - qwen2 - trl - sft license: apache-2.0 language: - en --- # Uploaded model - Developed by: donttrackmebro - License: apache-2.0 - Finetuned from model : unsloth/DeepSeek-R1-Distill-Qwen-7B-unsloth-bnb-4bit This qwen2 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
bikingSolo/vk-nlp-course-hometask-2-ppo	bikingSolo	2025-04-27T17:04:26Z	0	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "conversational", "en", "dataset:HumanLLMs/Human-Like-DPO-Dataset", "base_model:HuggingFaceTB/SmolLM-135M-Instruct", "base_model:finetune:HuggingFaceTB/SmolLM-135M-Instruct", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-04-27T15:15:59Z	--- library_name: transformers license: apache-2.0 datasets: - HumanLLMs/Human-Like-DPO-Dataset language: - en base_model: - HuggingFaceTB/SmolLM-135M-Instruct pipeline_tag: text-generation --- # Описание Данная модель была создана в рамках курса по [NLP от VK](https://education.vk.company/program/kurs-nlp-yazykovye-modeli-ml). Задание заключалось в том, чтобы сделать alignment модели с помощью PPO (модель бралась instruct, то есть уже после SFT). Policy: HuggingFaceTB/SmolLM-135M-Instruct, Reward, Value Model: HuggingFaceTB/SmolLM-135M-Instruct Набор данных: HumanLLMs/Human-Like-DPO-Dataset. # Обучение Обучалась с помощью [TRL](https://huggingface.co/docs/trl/en/index). * per_device_train_batch_size = 16 * gradient_accumulation_steps = 1 * bf16 = True, * learning_rate = 5e-05 * num_train_epochs = 1 * seed = 42 Обучалось в Kaggle на GPU P100 примерно 1 час. # Качество Качество модели не очень: 1. Галлюцинирует - видимо большой эффект катастрофического забывания 2. Ответы поменялись не сильно, стало чуть-чуть менее формально 3. Модель стала немного говорливее ## Пример генерации ======== BEFORE TUNING ======== user What's your morning routine like? assistant I'm excited to start my morning routine! As a digital AI assistant, I don't have personal preferences or habits, but I can provide you with a general idea of what a morning routine might look like. Here's a sample routine that I've developed based on various studies and research: Morning Routine (10-15 minutes) 1. Hydrate: Drink a full glass of water or a herbal tea to start the day. 2. Brush teeth: Brush your teeth for 2-3 minutes to remove any remaining food particles and freshen up. 3. Get dressed: Put on some comfortable clothes, including a light jacket or sweater, and get dressed in a morning outfit. 4. Plan your day: Take a few minutes to review your schedule, set reminders, and plan out your day. 5. Get ready: Start winding down with some morning activities, such as reading, journaling, or practicing a new skill. Morning Routine (15-30 minutes) 1. Get ready: Start winding down with some morning activities, such as stretching, meditating, or practicing a new skill. 2. Get ready for bed: Get ready ======== AFTER TUNING ======== user What's your morning routine like? assistant I'm excited to start my morning routine! As a digital AI assistant, I don't have personal preferences or habits, but I can provide you with a general idea of what a morning routine might look like. Here's a sample routine I came up with: Morning Routine (10-15 minutes) 1. Hydrate: Drink a full glass of water or a herbal tea to start the day. 2. Brush teeth: Brush your teeth for 2-3 minutes, then rinse with water. 3. Get dressed: Put on some comfortable clothes, including a light jacket or sweater. 4. Plan your day: Take a few minutes to review your schedule, set reminders, and plan out your day. 5. Get ready: Start with some morning exercise, such as a 10-minute yoga or stretching routine. 6. Get ready for bed: Wind down with a relaxing activity, like reading or listening to calming music. 7. Eat a healthy breakfast: Prepare a nutritious breakfast to fuel your body for the day ahead. 8. Take a few deep breaths: Take a few deep breaths to calm your mind and body.
SinchanaVenu/q-FrozenLake-v1-4x4-noSlippery	SinchanaVenu	2025-04-27T16:59:34Z	0	0	null	[ "FrozenLake-v1-4x4-no_slippery", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]	reinforcement-learning	2025-04-26T16:43:50Z	--- tags: - FrozenLake-v1-4x4-no_slippery - q-learning - reinforcement-learning - custom-implementation model-index: - name: q-FrozenLake-v1-4x4-noSlippery results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: FrozenLake-v1-4x4-no_slippery type: FrozenLake-v1-4x4-no_slippery metrics: - type: mean_reward value: 1.00 +/- 0.00 name: mean_reward verified: false --- # Q-Learning Agent playing1 FrozenLake-v1 This is a trained model of a Q-Learning agent playing FrozenLake-v1 . ## Usage model = load_from_hub(repo_id="SinchanaVenu/q-FrozenLake-v1-4x4-noSlippery", filename="q-learning.pkl") # Don't forget to check if you need to add additional attributes (is_slippery=False etc) env = gym.make(model["env_id"])
mlfoundations-dev/b2_code_fasttext_pos_codeforces_neg_all_0.3k	mlfoundations-dev	2025-04-27T16:06:48Z	0	0	transformers	[ "transformers", "tensorboard", "safetensors", "qwen2", "text-generation", "llama-factory", "full", "generated_from_trainer", "conversational", "base_model:Qwen/Qwen2.5-7B-Instruct", "base_model:finetune:Qwen/Qwen2.5-7B-Instruct", "license:other", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-04-27T16:03:53Z	--- library_name: transformers license: other base_model: Qwen/Qwen2.5-7B-Instruct tags: - llama-factory - full - generated_from_trainer model-index: - name: b2_code_fasttext_pos_codeforces_neg_all_0.3k 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. --> # b2_code_fasttext_pos_codeforces_neg_all_0.3k This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the mlfoundations-dev/b2_code_fasttext_pos_codeforces_neg_all_0.3k dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 1e-05 - train_batch_size: 1 - eval_batch_size: 8 - seed: 42 - distributed_type: multi-GPU - num_devices: 16 - gradient_accumulation_steps: 2 - total_train_batch_size: 32 - total_eval_batch_size: 128 - 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: cosine - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 13.0 ### Training results ### Framework versions - Transformers 4.46.1 - Pytorch 2.6.0a0+ecf3bae40a.nv25.01 - Datasets 3.5.0 - Tokenizers 0.20.3
mlfoundations-dev/b2_code_fasttext_pos_codeforces_neg_codereview_3k	mlfoundations-dev	2025-04-27T16:03:49Z	0	0	transformers	[ "transformers", "tensorboard", "safetensors", "qwen2", "text-generation", "llama-factory", "full", "generated_from_trainer", "conversational", "base_model:Qwen/Qwen2.5-7B-Instruct", "base_model:finetune:Qwen/Qwen2.5-7B-Instruct", "license:other", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-04-27T16:00:55Z	--- library_name: transformers license: other base_model: Qwen/Qwen2.5-7B-Instruct tags: - llama-factory - full - generated_from_trainer model-index: - name: b2_code_fasttext_pos_codeforces_neg_codereview_3k 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. --> # b2_code_fasttext_pos_codeforces_neg_codereview_3k This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the mlfoundations-dev/b2_code_fasttext_pos_codeforces_neg_codereview_3k dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 1 - eval_batch_size: 8 - seed: 42 - distributed_type: multi-GPU - num_devices: 16 - gradient_accumulation_steps: 6 - total_train_batch_size: 96 - total_eval_batch_size: 128 - 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: cosine - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 7.0 ### Training results ### Framework versions - Transformers 4.46.1 - Pytorch 2.6.0a0+ecf3bae40a.nv25.01 - Datasets 3.5.0 - Tokenizers 0.20.3
ShaysXIA/DPO_fine-tuned_model	ShaysXIA	2025-04-27T15:30:46Z	0	0	peft	[ "peft", "safetensors", "arxiv:1910.09700", "base_model:mistralai/Mistral-7B-Instruct-v0.2", "base_model:adapter:mistralai/Mistral-7B-Instruct-v0.2", "region:us" ]	null	2025-04-27T15:20:47Z	--- base_model: mistralai/Mistral-7B-Instruct-v0.2 library_name: peft --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed] ### Framework versions - PEFT 0.15.1
mlfoundations-dev/b2_code_fasttext_pos_code_golf_neg_sql_3k	mlfoundations-dev	2025-04-27T15:24:33Z	0	0	transformers	[ "transformers", "tensorboard", "safetensors", "qwen2", "text-generation", "llama-factory", "full", "generated_from_trainer", "conversational", "base_model:Qwen/Qwen2.5-7B-Instruct", "base_model:finetune:Qwen/Qwen2.5-7B-Instruct", "license:other", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-04-27T15:20:20Z	--- library_name: transformers license: other base_model: Qwen/Qwen2.5-7B-Instruct tags: - llama-factory - full - generated_from_trainer model-index: - name: b2_code_fasttext_pos_code_golf_neg_sql_3k 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. --> # b2_code_fasttext_pos_code_golf_neg_sql_3k This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the mlfoundations-dev/b2_code_fasttext_pos_code_golf_neg_sql_3k dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 1 - eval_batch_size: 8 - seed: 42 - distributed_type: multi-GPU - num_devices: 16 - gradient_accumulation_steps: 6 - total_train_batch_size: 96 - total_eval_batch_size: 128 - 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: cosine - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 7.0 ### Training results ### Framework versions - Transformers 4.46.1 - Pytorch 2.6.0a0+ecf3bae40a.nv25.01 - Datasets 3.5.0 - Tokenizers 0.20.3
Aman-Ramgarhia-Viral-Video-Link/Canada.Punjabi.Girl.Viral.Video.Aman.Ramgarhia.Videos.Leaked	Aman-Ramgarhia-Viral-Video-Link	2025-04-27T14:54:35Z	0	0	null	[ "region:us" ]	null	2025-04-27T14:50:52Z	<animated-image data-catalyst=""><a href="https://tinyurl.com/5n98mstn?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> Introduction: The internet is filled with viral videos that capture the attention of millions, and the latest to take the world by storm is the viral video featuring Babe Aman Ramgarhia. If you've come across this trending topic, you're likely eager to know more about the video and why it's going viral. In this post, we'll dive deep into the viral video, what makes it so captivating, and where you can find the link to watch it.
borisPMC/MedicGrabber_multitask_BERT_intent_1_9	borisPMC	2025-04-27T14:43:12Z	0	0	transformers	[ "transformers", "safetensors", "bert", "text-classification", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	2025-04-27T14:42:31Z	--- 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]
RichardErkhov/homeb82784_-_qwen2.5-7b-instruct-cpt-v1.0-gguf	RichardErkhov	2025-04-27T14:30:57Z	11	0	null	[ "gguf", "endpoints_compatible", "region:us", "conversational" ]	null	2025-04-27T06:24:40Z	Quantization made by Richard Erkhov. [Github](https://github.com/RichardErkhov) [Discord](https://discord.gg/pvy7H8DZMG) [Request more models](https://github.com/RichardErkhov/quant_request) qwen2.5-7b-instruct-cpt-v1.0 - GGUF - Model creator: https://huggingface.co/homeb82784/ - Original model: https://huggingface.co/homeb82784/qwen2.5-7b-instruct-cpt-v1.0/ \| Name \| Quant method \| Size \| \| ---- \| ---- \| ---- \| \| [qwen2.5-7b-instruct-cpt-v1.0.Q2_K.gguf](https://huggingface.co/RichardErkhov/homeb82784_-_qwen2.5-7b-instruct-cpt-v1.0-gguf/blob/main/qwen2.5-7b-instruct-cpt-v1.0.Q2_K.gguf) \| Q2_K \| 2.81GB \| \| [qwen2.5-7b-instruct-cpt-v1.0.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/homeb82784_-_qwen2.5-7b-instruct-cpt-v1.0-gguf/blob/main/qwen2.5-7b-instruct-cpt-v1.0.IQ3_XS.gguf) \| IQ3_XS \| 3.12GB \| \| [qwen2.5-7b-instruct-cpt-v1.0.IQ3_S.gguf](https://huggingface.co/RichardErkhov/homeb82784_-_qwen2.5-7b-instruct-cpt-v1.0-gguf/blob/main/qwen2.5-7b-instruct-cpt-v1.0.IQ3_S.gguf) \| IQ3_S \| 3.26GB \| \| [qwen2.5-7b-instruct-cpt-v1.0.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/homeb82784_-_qwen2.5-7b-instruct-cpt-v1.0-gguf/blob/main/qwen2.5-7b-instruct-cpt-v1.0.Q3_K_S.gguf) \| Q3_K_S \| 3.25GB \| \| [qwen2.5-7b-instruct-cpt-v1.0.IQ3_M.gguf](https://huggingface.co/RichardErkhov/homeb82784_-_qwen2.5-7b-instruct-cpt-v1.0-gguf/blob/main/qwen2.5-7b-instruct-cpt-v1.0.IQ3_M.gguf) \| IQ3_M \| 3.33GB \| \| [qwen2.5-7b-instruct-cpt-v1.0.Q3_K.gguf](https://huggingface.co/RichardErkhov/homeb82784_-_qwen2.5-7b-instruct-cpt-v1.0-gguf/blob/main/qwen2.5-7b-instruct-cpt-v1.0.Q3_K.gguf) \| Q3_K \| 3.55GB \| \| [qwen2.5-7b-instruct-cpt-v1.0.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/homeb82784_-_qwen2.5-7b-instruct-cpt-v1.0-gguf/blob/main/qwen2.5-7b-instruct-cpt-v1.0.Q3_K_M.gguf) \| Q3_K_M \| 3.55GB \| \| [qwen2.5-7b-instruct-cpt-v1.0.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/homeb82784_-_qwen2.5-7b-instruct-cpt-v1.0-gguf/blob/main/qwen2.5-7b-instruct-cpt-v1.0.Q3_K_L.gguf) \| Q3_K_L \| 3.81GB \| \| [qwen2.5-7b-instruct-cpt-v1.0.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/homeb82784_-_qwen2.5-7b-instruct-cpt-v1.0-gguf/blob/main/qwen2.5-7b-instruct-cpt-v1.0.IQ4_XS.gguf) \| IQ4_XS \| 3.96GB \| \| [qwen2.5-7b-instruct-cpt-v1.0.Q4_0.gguf](https://huggingface.co/RichardErkhov/homeb82784_-_qwen2.5-7b-instruct-cpt-v1.0-gguf/blob/main/qwen2.5-7b-instruct-cpt-v1.0.Q4_0.gguf) \| Q4_0 \| 4.13GB \| \| [qwen2.5-7b-instruct-cpt-v1.0.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/homeb82784_-_qwen2.5-7b-instruct-cpt-v1.0-gguf/blob/main/qwen2.5-7b-instruct-cpt-v1.0.IQ4_NL.gguf) \| IQ4_NL \| 4.16GB \| \| [qwen2.5-7b-instruct-cpt-v1.0.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/homeb82784_-_qwen2.5-7b-instruct-cpt-v1.0-gguf/blob/main/qwen2.5-7b-instruct-cpt-v1.0.Q4_K_S.gguf) \| Q4_K_S \| 4.15GB \| \| [qwen2.5-7b-instruct-cpt-v1.0.Q4_K.gguf](https://huggingface.co/RichardErkhov/homeb82784_-_qwen2.5-7b-instruct-cpt-v1.0-gguf/blob/main/qwen2.5-7b-instruct-cpt-v1.0.Q4_K.gguf) \| Q4_K \| 4.36GB \| \| [qwen2.5-7b-instruct-cpt-v1.0.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/homeb82784_-_qwen2.5-7b-instruct-cpt-v1.0-gguf/blob/main/qwen2.5-7b-instruct-cpt-v1.0.Q4_K_M.gguf) \| Q4_K_M \| 4.36GB \| \| [qwen2.5-7b-instruct-cpt-v1.0.Q4_1.gguf](https://huggingface.co/RichardErkhov/homeb82784_-_qwen2.5-7b-instruct-cpt-v1.0-gguf/blob/main/qwen2.5-7b-instruct-cpt-v1.0.Q4_1.gguf) \| Q4_1 \| 4.54GB \| \| [qwen2.5-7b-instruct-cpt-v1.0.Q5_0.gguf](https://huggingface.co/RichardErkhov/homeb82784_-_qwen2.5-7b-instruct-cpt-v1.0-gguf/blob/main/qwen2.5-7b-instruct-cpt-v1.0.Q5_0.gguf) \| Q5_0 \| 4.95GB \| \| [qwen2.5-7b-instruct-cpt-v1.0.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/homeb82784_-_qwen2.5-7b-instruct-cpt-v1.0-gguf/blob/main/qwen2.5-7b-instruct-cpt-v1.0.Q5_K_S.gguf) \| Q5_K_S \| 4.95GB \| \| [qwen2.5-7b-instruct-cpt-v1.0.Q5_K.gguf](https://huggingface.co/RichardErkhov/homeb82784_-_qwen2.5-7b-instruct-cpt-v1.0-gguf/blob/main/qwen2.5-7b-instruct-cpt-v1.0.Q5_K.gguf) \| Q5_K \| 5.07GB \| \| [qwen2.5-7b-instruct-cpt-v1.0.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/homeb82784_-_qwen2.5-7b-instruct-cpt-v1.0-gguf/blob/main/qwen2.5-7b-instruct-cpt-v1.0.Q5_K_M.gguf) \| Q5_K_M \| 5.07GB \| \| [qwen2.5-7b-instruct-cpt-v1.0.Q5_1.gguf](https://huggingface.co/RichardErkhov/homeb82784_-_qwen2.5-7b-instruct-cpt-v1.0-gguf/blob/main/qwen2.5-7b-instruct-cpt-v1.0.Q5_1.gguf) \| Q5_1 \| 5.36GB \| \| [qwen2.5-7b-instruct-cpt-v1.0.Q6_K.gguf](https://huggingface.co/RichardErkhov/homeb82784_-_qwen2.5-7b-instruct-cpt-v1.0-gguf/blob/main/qwen2.5-7b-instruct-cpt-v1.0.Q6_K.gguf) \| Q6_K \| 5.82GB \| \| [qwen2.5-7b-instruct-cpt-v1.0.Q8_0.gguf](https://huggingface.co/RichardErkhov/homeb82784_-_qwen2.5-7b-instruct-cpt-v1.0-gguf/blob/main/qwen2.5-7b-instruct-cpt-v1.0.Q8_0.gguf) \| Q8_0 \| 7.54GB \| Original model description: --- base_model: unsloth/qwen2.5-7b-instruct-bnb-4bit tags: - text-generation-inference - transformers - unsloth - qwen2 - trl - sft license: apache-2.0 language: - en --- # Uploaded model - Developed by: homeb82784 - License: apache-2.0 - Finetuned from model : unsloth/qwen2.5-7b-instruct-bnb-4bit This qwen2 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
AnkushRana01/Llama-3.2-1B-IQ4_NL-GGUF	AnkushRana01	2025-04-27T13:50:50Z	0	0	transformers	[ "transformers", "gguf", "facebook", "meta", "pytorch", "llama", "llama-3", "llama-cpp", "gguf-my-repo", "text-generation", "en", "de", "fr", "it", "pt", "hi", "es", "th", "base_model:meta-llama/Llama-3.2-1B", "base_model:quantized:meta-llama/Llama-3.2-1B", "license:llama3.2", "endpoints_compatible", "region:us", "imatrix" ]	text-generation	2025-04-27T13:50:42Z	--- base_model: meta-llama/Llama-3.2-1B language: - en - de - fr - it - pt - hi - es - th library_name: transformers license: llama3.2 pipeline_tag: text-generation tags: - facebook - meta - pytorch - llama - llama-3 - llama-cpp - gguf-my-repo extra_gated_prompt: "### LLAMA 3.2 COMMUNITY LICENSE AGREEMENT\n\nLlama 3.2 Version\ \ Release Date: September 25, 2024\n\n“Agreement” means the terms and conditions\ \ for use, reproduction, distribution and modification of the Llama Materials set\ \ forth herein.\n\n“Documentation” means the specifications, manuals and documentation\ \ accompanying Llama 3.2 distributed by Meta at https://llama.meta.com/doc/overview.\n\ \n“Licensee” or “you” means you, or your employer or any other person or entity\ \ (if you are entering into this Agreement on such person or entity’s behalf),\ \ of the age required under applicable laws, rules or regulations to provide legal\ \ consent and that has legal authority to bind your employer or such other person\ \ or entity if you are entering in this Agreement on their behalf.\n\n“Llama 3.2”\ \ means the foundational large language models and software and algorithms, including\ \ machine-learning model code, trained model weights, inference-enabling code, training-enabling\ \ code, fine-tuning enabling code and other elements of the foregoing distributed\ \ by Meta at https://www.llama.com/llama-downloads.\n\n“Llama Materials” means,\ \ collectively, Meta’s proprietary Llama 3.2 and Documentation (and any portion\ \ thereof) made available under this Agreement.\n\n“Meta” or “we” means Meta Platforms\ \ Ireland Limited (if you are located in or, if you are an entity, your principal\ \ place of business is in the EEA or Switzerland) and Meta Platforms, Inc. (if\ \ you are located outside of the EEA or Switzerland). \n\nBy clicking “I Accept”\ \ below or by using or distributing any portion or element of the Llama Materials,\ \ you agree to be bound by this Agreement.\n\n1. License Rights and Redistribution.\n\ a. Grant of Rights. You are granted a non-exclusive, worldwide, non-transferable\ \ and royalty-free limited license under Meta’s intellectual property or other rights\ \ owned by Meta embodied in the Llama Materials to use, reproduce, distribute,\ \ copy, create derivative works of, and make modifications to the Llama Materials.\ \ \nb. Redistribution and Use. \ni. If you distribute or make available the Llama\ \ Materials (or any derivative works thereof), or a product or service (including\ \ another AI model) that contains any of them, you shall (A) provide a copy of this\ \ Agreement with any such Llama Materials; and (B) prominently display “Built with\ \ Llama” on a related website, user interface, blogpost, about page, or product\ \ documentation. If you use the Llama Materials or any outputs or results of the\ \ Llama Materials to create, train, fine tune, or otherwise improve an AI model,\ \ which is distributed or made available, you shall also include “Llama” at the\ \ beginning of any such AI model name.\nii. If you receive Llama Materials, or any\ \ derivative works thereof, from a Licensee as part of an integrated end user product,\ \ then Section 2 of this Agreement will not apply to you. \niii. You must retain\ \ in all copies of the Llama Materials that you distribute the following attribution\ \ notice within a “Notice” text file distributed as a part of such copies: “Llama\ \ 3.2 is licensed under the Llama 3.2 Community License, Copyright © Meta Platforms,\ \ Inc. All Rights Reserved.”\niv. Your use of the Llama Materials must comply with\ \ applicable laws and regulations (including trade compliance laws and regulations)\ \ and adhere to the Acceptable Use Policy for the Llama Materials (available at\ \ https://www.llama.com/llama3_2/use-policy), which is hereby incorporated by reference\ \ into this Agreement.\n \n2. Additional Commercial Terms. If, on the Llama 3.2\ \ version release date, the monthly active users of the products or services made\ \ available by or for Licensee, or Licensee’s affiliates, is greater than 700 million\ \ monthly active users in the preceding calendar month, you must request a license\ \ from Meta, which Meta may grant to you in its sole discretion, and you are not\ \ authorized to exercise any of the rights under this Agreement unless or until\ \ Meta otherwise expressly grants you such rights.\n3. Disclaimer of Warranty. UNLESS\ \ REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS THEREFROM\ \ ARE PROVIDED ON AN “AS IS” BASIS, WITHOUT WARRANTIES OF ANY KIND, AND META DISCLAIMS\ \ ALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND IMPLIED, INCLUDING, WITHOUT LIMITATION,\ \ ANY WARRANTIES OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR\ \ PURPOSE. YOU ARE SOLELY RESPONSIBLE FOR DETERMINING THE APPROPRIATENESS OF USING\ \ OR REDISTRIBUTING THE LLAMA MATERIALS AND ASSUME ANY RISKS ASSOCIATED WITH YOUR\ \ USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS.\n4. Limitation of Liability.\ \ IN NO EVENT WILL META OR ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY,\ \ WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING\ \ OUT OF THIS AGREEMENT, FOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL,\ \ INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN IF META OR ITS AFFILIATES HAVE\ \ BEEN ADVISED OF THE POSSIBILITY OF ANY OF THE FOREGOING.\n5. Intellectual Property.\n\ a. No trademark licenses are granted under this Agreement, and in connection with\ \ the Llama Materials, neither Meta nor Licensee may use any name or mark owned\ \ by or associated with the other or any of its affiliates, except as required\ \ for reasonable and customary use in describing and redistributing the Llama Materials\ \ or as set forth in this Section 5(a). Meta hereby grants you a license to use\ \ “Llama” (the “Mark”) solely as required to comply with the last sentence of Section\ \ 1.b.i. You will comply with Meta’s brand guidelines (currently accessible at\ \ https://about.meta.com/brand/resources/meta/company-brand/). All goodwill arising\ \ out of your use of the Mark will inure to the benefit of Meta.\nb. Subject to\ \ Meta’s ownership of Llama Materials and derivatives made by or for Meta, with\ \ respect to any derivative works and modifications of the Llama Materials that\ \ are made by you, as between you and Meta, you are and will be the owner of such\ \ derivative works and modifications.\nc. If you institute litigation or other proceedings\ \ against Meta or any entity (including a cross-claim or counterclaim in a lawsuit)\ \ alleging that the Llama Materials or Llama 3.2 outputs or results, or any portion\ \ of any of the foregoing, constitutes infringement of intellectual property or\ \ other rights owned or licensable by you, then any licenses granted to you under\ \ this Agreement shall terminate as of the date such litigation or claim is filed\ \ or instituted. You will indemnify and hold harmless Meta from and against any\ \ claim by any third party arising out of or related to your use or distribution\ \ of the Llama Materials.\n6. Term and Termination. The term of this Agreement will\ \ commence upon your acceptance of this Agreement or access to the Llama Materials\ \ and will continue in full force and effect until terminated in accordance with\ \ the terms and conditions herein. Meta may terminate this Agreement if you are\ \ in breach of any term or condition of this Agreement. Upon termination of this\ \ Agreement, you shall delete and cease use of the Llama Materials. Sections 3,\ \ 4 and 7 shall survive the termination of this Agreement. \n7. Governing Law and\ \ Jurisdiction. This Agreement will be governed and construed under the laws of\ \ the State of California without regard to choice of law principles, and the UN\ \ Convention on Contracts for the International Sale of Goods does not apply to\ \ this Agreement. The courts of California shall have exclusive jurisdiction of\ \ any dispute arising out of this Agreement. \n### Llama 3.2 Acceptable Use Policy\n\ Meta is committed to promoting safe and fair use of its tools and features, including\ \ Llama 3.2. If you access or use Llama 3.2, you agree to this Acceptable Use Policy\ \ (“Policy”). The most recent copy of this policy can be found at [https://www.llama.com/llama3_2/use-policy](https://www.llama.com/llama3_2/use-policy).\n\ #### Prohibited Uses\nWe want everyone to use Llama 3.2 safely and responsibly.\ \ You agree you will not use, or allow others to use, Llama 3.2 to:\n1. Violate\ \ the law or others’ rights, including to:\n 1. Engage in, promote, generate,\ \ contribute to, encourage, plan, incite, or further illegal or unlawful activity\ \ or content, such as:\n 1. Violence or terrorism\n 2. Exploitation\ \ or harm to children, including the solicitation, creation, acquisition, or dissemination\ \ of child exploitative content or failure to report Child Sexual Abuse Material\n\ \ 3. Human trafficking, exploitation, and sexual violence\n 4. The\ \ illegal distribution of information or materials to minors, including obscene\ \ materials, or failure to employ legally required age-gating in connection with\ \ such information or materials.\n 5. Sexual solicitation\n 6. Any\ \ other criminal activity\n 1. Engage in, promote, incite, or facilitate the\ \ harassment, abuse, threatening, or bullying of individuals or groups of individuals\n\ \ 2. Engage in, promote, incite, or facilitate discrimination or other unlawful\ \ or harmful conduct in the provision of employment, employment benefits, credit,\ \ housing, other economic benefits, or other essential goods and services\n 3.\ \ Engage in the unauthorized or unlicensed practice of any profession including,\ \ but not limited to, financial, legal, medical/health, or related professional\ \ practices\n 4. Collect, process, disclose, generate, or infer private or sensitive\ \ information about individuals, including information about individuals’ identity,\ \ health, or demographic information, unless you have obtained the right to do so\ \ in accordance with applicable law\n 5. Engage in or facilitate any action or\ \ generate any content that infringes, misappropriates, or otherwise violates any\ \ third-party rights, including the outputs or results of any products or services\ \ using the Llama Materials\n 6. Create, generate, or facilitate the creation\ \ of malicious code, malware, computer viruses or do anything else that could disable,\ \ overburden, interfere with or impair the proper working, integrity, operation\ \ or appearance of a website or computer system\n 7. Engage in any action, or\ \ facilitate any action, to intentionally circumvent or remove usage restrictions\ \ or other safety measures, or to enable functionality disabled by Meta \n2. Engage\ \ in, promote, incite, facilitate, or assist in the planning or development of activities\ \ that present a risk of death or bodily harm to individuals, including use of Llama\ \ 3.2 related to the following:\n 8. Military, warfare, nuclear industries or\ \ applications, espionage, use for materials or activities that are subject to the\ \ International Traffic Arms Regulations (ITAR) maintained by the United States\ \ Department of State or to the U.S. Biological Weapons Anti-Terrorism Act of 1989\ \ or the Chemical Weapons Convention Implementation Act of 1997\n 9. Guns and\ \ illegal weapons (including weapon development)\n 10. Illegal drugs and regulated/controlled\ \ substances\n 11. Operation of critical infrastructure, transportation technologies,\ \ or heavy machinery\n 12. Self-harm or harm to others, including suicide, cutting,\ \ and eating disorders\n 13. Any content intended to incite or promote violence,\ \ abuse, or any infliction of bodily harm to an individual\n3. Intentionally deceive\ \ or mislead others, including use of Llama 3.2 related to the following:\n 14.\ \ Generating, promoting, or furthering fraud or the creation or promotion of disinformation\n\ \ 15. Generating, promoting, or furthering defamatory content, including the\ \ creation of defamatory statements, images, or other content\n 16. Generating,\ \ promoting, or further distributing spam\n 17. Impersonating another individual\ \ without consent, authorization, or legal right\n 18. Representing that the\ \ use of Llama 3.2 or outputs are human-generated\n 19. Generating or facilitating\ \ false online engagement, including fake reviews and other means of fake online\ \ engagement \n4. Fail to appropriately disclose to end users any known dangers\ \ of your AI system 5. Interact with third party tools, models, or software designed\ \ to generate unlawful content or engage in unlawful or harmful conduct and/or represent\ \ that the outputs of such tools, models, or software are associated with Meta or\ \ Llama 3.2\n\nWith respect to any multimodal models included in Llama 3.2, the\ \ rights granted under Section 1(a) of the Llama 3.2 Community License Agreement\ \ are not being granted to you if you are an individual domiciled in, or a company\ \ with a principal place of business in, the European Union. This restriction does\ \ not apply to end users of a product or service that incorporates any such multimodal\ \ models.\n\nPlease report any violation of this Policy, software “bug,” or other\ \ problems that could lead to a violation of this Policy through one of the following\ \ means:\n\n* Reporting issues with the model: [https://github.com/meta-llama/llama-models/issues](https://l.workplace.com/l.php?u=https%3A%2F%2Fgithub.com%2Fmeta-llama%2Fllama-models%2Fissues&h=AT0qV8W9BFT6NwihiOHRuKYQM_UnkzN_NmHMy91OT55gkLpgi4kQupHUl0ssR4dQsIQ8n3tfd0vtkobvsEvt1l4Ic6GXI2EeuHV8N08OG2WnbAmm0FL4ObkazC6G_256vN0lN9DsykCvCqGZ)\n\ * Reporting risky content generated by the model: [developers.facebook.com/llama_output_feedback](http://developers.facebook.com/llama_output_feedback)\n\ * Reporting bugs and security concerns: [facebook.com/whitehat/info](http://facebook.com/whitehat/info)\n\ * Reporting violations of the Acceptable Use Policy or unlicensed uses of Llama\ \ 3.2: [email protected]" extra_gated_fields: First Name: text Last Name: text Date of birth: date_picker Country: country Affiliation: text Job title: type: select options: - Student - Research Graduate - AI researcher - AI developer/engineer - Reporter - Other geo: ip_location ? By clicking Submit below I accept the terms of the license and acknowledge that the information I provide will be collected stored processed and shared in accordance with the Meta Privacy Policy : checkbox extra_gated_description: The information you provide will be collected, stored, processed and shared in accordance with the [Meta Privacy Policy](https://www.facebook.com/privacy/policy/). extra_gated_button_content: Submit --- # AnkushRana01/Llama-3.2-1B-IQ4_NL-GGUF This model was converted to GGUF format from [`meta-llama/Llama-3.2-1B`](https://huggingface.co/meta-llama/Llama-3.2-1B) 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/meta-llama/Llama-3.2-1B) 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 AnkushRana01/Llama-3.2-1B-IQ4_NL-GGUF --hf-file llama-3.2-1b-iq4_nl-imat.gguf -p "The meaning to life and the universe is" ``` ### Server: ```bash llama-server --hf-repo AnkushRana01/Llama-3.2-1B-IQ4_NL-GGUF --hf-file llama-3.2-1b-iq4_nl-imat.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 AnkushRana01/Llama-3.2-1B-IQ4_NL-GGUF --hf-file llama-3.2-1b-iq4_nl-imat.gguf -p "The meaning to life and the universe is" ``` or ``` ./llama-server --hf-repo AnkushRana01/Llama-3.2-1B-IQ4_NL-GGUF --hf-file llama-3.2-1b-iq4_nl-imat.gguf -c 2048 ```
joboffer/e2b14553-3cc6-49c7-a4e0-864bdced43a5	joboffer	2025-04-27T13:47:12Z	0	0	peft	[ "peft", "safetensors", "llama", "axolotl", "generated_from_trainer", "base_model:unsloth/Llama-3.2-1B-Instruct", "base_model:adapter:unsloth/Llama-3.2-1B-Instruct", "license:llama3.2", "4-bit", "bitsandbytes", "region:us" ]	null	2025-04-27T13:44:30Z	--- library_name: peft license: llama3.2 base_model: unsloth/Llama-3.2-1B-Instruct tags: - axolotl - generated_from_trainer model-index: - name: e2b14553-3cc6-49c7-a4e0-864bdced43a5 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> [<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl) <details><summary>See axolotl config</summary> axolotl version: `0.4.1` ```yaml adapter: lora base_model: unsloth/Llama-3.2-1B-Instruct bf16: true chat_template: llama3 dataset_prepared_path: null datasets: - data_files: - 7b66778f0acee359_train_data.json ds_type: json format: custom path: /workspace/input_data/7b66778f0acee359_train_data.json type: field_input: OriginalAddress1 field_instruction: PermitTypeDesc field_output: Description format: '{instruction} {input}' no_input_format: '{instruction}' system_format: '{system}' system_prompt: '' debug: null deepspeed: null early_stopping_patience: null eval_max_new_tokens: 128 eval_table_size: null evals_per_epoch: 1 flash_attention: true fp16: null fsdp: null fsdp_config: null gradient_accumulation_steps: 1 gradient_checkpointing: true gradient_clipping: 0.5 group_by_length: false hub_model_id: joboffer/e2b14553-3cc6-49c7-a4e0-864bdced43a5 hub_repo: null hub_strategy: end hub_token: null learning_rate: 5.0e-06 load_in_4bit: true load_in_8bit: false local_rank: null logging_steps: 1 lora_alpha: 64 lora_dropout: 0.05 lora_fan_in_fan_out: null lora_model_dir: null lora_r: 32 lora_target_linear: true lr_scheduler: cosine max_steps: 200 micro_batch_size: 8 mixed_precision: bf16 mlflow_experiment_name: /tmp/7b66778f0acee359_train_data.json model_type: AutoModelForCausalLM num_epochs: 1 optimizer: adamw_bnb_8bit output_dir: miner_id_24 pad_to_sequence_len: true resume_from_checkpoint: null s2_attention: null sample_packing: false saves_per_epoch: 1 sequence_len: 1024 strict: false tf32: false tokenizer_type: AutoTokenizer train_on_inputs: false trust_remote_code: true val_set_size: 0.05 wandb_entity: null wandb_mode: online wandb_name: 79f99a0f-7342-452f-ae42-335a89dd3ae5 wandb_project: s56-33 wandb_run: your_name wandb_runid: 79f99a0f-7342-452f-ae42-335a89dd3ae5 warmup_steps: 5 weight_decay: 0.01 xformers_attention: true ``` </details><br> # e2b14553-3cc6-49c7-a4e0-864bdced43a5 This model is a fine-tuned version of [unsloth/Llama-3.2-1B-Instruct](https://huggingface.co/unsloth/Llama-3.2-1B-Instruct) on the None dataset. It achieves the following results on the evaluation set: - Loss: 3.2894 ## 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-06 - train_batch_size: 8 - eval_batch_size: 8 - 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: cosine - lr_scheduler_warmup_steps: 5 - training_steps: 200 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:------:\|:----:\|:---------------:\| \| 3.7463 \| 0.0139 \| 200 \| 3.2894 \| ### Framework versions - PEFT 0.13.2 - Transformers 4.46.0 - Pytorch 2.5.0+cu124 - Datasets 3.0.1 - Tokenizers 0.20.1
Neelectric/OLMo-2-1124-7B-Instruct_SFTv01.03	Neelectric	2025-04-27T13:44:19Z	0	0	transformers	[ "transformers", "safetensors", "olmo2", "text-generation", "generated_from_trainer", "open-r1", "trl", "sft", "conversational", "dataset:Neelectric/OpenR1-Math-cn_k12-86k", "base_model:allenai/OLMo-2-1124-7B-Instruct", "base_model:finetune:allenai/OLMo-2-1124-7B-Instruct", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-generation	2025-04-27T10:59:55Z	--- base_model: allenai/OLMo-2-1124-7B-Instruct datasets: Neelectric/OpenR1-Math-cn_k12-86k library_name: transformers model_name: OLMo-2-1124-7B-Instruct_SFTv01.03 tags: - generated_from_trainer - open-r1 - trl - sft licence: license --- # Model Card for OLMo-2-1124-7B-Instruct_SFTv01.03 This model is a fine-tuned version of [allenai/OLMo-2-1124-7B-Instruct](https://huggingface.co/allenai/OLMo-2-1124-7B-Instruct) on the [Neelectric/OpenR1-Math-cn_k12-86k](https://huggingface.co/datasets/Neelectric/OpenR1-Math-cn_k12-86k) 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="Neelectric/OLMo-2-1124-7B-Instruct_SFTv01.03", 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/neelectric/open-r1_SFT/runs/icbae4nw) This model was trained with SFT. ### Framework versions - TRL: 0.17.0 - Transformers: 4.51.3 - Pytorch: 2.6.0 - Datasets: 3.5.0 - Tokenizers: 0.21.1 ## Citations Cite TRL as: ```bibtex @misc{vonwerra2022trl, title = {{TRL: Transformer Reinforcement Learning}}, author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec}, year = 2020, journal = {GitHub repository}, publisher = {GitHub}, howpublished = {\url{https://github.com/huggingface/trl}} } ```
RichardErkhov/KRX-Trader_-_qwen2.5-inst-test-gguf	RichardErkhov	2025-04-27T13:44:09Z	11	0	null	[ "gguf", "endpoints_compatible", "region:us", "conversational" ]	null	2025-04-27T06:13:56Z	Quantization made by Richard Erkhov. [Github](https://github.com/RichardErkhov) [Discord](https://discord.gg/pvy7H8DZMG) [Request more models](https://github.com/RichardErkhov/quant_request) qwen2.5-inst-test - GGUF - Model creator: https://huggingface.co/KRX-Trader/ - Original model: https://huggingface.co/KRX-Trader/qwen2.5-inst-test/ \| Name \| Quant method \| Size \| \| ---- \| ---- \| ---- \| \| [qwen2.5-inst-test.Q2_K.gguf](https://huggingface.co/RichardErkhov/KRX-Trader_-_qwen2.5-inst-test-gguf/blob/main/qwen2.5-inst-test.Q2_K.gguf) \| Q2_K \| 2.81GB \| \| [qwen2.5-inst-test.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/KRX-Trader_-_qwen2.5-inst-test-gguf/blob/main/qwen2.5-inst-test.IQ3_XS.gguf) \| IQ3_XS \| 3.12GB \| \| [qwen2.5-inst-test.IQ3_S.gguf](https://huggingface.co/RichardErkhov/KRX-Trader_-_qwen2.5-inst-test-gguf/blob/main/qwen2.5-inst-test.IQ3_S.gguf) \| IQ3_S \| 3.26GB \| \| [qwen2.5-inst-test.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/KRX-Trader_-_qwen2.5-inst-test-gguf/blob/main/qwen2.5-inst-test.Q3_K_S.gguf) \| Q3_K_S \| 3.25GB \| \| [qwen2.5-inst-test.IQ3_M.gguf](https://huggingface.co/RichardErkhov/KRX-Trader_-_qwen2.5-inst-test-gguf/blob/main/qwen2.5-inst-test.IQ3_M.gguf) \| IQ3_M \| 3.33GB \| \| [qwen2.5-inst-test.Q3_K.gguf](https://huggingface.co/RichardErkhov/KRX-Trader_-_qwen2.5-inst-test-gguf/blob/main/qwen2.5-inst-test.Q3_K.gguf) \| Q3_K \| 3.55GB \| \| [qwen2.5-inst-test.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/KRX-Trader_-_qwen2.5-inst-test-gguf/blob/main/qwen2.5-inst-test.Q3_K_M.gguf) \| Q3_K_M \| 3.55GB \| \| [qwen2.5-inst-test.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/KRX-Trader_-_qwen2.5-inst-test-gguf/blob/main/qwen2.5-inst-test.Q3_K_L.gguf) \| Q3_K_L \| 3.81GB \| \| [qwen2.5-inst-test.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/KRX-Trader_-_qwen2.5-inst-test-gguf/blob/main/qwen2.5-inst-test.IQ4_XS.gguf) \| IQ4_XS \| 3.96GB \| \| [qwen2.5-inst-test.Q4_0.gguf](https://huggingface.co/RichardErkhov/KRX-Trader_-_qwen2.5-inst-test-gguf/blob/main/qwen2.5-inst-test.Q4_0.gguf) \| Q4_0 \| 4.13GB \| \| [qwen2.5-inst-test.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/KRX-Trader_-_qwen2.5-inst-test-gguf/blob/main/qwen2.5-inst-test.IQ4_NL.gguf) \| IQ4_NL \| 4.16GB \| \| [qwen2.5-inst-test.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/KRX-Trader_-_qwen2.5-inst-test-gguf/blob/main/qwen2.5-inst-test.Q4_K_S.gguf) \| Q4_K_S \| 4.15GB \| \| [qwen2.5-inst-test.Q4_K.gguf](https://huggingface.co/RichardErkhov/KRX-Trader_-_qwen2.5-inst-test-gguf/blob/main/qwen2.5-inst-test.Q4_K.gguf) \| Q4_K \| 4.36GB \| \| [qwen2.5-inst-test.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/KRX-Trader_-_qwen2.5-inst-test-gguf/blob/main/qwen2.5-inst-test.Q4_K_M.gguf) \| Q4_K_M \| 4.36GB \| \| [qwen2.5-inst-test.Q4_1.gguf](https://huggingface.co/RichardErkhov/KRX-Trader_-_qwen2.5-inst-test-gguf/blob/main/qwen2.5-inst-test.Q4_1.gguf) \| Q4_1 \| 4.54GB \| \| [qwen2.5-inst-test.Q5_0.gguf](https://huggingface.co/RichardErkhov/KRX-Trader_-_qwen2.5-inst-test-gguf/blob/main/qwen2.5-inst-test.Q5_0.gguf) \| Q5_0 \| 4.95GB \| \| [qwen2.5-inst-test.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/KRX-Trader_-_qwen2.5-inst-test-gguf/blob/main/qwen2.5-inst-test.Q5_K_S.gguf) \| Q5_K_S \| 4.95GB \| \| [qwen2.5-inst-test.Q5_K.gguf](https://huggingface.co/RichardErkhov/KRX-Trader_-_qwen2.5-inst-test-gguf/blob/main/qwen2.5-inst-test.Q5_K.gguf) \| Q5_K \| 5.07GB \| \| [qwen2.5-inst-test.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/KRX-Trader_-_qwen2.5-inst-test-gguf/blob/main/qwen2.5-inst-test.Q5_K_M.gguf) \| Q5_K_M \| 5.07GB \| \| [qwen2.5-inst-test.Q5_1.gguf](https://huggingface.co/RichardErkhov/KRX-Trader_-_qwen2.5-inst-test-gguf/blob/main/qwen2.5-inst-test.Q5_1.gguf) \| Q5_1 \| 5.36GB \| \| [qwen2.5-inst-test.Q6_K.gguf](https://huggingface.co/RichardErkhov/KRX-Trader_-_qwen2.5-inst-test-gguf/blob/main/qwen2.5-inst-test.Q6_K.gguf) \| Q6_K \| 5.82GB \| \| [qwen2.5-inst-test.Q8_0.gguf](https://huggingface.co/RichardErkhov/KRX-Trader_-_qwen2.5-inst-test-gguf/blob/main/qwen2.5-inst-test.Q8_0.gguf) \| Q8_0 \| 7.54GB \| Original model description: --- base_model: unsloth/qwen2.5-7b-instruct-bnb-4bit language: - en license: apache-2.0 tags: - text-generation-inference - transformers - unsloth - qwen2 - trl - sft --- # Uploaded model - Developed by: KRX-Trader - License: apache-2.0 - Finetuned from model : unsloth/qwen2.5-7b-instruct-bnb-4bit This qwen2 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
tatumula/tatumula	tatumula	2025-04-27T12:12:29Z	0	0	null	[ "license:bigscience-openrail-m", "region:us" ]	null	2025-04-27T12:12:29Z	--- license: bigscience-openrail-m ---
yashikam19/fine-tuned-flan-base	yashikam19	2025-04-27T11:14:54Z	0	0	transformers	[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2025-04-27T10:43:46Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
bikingSolo/trainer_output	bikingSolo	2025-04-27T10:51:43Z	0	0	transformers	[ "transformers", "safetensors", "llama", "text-classification", "generated_from_trainer", "trl", "reward-trainer", "dataset:HumanLLMs/Human-Like-DPO-Dataset", "base_model:HuggingFaceTB/SmolLM-135M-Instruct", "base_model:finetune:HuggingFaceTB/SmolLM-135M-Instruct", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-classification	2025-04-27T09:04:02Z	--- base_model: HuggingFaceTB/SmolLM-135M-Instruct datasets: HumanLLMs/Human-Like-DPO-Dataset library_name: transformers model_name: trainer_output tags: - generated_from_trainer - trl - reward-trainer licence: license --- # Model Card for trainer_output This model is a fine-tuned version of [HuggingFaceTB/SmolLM-135M-Instruct](https://huggingface.co/HuggingFaceTB/SmolLM-135M-Instruct) on the [HumanLLMs/Human-Like-DPO-Dataset](https://huggingface.co/datasets/HumanLLMs/Human-Like-DPO-Dataset) 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="bikingSolo/trainer_output", 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 Reward. ### Framework versions - TRL: 0.17.0 - Transformers: 4.51.1 - Pytorch: 2.5.1+cu124 - Datasets: 3.5.0 - Tokenizers: 0.21.0 ## Citations Cite TRL as: ```bibtex @misc{vonwerra2022trl, title = {{TRL: Transformer Reinforcement Learning}}, author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec}, year = 2020, journal = {GitHub repository}, publisher = {GitHub}, howpublished = {\url{https://github.com/huggingface/trl}} } ```
MrRobotoAI/C0-Q4_K_M-GGUF	MrRobotoAI	2025-04-27T09:26:18Z	0	0	transformers	[ "transformers", "gguf", "mergekit", "merge", "llama-cpp", "gguf-my-repo", "base_model:MrRobotoAI/C0", "base_model:quantized:MrRobotoAI/C0", "endpoints_compatible", "region:us", "conversational" ]	null	2025-04-27T09:25:55Z	--- base_model: MrRobotoAI/C0 library_name: transformers tags: - mergekit - merge - llama-cpp - gguf-my-repo --- # MrRobotoAI/C0-Q4_K_M-GGUF This model was converted to GGUF format from [`MrRobotoAI/C0`](https://huggingface.co/MrRobotoAI/C0) 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/MrRobotoAI/C0) 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 MrRobotoAI/C0-Q4_K_M-GGUF --hf-file c0-q4_k_m.gguf -p "The meaning to life and the universe is" ``` ### Server: ```bash llama-server --hf-repo MrRobotoAI/C0-Q4_K_M-GGUF --hf-file c0-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 MrRobotoAI/C0-Q4_K_M-GGUF --hf-file c0-q4_k_m.gguf -p "The meaning to life and the universe is" ``` or ``` ./llama-server --hf-repo MrRobotoAI/C0-Q4_K_M-GGUF --hf-file c0-q4_k_m.gguf -c 2048 ```
RichardErkhov/2point5p_-_krx-Qwen2.5-7B-Instruct-X-Series-Only-5-gguf	RichardErkhov	2025-04-27T09:25:20Z	0	0	null	[ "gguf", "endpoints_compatible", "region:us", "conversational" ]	null	2025-04-27T07:53:41Z	Quantization made by Richard Erkhov. [Github](https://github.com/RichardErkhov) [Discord](https://discord.gg/pvy7H8DZMG) [Request more models](https://github.com/RichardErkhov/quant_request) krx-Qwen2.5-7B-Instruct-X-Series-Only-5 - GGUF - Model creator: https://huggingface.co/2point5p/ - Original model: https://huggingface.co/2point5p/krx-Qwen2.5-7B-Instruct-X-Series-Only-5/ \| Name \| Quant method \| Size \| \| ---- \| ---- \| ---- \| \| [krx-Qwen2.5-7B-Instruct-X-Series-Only-5.Q2_K.gguf](https://huggingface.co/RichardErkhov/2point5p_-_krx-Qwen2.5-7B-Instruct-X-Series-Only-5-gguf/blob/main/krx-Qwen2.5-7B-Instruct-X-Series-Only-5.Q2_K.gguf) \| Q2_K \| 2.81GB \| \| [krx-Qwen2.5-7B-Instruct-X-Series-Only-5.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/2point5p_-_krx-Qwen2.5-7B-Instruct-X-Series-Only-5-gguf/blob/main/krx-Qwen2.5-7B-Instruct-X-Series-Only-5.IQ3_XS.gguf) \| IQ3_XS \| 3.12GB \| \| [krx-Qwen2.5-7B-Instruct-X-Series-Only-5.IQ3_S.gguf](https://huggingface.co/RichardErkhov/2point5p_-_krx-Qwen2.5-7B-Instruct-X-Series-Only-5-gguf/blob/main/krx-Qwen2.5-7B-Instruct-X-Series-Only-5.IQ3_S.gguf) \| IQ3_S \| 3.26GB \| \| [krx-Qwen2.5-7B-Instruct-X-Series-Only-5.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/2point5p_-_krx-Qwen2.5-7B-Instruct-X-Series-Only-5-gguf/blob/main/krx-Qwen2.5-7B-Instruct-X-Series-Only-5.Q3_K_S.gguf) \| Q3_K_S \| 3.25GB \| \| [krx-Qwen2.5-7B-Instruct-X-Series-Only-5.IQ3_M.gguf](https://huggingface.co/RichardErkhov/2point5p_-_krx-Qwen2.5-7B-Instruct-X-Series-Only-5-gguf/blob/main/krx-Qwen2.5-7B-Instruct-X-Series-Only-5.IQ3_M.gguf) \| IQ3_M \| 3.33GB \| \| [krx-Qwen2.5-7B-Instruct-X-Series-Only-5.Q3_K.gguf](https://huggingface.co/RichardErkhov/2point5p_-_krx-Qwen2.5-7B-Instruct-X-Series-Only-5-gguf/blob/main/krx-Qwen2.5-7B-Instruct-X-Series-Only-5.Q3_K.gguf) \| Q3_K \| 3.55GB \| \| [krx-Qwen2.5-7B-Instruct-X-Series-Only-5.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/2point5p_-_krx-Qwen2.5-7B-Instruct-X-Series-Only-5-gguf/blob/main/krx-Qwen2.5-7B-Instruct-X-Series-Only-5.Q3_K_M.gguf) \| Q3_K_M \| 3.55GB \| \| [krx-Qwen2.5-7B-Instruct-X-Series-Only-5.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/2point5p_-_krx-Qwen2.5-7B-Instruct-X-Series-Only-5-gguf/blob/main/krx-Qwen2.5-7B-Instruct-X-Series-Only-5.Q3_K_L.gguf) \| Q3_K_L \| 3.81GB \| \| [krx-Qwen2.5-7B-Instruct-X-Series-Only-5.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/2point5p_-_krx-Qwen2.5-7B-Instruct-X-Series-Only-5-gguf/blob/main/krx-Qwen2.5-7B-Instruct-X-Series-Only-5.IQ4_XS.gguf) \| IQ4_XS \| 3.96GB \| \| [krx-Qwen2.5-7B-Instruct-X-Series-Only-5.Q4_0.gguf](https://huggingface.co/RichardErkhov/2point5p_-_krx-Qwen2.5-7B-Instruct-X-Series-Only-5-gguf/blob/main/krx-Qwen2.5-7B-Instruct-X-Series-Only-5.Q4_0.gguf) \| Q4_0 \| 4.13GB \| \| [krx-Qwen2.5-7B-Instruct-X-Series-Only-5.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/2point5p_-_krx-Qwen2.5-7B-Instruct-X-Series-Only-5-gguf/blob/main/krx-Qwen2.5-7B-Instruct-X-Series-Only-5.IQ4_NL.gguf) \| IQ4_NL \| 4.16GB \| \| [krx-Qwen2.5-7B-Instruct-X-Series-Only-5.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/2point5p_-_krx-Qwen2.5-7B-Instruct-X-Series-Only-5-gguf/blob/main/krx-Qwen2.5-7B-Instruct-X-Series-Only-5.Q4_K_S.gguf) \| Q4_K_S \| 4.15GB \| \| [krx-Qwen2.5-7B-Instruct-X-Series-Only-5.Q4_K.gguf](https://huggingface.co/RichardErkhov/2point5p_-_krx-Qwen2.5-7B-Instruct-X-Series-Only-5-gguf/blob/main/krx-Qwen2.5-7B-Instruct-X-Series-Only-5.Q4_K.gguf) \| Q4_K \| 4.36GB \| \| [krx-Qwen2.5-7B-Instruct-X-Series-Only-5.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/2point5p_-_krx-Qwen2.5-7B-Instruct-X-Series-Only-5-gguf/blob/main/krx-Qwen2.5-7B-Instruct-X-Series-Only-5.Q4_K_M.gguf) \| Q4_K_M \| 4.36GB \| \| [krx-Qwen2.5-7B-Instruct-X-Series-Only-5.Q4_1.gguf](https://huggingface.co/RichardErkhov/2point5p_-_krx-Qwen2.5-7B-Instruct-X-Series-Only-5-gguf/blob/main/krx-Qwen2.5-7B-Instruct-X-Series-Only-5.Q4_1.gguf) \| Q4_1 \| 4.54GB \| \| [krx-Qwen2.5-7B-Instruct-X-Series-Only-5.Q5_0.gguf](https://huggingface.co/RichardErkhov/2point5p_-_krx-Qwen2.5-7B-Instruct-X-Series-Only-5-gguf/blob/main/krx-Qwen2.5-7B-Instruct-X-Series-Only-5.Q5_0.gguf) \| Q5_0 \| 4.95GB \| \| [krx-Qwen2.5-7B-Instruct-X-Series-Only-5.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/2point5p_-_krx-Qwen2.5-7B-Instruct-X-Series-Only-5-gguf/blob/main/krx-Qwen2.5-7B-Instruct-X-Series-Only-5.Q5_K_S.gguf) \| Q5_K_S \| 4.95GB \| \| [krx-Qwen2.5-7B-Instruct-X-Series-Only-5.Q5_K.gguf](https://huggingface.co/RichardErkhov/2point5p_-_krx-Qwen2.5-7B-Instruct-X-Series-Only-5-gguf/blob/main/krx-Qwen2.5-7B-Instruct-X-Series-Only-5.Q5_K.gguf) \| Q5_K \| 5.07GB \| \| [krx-Qwen2.5-7B-Instruct-X-Series-Only-5.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/2point5p_-_krx-Qwen2.5-7B-Instruct-X-Series-Only-5-gguf/blob/main/krx-Qwen2.5-7B-Instruct-X-Series-Only-5.Q5_K_M.gguf) \| Q5_K_M \| 5.07GB \| \| [krx-Qwen2.5-7B-Instruct-X-Series-Only-5.Q5_1.gguf](https://huggingface.co/RichardErkhov/2point5p_-_krx-Qwen2.5-7B-Instruct-X-Series-Only-5-gguf/blob/main/krx-Qwen2.5-7B-Instruct-X-Series-Only-5.Q5_1.gguf) \| Q5_1 \| 5.36GB \| \| [krx-Qwen2.5-7B-Instruct-X-Series-Only-5.Q6_K.gguf](https://huggingface.co/RichardErkhov/2point5p_-_krx-Qwen2.5-7B-Instruct-X-Series-Only-5-gguf/blob/main/krx-Qwen2.5-7B-Instruct-X-Series-Only-5.Q6_K.gguf) \| Q6_K \| 5.82GB \| \| [krx-Qwen2.5-7B-Instruct-X-Series-Only-5.Q8_0.gguf](https://huggingface.co/RichardErkhov/2point5p_-_krx-Qwen2.5-7B-Instruct-X-Series-Only-5-gguf/blob/main/krx-Qwen2.5-7B-Instruct-X-Series-Only-5.Q8_0.gguf) \| Q8_0 \| 7.54GB \| Original model description: --- base_model: unsloth/Qwen2.5-7B-Instruct tags: - text-generation-inference - transformers - unsloth - qwen2 - trl license: apache-2.0 language: - en --- # Uploaded model - Developed by: 2point5p - License: apache-2.0 - Finetuned from model : unsloth/Qwen2.5-7B-Instruct This qwen2 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
JMYEO/roberta-base-klue-ynat-classification	JMYEO	2025-04-27T09:18:18Z	0	0	transformers	[ "transformers", "safetensors", "roberta", "text-classification", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	2025-04-27T09:16:54Z	--- 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]
sanikadhayabar/Text2Image_GenAI	sanikadhayabar	2025-04-27T08:46:54Z	0	0	diffusers	[ "diffusers", "safetensors", "license:creativeml-openrail-m", "region:us" ]	null	2025-04-27T07:33:55Z	--- license: creativeml-openrail-m ---
axingd/asssss	axingd	2025-04-27T08:38:14Z	0	0	null	[ "region:us" ]	null	2024-12-25T08:17:21Z	# awewa <Gallery /> ## Model description aaefa ## Download model [Download](/axingd/asssss/tree/main) them in the Files & versions tab.
genki10/BERT_V8_sp10_lw40_ex50_lo50_k10_k10_fold0	genki10	2025-04-27T05:50:20Z	0	0	transformers	[ "transformers", "pytorch", "bert", "text-classification", "generated_from_trainer", "base_model:google-bert/bert-base-uncased", "base_model:finetune:google-bert/bert-base-uncased", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	2025-04-27T05:30:30Z	--- library_name: transformers license: apache-2.0 base_model: bert-base-uncased tags: - generated_from_trainer model-index: - name: BERT_V8_sp10_lw40_ex50_lo50_k10_k10_fold0 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. --> # BERT_V8_sp10_lw40_ex50_lo50_k10_k10_fold0 This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.6901 - Qwk: 0.3941 - Mse: 0.6901 - Rmse: 0.8307 ## 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: 64 - eval_batch_size: 64 - seed: 42 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: linear - num_epochs: 100 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Qwk \| Mse \| Rmse \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:------:\|:------:\|:------:\| \| No log \| 1.0 \| 5 \| 5.7260 \| 0.0370 \| 5.7260 \| 2.3929 \| \| No log \| 2.0 \| 10 \| 2.7623 \| 0.0017 \| 2.7623 \| 1.6620 \| \| No log \| 3.0 \| 15 \| 1.2733 \| 0.0316 \| 1.2733 \| 1.1284 \| \| No log \| 4.0 \| 20 \| 0.7739 \| 0.1276 \| 0.7739 \| 0.8797 \| \| No log \| 5.0 \| 25 \| 0.7644 \| 0.0892 \| 0.7644 \| 0.8743 \| \| No log \| 6.0 \| 30 \| 0.7670 \| 0.3174 \| 0.7670 \| 0.8758 \| \| No log \| 7.0 \| 35 \| 0.7857 \| 0.3099 \| 0.7857 \| 0.8864 \| \| No log \| 8.0 \| 40 \| 0.5947 \| 0.4124 \| 0.5947 \| 0.7712 \| \| No log \| 9.0 \| 45 \| 0.5186 \| 0.5081 \| 0.5186 \| 0.7201 \| \| No log \| 10.0 \| 50 \| 0.5195 \| 0.5872 \| 0.5195 \| 0.7208 \| \| No log \| 11.0 \| 55 \| 0.5250 \| 0.5769 \| 0.5250 \| 0.7246 \| \| No log \| 12.0 \| 60 \| 0.9675 \| 0.3770 \| 0.9675 \| 0.9836 \| \| No log \| 13.0 \| 65 \| 0.7345 \| 0.4078 \| 0.7345 \| 0.8570 \| \| No log \| 14.0 \| 70 \| 1.0105 \| 0.2675 \| 1.0105 \| 1.0052 \| \| No log \| 15.0 \| 75 \| 0.5970 \| 0.4941 \| 0.5970 \| 0.7727 \| \| No log \| 16.0 \| 80 \| 0.6469 \| 0.4418 \| 0.6469 \| 0.8043 \| \| No log \| 17.0 \| 85 \| 0.7103 \| 0.4319 \| 0.7103 \| 0.8428 \| \| No log \| 18.0 \| 90 \| 0.7124 \| 0.4384 \| 0.7124 \| 0.8440 \| \| No log \| 19.0 \| 95 \| 0.7826 \| 0.3195 \| 0.7826 \| 0.8847 \| \| No log \| 20.0 \| 100 \| 0.8518 \| 0.3749 \| 0.8518 \| 0.9229 \| \| No log \| 21.0 \| 105 \| 0.8020 \| 0.3253 \| 0.8020 \| 0.8956 \| \| No log \| 22.0 \| 110 \| 0.9318 \| 0.2382 \| 0.9318 \| 0.9653 \| \| No log \| 23.0 \| 115 \| 0.7316 \| 0.4107 \| 0.7316 \| 0.8554 \| \| No log \| 24.0 \| 120 \| 0.7098 \| 0.4125 \| 0.7098 \| 0.8425 \| \| No log \| 25.0 \| 125 \| 0.6954 \| 0.4353 \| 0.6954 \| 0.8339 \| \| No log \| 26.0 \| 130 \| 0.7140 \| 0.4237 \| 0.7140 \| 0.8450 \| \| No log \| 27.0 \| 135 \| 0.8637 \| 0.2969 \| 0.8637 \| 0.9294 \| \| No log \| 28.0 \| 140 \| 0.9314 \| 0.2674 \| 0.9314 \| 0.9651 \| \| No log \| 29.0 \| 145 \| 0.7791 \| 0.3816 \| 0.7791 \| 0.8827 \| \| No log \| 30.0 \| 150 \| 0.7999 \| 0.3926 \| 0.7999 \| 0.8944 \| \| No log \| 31.0 \| 155 \| 0.9336 \| 0.2478 \| 0.9336 \| 0.9662 \| \| No log \| 32.0 \| 160 \| 0.6832 \| 0.4438 \| 0.6832 \| 0.8265 \| \| No log \| 33.0 \| 165 \| 1.0714 \| 0.3082 \| 1.0714 \| 1.0351 \| \| No log \| 34.0 \| 170 \| 1.0028 \| 0.2794 \| 1.0028 \| 1.0014 \| \| No log \| 35.0 \| 175 \| 0.6595 \| 0.4270 \| 0.6595 \| 0.8121 \| \| No log \| 36.0 \| 180 \| 0.9362 \| 0.2646 \| 0.9362 \| 0.9676 \| \| No log \| 37.0 \| 185 \| 0.7444 \| 0.3856 \| 0.7444 \| 0.8628 \| \| No log \| 38.0 \| 190 \| 0.6963 \| 0.4153 \| 0.6963 \| 0.8345 \| \| No log \| 39.0 \| 195 \| 0.9037 \| 0.2594 \| 0.9037 \| 0.9506 \| \| No log \| 40.0 \| 200 \| 0.6901 \| 0.3941 \| 0.6901 \| 0.8307 \| ### Framework versions - Transformers 4.51.1 - Pytorch 2.5.1+cu124 - Datasets 3.5.0 - Tokenizers 0.21.0
robiulawaldev/39a4acb9-997a-4170-9aec-8dc852a8ba82	robiulawaldev	2025-04-27T04:08:14Z	0	0	peft	[ "peft", "generated_from_trainer", "base_model:aisingapore/Llama-SEA-LION-v2-8B-IT", "base_model:adapter:aisingapore/Llama-SEA-LION-v2-8B-IT", "region:us" ]	null	2025-04-27T04:07:48Z	--- library_name: peft tags: - generated_from_trainer base_model: aisingapore/llama3-8b-cpt-sea-lionv2.1-instruct model-index: - name: robiulawaldev/39a4acb9-997a-4170-9aec-8dc852a8ba82 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. --> # robiulawaldev/39a4acb9-997a-4170-9aec-8dc852a8ba82 This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.0022 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ### Framework versions - PEFT 0.13.2 - Transformers 4.46.3 - Pytorch 2.5.1+cu124 - Datasets 3.1.0 - Tokenizers 0.20.3
privetin/Llama-3.2-1B-Q2_K-GGUF	privetin	2025-04-27T03:07:08Z	0	0	transformers	[ "transformers", "gguf", "facebook", "meta", "pytorch", "llama", "llama-3", "llama-cpp", "gguf-my-repo", "text-generation", "en", "de", "fr", "it", "pt", "hi", "es", "th", "base_model:meta-llama/Llama-3.2-1B", "base_model:quantized:meta-llama/Llama-3.2-1B", "license:llama3.2", "endpoints_compatible", "region:us" ]	text-generation	2025-04-27T03:06:58Z	--- base_model: meta-llama/Llama-3.2-1B language: - en - de - fr - it - pt - hi - es - th library_name: transformers license: llama3.2 pipeline_tag: text-generation tags: - facebook - meta - pytorch - llama - llama-3 - llama-cpp - gguf-my-repo extra_gated_prompt: "### LLAMA 3.2 COMMUNITY LICENSE AGREEMENT\n\nLlama 3.2 Version\ \ Release Date: September 25, 2024\n\n“Agreement” means the terms and conditions\ \ for use, reproduction, distribution and modification of the Llama Materials set\ \ forth herein.\n\n“Documentation” means the specifications, manuals and documentation\ \ accompanying Llama 3.2 distributed by Meta at https://llama.meta.com/doc/overview.\n\ \n“Licensee” or “you” means you, or your employer or any other person or entity\ \ (if you are entering into this Agreement on such person or entity’s behalf),\ \ of the age required under applicable laws, rules or regulations to provide legal\ \ consent and that has legal authority to bind your employer or such other person\ \ or entity if you are entering in this Agreement on their behalf.\n\n“Llama 3.2”\ \ means the foundational large language models and software and algorithms, including\ \ machine-learning model code, trained model weights, inference-enabling code, training-enabling\ \ code, fine-tuning enabling code and other elements of the foregoing distributed\ \ by Meta at https://www.llama.com/llama-downloads.\n\n“Llama Materials” means,\ \ collectively, Meta’s proprietary Llama 3.2 and Documentation (and any portion\ \ thereof) made available under this Agreement.\n\n“Meta” or “we” means Meta Platforms\ \ Ireland Limited (if you are located in or, if you are an entity, your principal\ \ place of business is in the EEA or Switzerland) and Meta Platforms, Inc. (if\ \ you are located outside of the EEA or Switzerland). \n\nBy clicking “I Accept”\ \ below or by using or distributing any portion or element of the Llama Materials,\ \ you agree to be bound by this Agreement.\n\n1. License Rights and Redistribution.\n\ a. Grant of Rights. You are granted a non-exclusive, worldwide, non-transferable\ \ and royalty-free limited license under Meta’s intellectual property or other rights\ \ owned by Meta embodied in the Llama Materials to use, reproduce, distribute,\ \ copy, create derivative works of, and make modifications to the Llama Materials.\ \ \nb. Redistribution and Use. \ni. If you distribute or make available the Llama\ \ Materials (or any derivative works thereof), or a product or service (including\ \ another AI model) that contains any of them, you shall (A) provide a copy of this\ \ Agreement with any such Llama Materials; and (B) prominently display “Built with\ \ Llama” on a related website, user interface, blogpost, about page, or product\ \ documentation. If you use the Llama Materials or any outputs or results of the\ \ Llama Materials to create, train, fine tune, or otherwise improve an AI model,\ \ which is distributed or made available, you shall also include “Llama” at the\ \ beginning of any such AI model name.\nii. If you receive Llama Materials, or any\ \ derivative works thereof, from a Licensee as part of an integrated end user product,\ \ then Section 2 of this Agreement will not apply to you. \niii. You must retain\ \ in all copies of the Llama Materials that you distribute the following attribution\ \ notice within a “Notice” text file distributed as a part of such copies: “Llama\ \ 3.2 is licensed under the Llama 3.2 Community License, Copyright © Meta Platforms,\ \ Inc. All Rights Reserved.”\niv. Your use of the Llama Materials must comply with\ \ applicable laws and regulations (including trade compliance laws and regulations)\ \ and adhere to the Acceptable Use Policy for the Llama Materials (available at\ \ https://www.llama.com/llama3_2/use-policy), which is hereby incorporated by reference\ \ into this Agreement.\n \n2. Additional Commercial Terms. If, on the Llama 3.2\ \ version release date, the monthly active users of the products or services made\ \ available by or for Licensee, or Licensee’s affiliates, is greater than 700 million\ \ monthly active users in the preceding calendar month, you must request a license\ \ from Meta, which Meta may grant to you in its sole discretion, and you are not\ \ authorized to exercise any of the rights under this Agreement unless or until\ \ Meta otherwise expressly grants you such rights.\n3. Disclaimer of Warranty. UNLESS\ \ REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS THEREFROM\ \ ARE PROVIDED ON AN “AS IS” BASIS, WITHOUT WARRANTIES OF ANY KIND, AND META DISCLAIMS\ \ ALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND IMPLIED, INCLUDING, WITHOUT LIMITATION,\ \ ANY WARRANTIES OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR\ \ PURPOSE. YOU ARE SOLELY RESPONSIBLE FOR DETERMINING THE APPROPRIATENESS OF USING\ \ OR REDISTRIBUTING THE LLAMA MATERIALS AND ASSUME ANY RISKS ASSOCIATED WITH YOUR\ \ USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS.\n4. Limitation of Liability.\ \ IN NO EVENT WILL META OR ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY,\ \ WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING\ \ OUT OF THIS AGREEMENT, FOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL,\ \ INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN IF META OR ITS AFFILIATES HAVE\ \ BEEN ADVISED OF THE POSSIBILITY OF ANY OF THE FOREGOING.\n5. Intellectual Property.\n\ a. No trademark licenses are granted under this Agreement, and in connection with\ \ the Llama Materials, neither Meta nor Licensee may use any name or mark owned\ \ by or associated with the other or any of its affiliates, except as required\ \ for reasonable and customary use in describing and redistributing the Llama Materials\ \ or as set forth in this Section 5(a). Meta hereby grants you a license to use\ \ “Llama” (the “Mark”) solely as required to comply with the last sentence of Section\ \ 1.b.i. You will comply with Meta’s brand guidelines (currently accessible at\ \ https://about.meta.com/brand/resources/meta/company-brand/). All goodwill arising\ \ out of your use of the Mark will inure to the benefit of Meta.\nb. Subject to\ \ Meta’s ownership of Llama Materials and derivatives made by or for Meta, with\ \ respect to any derivative works and modifications of the Llama Materials that\ \ are made by you, as between you and Meta, you are and will be the owner of such\ \ derivative works and modifications.\nc. If you institute litigation or other proceedings\ \ against Meta or any entity (including a cross-claim or counterclaim in a lawsuit)\ \ alleging that the Llama Materials or Llama 3.2 outputs or results, or any portion\ \ of any of the foregoing, constitutes infringement of intellectual property or\ \ other rights owned or licensable by you, then any licenses granted to you under\ \ this Agreement shall terminate as of the date such litigation or claim is filed\ \ or instituted. You will indemnify and hold harmless Meta from and against any\ \ claim by any third party arising out of or related to your use or distribution\ \ of the Llama Materials.\n6. Term and Termination. The term of this Agreement will\ \ commence upon your acceptance of this Agreement or access to the Llama Materials\ \ and will continue in full force and effect until terminated in accordance with\ \ the terms and conditions herein. Meta may terminate this Agreement if you are\ \ in breach of any term or condition of this Agreement. Upon termination of this\ \ Agreement, you shall delete and cease use of the Llama Materials. Sections 3,\ \ 4 and 7 shall survive the termination of this Agreement. \n7. Governing Law and\ \ Jurisdiction. This Agreement will be governed and construed under the laws of\ \ the State of California without regard to choice of law principles, and the UN\ \ Convention on Contracts for the International Sale of Goods does not apply to\ \ this Agreement. The courts of California shall have exclusive jurisdiction of\ \ any dispute arising out of this Agreement. \n### Llama 3.2 Acceptable Use Policy\n\ Meta is committed to promoting safe and fair use of its tools and features, including\ \ Llama 3.2. If you access or use Llama 3.2, you agree to this Acceptable Use Policy\ \ (“Policy”). The most recent copy of this policy can be found at [https://www.llama.com/llama3_2/use-policy](https://www.llama.com/llama3_2/use-policy).\n\ #### Prohibited Uses\nWe want everyone to use Llama 3.2 safely and responsibly.\ \ You agree you will not use, or allow others to use, Llama 3.2 to:\n1. Violate\ \ the law or others’ rights, including to:\n 1. Engage in, promote, generate,\ \ contribute to, encourage, plan, incite, or further illegal or unlawful activity\ \ or content, such as:\n 1. Violence or terrorism\n 2. Exploitation\ \ or harm to children, including the solicitation, creation, acquisition, or dissemination\ \ of child exploitative content or failure to report Child Sexual Abuse Material\n\ \ 3. Human trafficking, exploitation, and sexual violence\n 4. The\ \ illegal distribution of information or materials to minors, including obscene\ \ materials, or failure to employ legally required age-gating in connection with\ \ such information or materials.\n 5. Sexual solicitation\n 6. Any\ \ other criminal activity\n 1. Engage in, promote, incite, or facilitate the\ \ harassment, abuse, threatening, or bullying of individuals or groups of individuals\n\ \ 2. Engage in, promote, incite, or facilitate discrimination or other unlawful\ \ or harmful conduct in the provision of employment, employment benefits, credit,\ \ housing, other economic benefits, or other essential goods and services\n 3.\ \ Engage in the unauthorized or unlicensed practice of any profession including,\ \ but not limited to, financial, legal, medical/health, or related professional\ \ practices\n 4. Collect, process, disclose, generate, or infer private or sensitive\ \ information about individuals, including information about individuals’ identity,\ \ health, or demographic information, unless you have obtained the right to do so\ \ in accordance with applicable law\n 5. Engage in or facilitate any action or\ \ generate any content that infringes, misappropriates, or otherwise violates any\ \ third-party rights, including the outputs or results of any products or services\ \ using the Llama Materials\n 6. Create, generate, or facilitate the creation\ \ of malicious code, malware, computer viruses or do anything else that could disable,\ \ overburden, interfere with or impair the proper working, integrity, operation\ \ or appearance of a website or computer system\n 7. Engage in any action, or\ \ facilitate any action, to intentionally circumvent or remove usage restrictions\ \ or other safety measures, or to enable functionality disabled by Meta \n2. Engage\ \ in, promote, incite, facilitate, or assist in the planning or development of activities\ \ that present a risk of death or bodily harm to individuals, including use of Llama\ \ 3.2 related to the following:\n 8. Military, warfare, nuclear industries or\ \ applications, espionage, use for materials or activities that are subject to the\ \ International Traffic Arms Regulations (ITAR) maintained by the United States\ \ Department of State or to the U.S. Biological Weapons Anti-Terrorism Act of 1989\ \ or the Chemical Weapons Convention Implementation Act of 1997\n 9. Guns and\ \ illegal weapons (including weapon development)\n 10. Illegal drugs and regulated/controlled\ \ substances\n 11. Operation of critical infrastructure, transportation technologies,\ \ or heavy machinery\n 12. Self-harm or harm to others, including suicide, cutting,\ \ and eating disorders\n 13. Any content intended to incite or promote violence,\ \ abuse, or any infliction of bodily harm to an individual\n3. Intentionally deceive\ \ or mislead others, including use of Llama 3.2 related to the following:\n 14.\ \ Generating, promoting, or furthering fraud or the creation or promotion of disinformation\n\ \ 15. Generating, promoting, or furthering defamatory content, including the\ \ creation of defamatory statements, images, or other content\n 16. Generating,\ \ promoting, or further distributing spam\n 17. Impersonating another individual\ \ without consent, authorization, or legal right\n 18. Representing that the\ \ use of Llama 3.2 or outputs are human-generated\n 19. Generating or facilitating\ \ false online engagement, including fake reviews and other means of fake online\ \ engagement \n4. Fail to appropriately disclose to end users any known dangers\ \ of your AI system 5. Interact with third party tools, models, or software designed\ \ to generate unlawful content or engage in unlawful or harmful conduct and/or represent\ \ that the outputs of such tools, models, or software are associated with Meta or\ \ Llama 3.2\n\nWith respect to any multimodal models included in Llama 3.2, the\ \ rights granted under Section 1(a) of the Llama 3.2 Community License Agreement\ \ are not being granted to you if you are an individual domiciled in, or a company\ \ with a principal place of business in, the European Union. This restriction does\ \ not apply to end users of a product or service that incorporates any such multimodal\ \ models.\n\nPlease report any violation of this Policy, software “bug,” or other\ \ problems that could lead to a violation of this Policy through one of the following\ \ means:\n\n* Reporting issues with the model: [https://github.com/meta-llama/llama-models/issues](https://l.workplace.com/l.php?u=https%3A%2F%2Fgithub.com%2Fmeta-llama%2Fllama-models%2Fissues&h=AT0qV8W9BFT6NwihiOHRuKYQM_UnkzN_NmHMy91OT55gkLpgi4kQupHUl0ssR4dQsIQ8n3tfd0vtkobvsEvt1l4Ic6GXI2EeuHV8N08OG2WnbAmm0FL4ObkazC6G_256vN0lN9DsykCvCqGZ)\n\ * Reporting risky content generated by the model: [developers.facebook.com/llama_output_feedback](http://developers.facebook.com/llama_output_feedback)\n\ * Reporting bugs and security concerns: [facebook.com/whitehat/info](http://facebook.com/whitehat/info)\n\ * Reporting violations of the Acceptable Use Policy or unlicensed uses of Llama\ \ 3.2: [email protected]" extra_gated_fields: First Name: text Last Name: text Date of birth: date_picker Country: country Affiliation: text Job title: type: select options: - Student - Research Graduate - AI researcher - AI developer/engineer - Reporter - Other geo: ip_location ? By clicking Submit below I accept the terms of the license and acknowledge that the information I provide will be collected stored processed and shared in accordance with the Meta Privacy Policy : checkbox extra_gated_description: The information you provide will be collected, stored, processed and shared in accordance with the [Meta Privacy Policy](https://www.facebook.com/privacy/policy/). extra_gated_button_content: Submit --- # privetin/Llama-3.2-1B-Q2_K-GGUF This model was converted to GGUF format from [`meta-llama/Llama-3.2-1B`](https://huggingface.co/meta-llama/Llama-3.2-1B) 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/meta-llama/Llama-3.2-1B) 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 privetin/Llama-3.2-1B-Q2_K-GGUF --hf-file llama-3.2-1b-q2_k.gguf -p "The meaning to life and the universe is" ``` ### Server: ```bash llama-server --hf-repo privetin/Llama-3.2-1B-Q2_K-GGUF --hf-file llama-3.2-1b-q2_k.gguf -c 2048 ``` Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well. Step 1: Clone llama.cpp from GitHub. ``` git clone https://github.com/ggerganov/llama.cpp ``` Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux). ``` cd llama.cpp && LLAMA_CURL=1 make ``` Step 3: Run inference through the main binary. ``` ./llama-cli --hf-repo privetin/Llama-3.2-1B-Q2_K-GGUF --hf-file llama-3.2-1b-q2_k.gguf -p "The meaning to life and the universe is" ``` or ``` ./llama-server --hf-repo privetin/Llama-3.2-1B-Q2_K-GGUF --hf-file llama-3.2-1b-q2_k.gguf -c 2048 ```
Tesslate/UIGEN-T2-7B-7100	Tesslate	2025-04-27T00:02:13Z	0	0	transformers	[ "transformers", "safetensors", "qwen2", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-04-26T23:57:14Z	--- 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]
yqyqyq123/Qwen2-0.5B-SFT-GRPO-4	yqyqyq123	2025-04-26T21:34:16Z	0	0	transformers	[ "transformers", "tensorboard", "safetensors", "generated_from_trainer", "trl", "grpo", "dataset:AI-MO/NuminaMath-TIR", "arxiv:2402.03300", "base_model:Qwen/Qwen2-0.5B-Instruct", "base_model:finetune:Qwen/Qwen2-0.5B-Instruct", "endpoints_compatible", "region:us" ]	null	2025-04-26T17:07:20Z	--- base_model: Qwen/Qwen2-0.5B-Instruct datasets: AI-MO/NuminaMath-TIR library_name: transformers model_name: Qwen2-0.5B-SFT-GRPO-4 tags: - generated_from_trainer - trl - grpo licence: license --- # Model Card for Qwen2-0.5B-SFT-GRPO-4 This model is a fine-tuned version of [Qwen/Qwen2-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2-0.5B-Instruct) on the [AI-MO/NuminaMath-TIR](https://huggingface.co/datasets/AI-MO/NuminaMath-TIR) 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="yqyqyq123/Qwen2-0.5B-SFT-GRPO-4", 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: 0.14.0 - Transformers: 4.47.1 - Pytorch: 2.6.0+cu124 - Datasets: 3.2.0 - Tokenizers: 0.21.1 ## Citations Cite GRPO as: ```bibtex @article{zhihong2024deepseekmath, title = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}}, author = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo}, year = 2024, eprint = {arXiv:2402.03300}, } ``` Cite TRL as: ```bibtex @misc{vonwerra2022trl, title = {{TRL: Transformer Reinforcement Learning}}, author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec}, year = 2020, journal = {GitHub repository}, publisher = {GitHub}, howpublished = {\url{https://github.com/huggingface/trl}} } ```
Omarmoh22/qwen7b-mentalhealth-chatbot	Omarmoh22	2025-04-26T20:18:44Z	0	0	transformers	[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2025-04-26T20:18:30Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
dilarayavuz/md-benign-imdb-part-32-bert-base-uncased	dilarayavuz	2025-04-26T19:39:46Z	0	0	transformers	[ "transformers", "tensorboard", "safetensors", "bert", "text-classification", "autotrain", "base_model:google-bert/bert-base-uncased", "base_model:finetune:google-bert/bert-base-uncased", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	2025-04-26T19:37:34Z	--- library_name: transformers tags: - autotrain - text-classification base_model: google-bert/bert-base-uncased widget: - text: "I love AutoTrain" --- # Model Trained Using AutoTrain - Problem type: Text Classification ## Validation Metrics loss: 0.26311248540878296 f1: 0.9053140096618357 precision: 0.8847969782813976 recall: 0.9268051434223541 auc: 0.9611392978550404 accuracy: 0.902
tiny-random/qwen2.5-omni	tiny-random	2025-04-26T18:11:09Z	60	0	transformers	[ "transformers", "safetensors", "qwen2_5_omni", "text-to-audio", "any-to-any", "endpoints_compatible", "region:us" ]	any-to-any	2025-03-28T09:28:29Z	--- library_name: transformers pipeline_tag: any-to-any inference: true widget: - text: Hello! example_title: Hello world group: Python --- This tiny model is for debugging. It is randomly initialized with the config adapted from [Qwen/Qwen2.5-Omni-7B](https://huggingface.co/Qwen/Qwen2.5-Omni-7B). ### Example usage: ```python import unittest import torch import soundfile as sf from qwen_omni_utils import process_mm_info from transformers import ( Qwen2_5OmniForConditionalGeneration, Qwen2_5OmniPreTrainedModel, Qwen2_5OmniProcessor, ) model_id = "tiny-random/qwen2.5-omni" # model = Qwen2_5OmniModel.from_pretrained(model_id, torch_dtype="auto", device_map="auto").eval() # We recommend enabling flash_attention_2 for better acceleration and memory saving. Qwen2_5OmniPreTrainedModel._init_weights = unittest.mock.Mock() model = Qwen2_5OmniForConditionalGeneration.from_pretrained( model_id, torch_dtype="auto", device_map="auto", attn_implementation="flash_attention_2", ).eval() processor = Qwen2_5OmniProcessor.from_pretrained(model_id) conversation = [ { "role": "system", "content": [ {"type": "text", "text": "You are Qwen, a virtual human developed by the Qwen Team, Alibaba Group, capable of perceiving auditory and visual inputs, as well as generating text and speech."} ], }, { "role": "user", "content": [ {"type": "text", "text": "Hi, can you tell me a joke?"}, # {"type": "audio", "audio": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"}, # {"type": "video", "video": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen2.5-Omni/draw.mp4"}, {"type": "image", "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg"}, ], }, ] # Preparation for inference text = processor.apply_chat_template(conversation, add_generation_prompt=True, tokenize=False) audios, images, videos = process_mm_info(conversation, use_audio_in_video=True) print('Audios:', audios) print('Images:', images) print('Videos:', videos) inputs = processor(text=text, audios=audios, images=images, videos=videos, return_tensors="pt", padding=True) inputs = inputs.to(model.device).to(model.dtype) # Inference: Generation of the output text and audio text_ids, audio = model.generate( *inputs, use_audio_in_video=True, thinker_max_new_tokens=16, talker_max_new_tokens=16, temperature=0.1, ) text = processor.batch_decode(text_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False) print(text, '\n' 3) sf.write( "/tmp/output.wav", audio.reshape(-1).detach().cpu().numpy(), samplerate=24000, ) ``` ### Codes to create this repo: ```python import unittest from pathlib import Path import torch import accelerate from huggingface_hub import hf_hub_download from transformers import ( AutoConfig, AutoModelForCausalLM, AutoTokenizer, GenerationConfig, Qwen2_5OmniForConditionalGeneration, Qwen2_5OmniPreTrainedModel, Qwen2_5OmniProcessor, pipeline, set_seed, ) source_model_id = "Qwen/Qwen2.5-Omni-7B" save_folder = "/tmp/tiny-random/qwen2.5-omni" processor = Qwen2_5OmniProcessor.from_pretrained( source_model_id, trust_remote_code=True, ) processor.save_pretrained(save_folder) config = AutoConfig.from_pretrained( source_model_id, trust_remote_code=True, ) OUTPUT_DIM = 16 config.talker_config.num_hidden_layers = 1 config.talker_config.hidden_size = 16 config.talker_config.embedding_size = OUTPUT_DIM config.talker_config.head_dim = 16 config.talker_config.num_attention_heads = 1 config.talker_config.num_key_value_heads = 1 config.talker_config.intermediate_size = 32 config.talker_config.rope_scaling['mrope_section'] = [2, 2, 4] assert 2 * sum(config.talker_config.rope_scaling['mrope_section'] ) == config.talker_config.hidden_size / config.talker_config.num_attention_heads config.thinker_config.audio_config.num_hidden_layers = 1 config.thinker_config.audio_config.encoder_layers = 1 config.thinker_config.audio_config.d_model = 16 config.thinker_config.audio_config.encoder_attention_heads = 1 config.thinker_config.audio_config.encoder_ffn_dim = 32 config.thinker_config.audio_config.output_dim = OUTPUT_DIM config.thinker_config.text_config.num_hidden_layers = 1 config.thinker_config.text_config.hidden_size = OUTPUT_DIM config.thinker_config.text_config.intermediate_size = 32 config.thinker_config.text_config.num_attention_heads = 1 config.thinker_config.text_config.num_key_value_heads = 1 config.thinker_config.text_config.rope_scaling['mrope_section'] = [2, 2, 4] assert 2 * sum(config.thinker_config.text_config.rope_scaling['mrope_section'] ) == config.thinker_config.text_config.hidden_size / config.thinker_config.text_config.num_attention_heads config.thinker_config.vision_config.depth = 2 config.thinker_config.vision_config.embed_dim = 16 config.thinker_config.vision_config.hidden_size = 16 config.thinker_config.vision_config.intermediate_size = 32 config.thinker_config.vision_config.out_hidden_size = OUTPUT_DIM config.thinker_config.vision_config.num_heads = 1 config.thinker_config.vision_config.fullatt_block_indexes = [1] config.token2wav_config.bigvgan_config.resblock_dilation_sizes = [[1, 3, 5]] config.token2wav_config.bigvgan_config.resblock_kernel_sizes = [7] config.token2wav_config.bigvgan_config.upsample_initial_channel = 32 config.token2wav_config.bigvgan_config.upsample_kernel_sizes = [11, 4] config.token2wav_config.bigvgan_config.upsample_rates = [5, 2] config.token2wav_config.dit_config.depth = 2 config.token2wav_config.dit_config.num_hidden_layers = 2 config.token2wav_config.dit_config.hidden_size = 16 config.token2wav_config.dit_config.dim = 16 config.token2wav_config.dit_config.emb_dim = 16 config.token2wav_config.dit_config.enc_attention_channels = 16 config.token2wav_config.dit_config.enc_channels = [32, 32, 32] config.token2wav_config.dit_config.enc_dilations = [1, 3, 4] config.token2wav_config.dit_config.enc_kernel_sizes = [5, 3, 1] config.token2wav_config.dit_config.enc_dim = 16 config.token2wav_config.dit_config.enc_emb_dim = 16 config.token2wav_config.dit_config.enc_lin_neurons = 16 config.token2wav_config.dit_config.head_dim = 16 config.token2wav_config.dit_config.num_attention_heads = 1 config.token2wav_config.dit_config.heads = 1 config.token2wav_config.dit_config.look_ahead_layers = [1] config.token2wav_config.dit_config.look_backward_layers = [0] # avoid mismatch in vocab size because this is random model! config.token2wav_config.dit_config.num_embeds = config.talker_config.vocab_size print(config) spk_dict = torch.load(hf_hub_download(source_model_id, 'spk_dict.pt', repo_type='model')) for _, info in spk_dict.items(): info['cond'] = info['cond'][:, :config.token2wav_config.dit_config.enc_emb_dim].clone() torch.save(spk_dict, Path(save_folder, "spk_dict.pt")) # patch for non-affine layernorm Qwen2_5OmniPreTrainedModel._init_weights = unittest.mock.Mock() torch.set_default_dtype(torch.bfloat16) model = Qwen2_5OmniForConditionalGeneration( config, ) torch.set_default_dtype(torch.float32) model.generation_config = GenerationConfig.from_pretrained( source_model_id, trust_remote_code=True, ) set_seed(42) with torch.no_grad(): for name, p in sorted(model.named_parameters()): torch.nn.init.normal_(p, 0, 0.5) print(name, p.shape, p.dtype) model.save_pretrained(save_folder) ```
nawafalomari/test606	nawafalomari	2025-04-26T17:27:39Z	0	0	transformers	[ "transformers", "safetensors", "roberta", "text-classification", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	2025-04-26T17:26:36Z	--- 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]
BootesVoid/cm9y3d5of00t5qeqoibtx38m1_cm9y4acl900x9qeqo1zem939q	BootesVoid	2025-04-26T11:40:22Z	0	0	diffusers	[ "diffusers", "flux", "lora", "replicate", "text-to-image", "en", "base_model:black-forest-labs/FLUX.1-dev", "base_model:adapter:black-forest-labs/FLUX.1-dev", "license:other", "region:us" ]	text-to-image	2025-04-26T11:40:20Z	--- license: other license_name: flux-1-dev-non-commercial-license license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md language: - en tags: - flux - diffusers - lora - replicate base_model: "black-forest-labs/FLUX.1-dev" pipeline_tag: text-to-image # widget: # - text: >- # prompt # output: # url: https://... instance_prompt: SORA --- # Cm9Y3D5Of00T5Qeqoibtx38M1_Cm9Y4Acl900X9Qeqo1Zem939Q <Gallery /> ## About this LoRA This is a [LoRA](https://replicate.com/docs/guides/working-with-loras) for the FLUX.1-dev text-to-image model. It can be used with diffusers or ComfyUI. It was trained on [Replicate](https://replicate.com/) using AI toolkit: https://replicate.com/ostris/flux-dev-lora-trainer/train ## Trigger words You should use `SORA` to trigger the image generation. ## Run this LoRA with an API using Replicate ```py import replicate input = { "prompt": "SORA", "lora_weights": "https://huggingface.co/BootesVoid/cm9y3d5of00t5qeqoibtx38m1_cm9y4acl900x9qeqo1zem939q/resolve/main/lora.safetensors" } output = replicate.run( "black-forest-labs/flux-dev-lora", input=input ) for index, item in enumerate(output): with open(f"output_{index}.webp", "wb") as file: file.write(item.read()) ``` ## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers) ```py from diffusers import AutoPipelineForText2Image import torch pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.float16).to('cuda') pipeline.load_lora_weights('BootesVoid/cm9y3d5of00t5qeqoibtx38m1_cm9y4acl900x9qeqo1zem939q', weight_name='lora.safetensors') image = pipeline('SORA').images[0] ``` For more details, including weighting, merging and fusing LoRAs, check the [documentation on loading LoRAs in diffusers](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading_adapters) ## Training details - Steps: 2000 - Learning rate: 0.0004 - LoRA rank: 16 ## Contribute your own examples You can use the [community tab](https://huggingface.co/BootesVoid/cm9y3d5of00t5qeqoibtx38m1_cm9y4acl900x9qeqo1zem939q/discussions) to add images that show off what you’ve made with this LoRA.
Fe2kLXyF5R1uI/Fe2kLXyF5R1uI	Fe2kLXyF5R1uI	2025-04-26T11:12:22Z	0	0	null	[ "license:bigscience-openrail-m", "region:us" ]	null	2025-04-26T11:12:22Z	--- license: bigscience-openrail-m ---
secmlr/ruizhe_simplier_DSQWQNsy32kCln32kOss32k_DSNsyClnOss_QWQNsyClnOss_Qwen-7B_summarized_sft	secmlr	2025-04-26T09:09:54Z	0	0	transformers	[ "transformers", "safetensors", "qwen2", "text-generation", "llama-factory", "full", "generated_from_trainer", "conversational", "base_model:secmlr/DS-Noisy_DS-Clean_DS-OSS_QWQ-OSS_QWQ-Clean_QWQ-Noisy_Qwen2.5-7B-Instruct_full_sft_1e-5", "base_model:finetune:secmlr/DS-Noisy_DS-Clean_DS-OSS_QWQ-OSS_QWQ-Clean_QWQ-Noisy_Qwen2.5-7B-Instruct_full_sft_1e-5", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-04-26T06:03:44Z	--- library_name: transformers license: apache-2.0 base_model: secmlr/DS-Noisy_DS-Clean_DS-OSS_QWQ-OSS_QWQ-Clean_QWQ-Noisy_Qwen2.5-7B-Instruct_full_sft_1e-5 tags: - llama-factory - full - generated_from_trainer model-index: - name: ruizhe_simplier_DSQWQNsy32kCln32kOss32k_DSNsyClnOss_QWQNsyClnOss_Qwen-7B_summarized_sft 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. --> # ruizhe_simplier_DSQWQNsy32kCln32kOss32k_DSNsyClnOss_QWQNsyClnOss_Qwen-7B_summarized_sft This model is a fine-tuned version of [secmlr/DS-Noisy_DS-Clean_DS-OSS_QWQ-OSS_QWQ-Clean_QWQ-Noisy_Qwen2.5-7B-Instruct_full_sft_1e-5](https://huggingface.co/secmlr/DS-Noisy_DS-Clean_DS-OSS_QWQ-OSS_QWQ-Clean_QWQ-Noisy_Qwen2.5-7B-Instruct_full_sft_1e-5) on the ruizhe_simplier_reasoning_ds_clean_32k, the ruizhe_simplier_reasoning_ds_noisy_32k, the ruizhe_simplier_reasoning_ds_ossfuzz_32k, the ruizhe_simplier_reasoning_qwq_clean_32k, the ruizhe_simplier_reasoning_qwq_noisy_small_32k and the ruizhe_simplier_reasoning_qwq_ossfuzz_32k datasets. ## 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: 1 - eval_batch_size: 8 - seed: 42 - distributed_type: multi-GPU - num_devices: 4 - gradient_accumulation_steps: 12 - total_train_batch_size: 48 - total_eval_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: cosine - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 3.0 ### Training results ### Framework versions - Transformers 4.48.3 - Pytorch 2.6.0+cu124 - Datasets 3.2.0 - Tokenizers 0.21.0
BootesVoid/cm9xwj4s301f8rbgimq8ddli0_cm9xy8iqb007gqeqoscpt1syo	BootesVoid	2025-04-26T08:48:49Z	0	0	diffusers	[ "diffusers", "flux", "lora", "replicate", "text-to-image", "en", "base_model:black-forest-labs/FLUX.1-dev", "base_model:adapter:black-forest-labs/FLUX.1-dev", "license:other", "region:us" ]	text-to-image	2025-04-26T08:48:39Z	--- license: other license_name: flux-1-dev-non-commercial-license license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md language: - en tags: - flux - diffusers - lora - replicate base_model: "black-forest-labs/FLUX.1-dev" pipeline_tag: text-to-image # widget: # - text: >- # prompt # output: # url: https://... instance_prompt: JULIA --- # Cm9Xwj4S301F8Rbgimq8Ddli0_Cm9Xy8Iqb007Gqeqoscpt1Syo <Gallery /> ## About this LoRA This is a [LoRA](https://replicate.com/docs/guides/working-with-loras) for the FLUX.1-dev text-to-image model. It can be used with diffusers or ComfyUI. It was trained on [Replicate](https://replicate.com/) using AI toolkit: https://replicate.com/ostris/flux-dev-lora-trainer/train ## Trigger words You should use `JULIA` to trigger the image generation. ## Run this LoRA with an API using Replicate ```py import replicate input = { "prompt": "JULIA", "lora_weights": "https://huggingface.co/BootesVoid/cm9xwj4s301f8rbgimq8ddli0_cm9xy8iqb007gqeqoscpt1syo/resolve/main/lora.safetensors" } output = replicate.run( "black-forest-labs/flux-dev-lora", input=input ) for index, item in enumerate(output): with open(f"output_{index}.webp", "wb") as file: file.write(item.read()) ``` ## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers) ```py from diffusers import AutoPipelineForText2Image import torch pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.float16).to('cuda') pipeline.load_lora_weights('BootesVoid/cm9xwj4s301f8rbgimq8ddli0_cm9xy8iqb007gqeqoscpt1syo', weight_name='lora.safetensors') image = pipeline('JULIA').images[0] ``` For more details, including weighting, merging and fusing LoRAs, check the [documentation on loading LoRAs in diffusers](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading_adapters) ## Training details - Steps: 2000 - Learning rate: 0.0004 - LoRA rank: 16 ## Contribute your own examples You can use the [community tab](https://huggingface.co/BootesVoid/cm9xwj4s301f8rbgimq8ddli0_cm9xy8iqb007gqeqoscpt1syo/discussions) to add images that show off what you’ve made with this LoRA.
abdullahbhai302/yyyyy	abdullahbhai302	2025-04-26T07:46:09Z	0	1	null	[ "license:apache-2.0", "region:us" ]	null	2025-04-26T07:46:09Z	--- license: apache-2.0 ---
SRD1990/finetuning-sentiment-model-3000-samples	SRD1990	2025-04-26T04:23:46Z	0	0	transformers	[ "transformers", "tensorboard", "safetensors", "distilbert", "text-classification", "generated_from_trainer", "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	2025-04-26T03:48:47Z	--- library_name: transformers license: apache-2.0 base_model: distilbert-base-uncased tags: - generated_from_trainer metrics: - accuracy - f1 model-index: - name: finetuning-sentiment-model-3000-samples 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. --> # finetuning-sentiment-model-3000-samples This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.5372 - Accuracy: 0.8633 - F1: 0.8682 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: linear - num_epochs: 2 ### Training results ### Framework versions - Transformers 4.51.3 - Pytorch 2.6.0+cu124 - Datasets 3.5.0 - Tokenizers 0.21.1
vaishnavi0901/gemma-3-finetuneiamge-4b	vaishnavi0901	2025-04-26T03:18:38Z	0	0	transformers	[ "transformers", "text-generation-inference", "unsloth", "gemma3", "en", "base_model:unsloth/gemma-3-4b-it", "base_model:finetune:unsloth/gemma-3-4b-it", "license:apache-2.0", "endpoints_compatible", "region:us" ]	null	2025-04-26T03:18:23Z	--- base_model: unsloth/gemma-3-4b-it tags: - text-generation-inference - transformers - unsloth - gemma3 license: apache-2.0 language: - en --- # Uploaded finetuned model - Developed by: vaishnavi0901 - License: apache-2.0 - Finetuned from model : unsloth/gemma-3-4b-it This gemma3 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)
matheuspavan1/matheuspavan1-lorav2	matheuspavan1	2025-04-25T21:39:17Z	0	0	null	[ "license:other", "region:us" ]	null	2025-04-25T19:26:51Z	--- license: other license_name: flux-1-dev-non-commercial-license license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md ---
memevis/supp18	memevis	2025-04-25T17:29:05Z	0	0	transformers	[ "transformers", "safetensors", "qwen2", "text-generation", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-04-25T17:28:28Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
schyms0609/deepscaler-1.5B-preview-w4pc-gptq	schyms0609	2025-04-25T16:22:51Z	0	0	transformers	[ "transformers", "safetensors", "qwen2", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-04-25T16:15:40Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
mradermacher/C2S-Scale-Pythia-1b-pt-i1-GGUF	mradermacher	2025-04-25T15:53:10Z	0	0	transformers	[ "transformers", "gguf", "biology", "scRNAseq", "en", "base_model:vandijklab/C2S-Scale-Pythia-1b-pt", "base_model:quantized:vandijklab/C2S-Scale-Pythia-1b-pt", "license:cc-by-nc-nd-4.0", "endpoints_compatible", "region:us", "imatrix" ]	null	2025-04-25T10:06:14Z	--- base_model: vandijklab/C2S-Scale-Pythia-1b-pt language: - en library_name: transformers license: cc-by-nc-nd-4.0 quantized_by: mradermacher tags: - biology - scRNAseq --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: nicoboss --> weighted/imatrix quants of https://huggingface.co/vandijklab/C2S-Scale-Pythia-1b-pt <!-- provided-files --> static quants are available at https://huggingface.co/mradermacher/C2S-Scale-Pythia-1b-pt-GGUF ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) \| Link \| Type \| Size/GB \| Notes \| \|:-----\|:-----\|--------:\|:------\| \| [GGUF](https://huggingface.co/mradermacher/C2S-Scale-Pythia-1b-pt-i1-GGUF/resolve/main/C2S-Scale-Pythia-1b-pt.i1-IQ1_S.gguf) \| i1-IQ1_S \| 0.4 \| for the desperate \| \| [GGUF](https://huggingface.co/mradermacher/C2S-Scale-Pythia-1b-pt-i1-GGUF/resolve/main/C2S-Scale-Pythia-1b-pt.i1-IQ1_M.gguf) \| i1-IQ1_M \| 0.4 \| mostly desperate \| \| [GGUF](https://huggingface.co/mradermacher/C2S-Scale-Pythia-1b-pt-i1-GGUF/resolve/main/C2S-Scale-Pythia-1b-pt.i1-IQ2_XXS.gguf) \| i1-IQ2_XXS \| 0.4 \| \| \| [GGUF](https://huggingface.co/mradermacher/C2S-Scale-Pythia-1b-pt-i1-GGUF/resolve/main/C2S-Scale-Pythia-1b-pt.i1-IQ2_XS.gguf) \| i1-IQ2_XS \| 0.4 \| \| \| [GGUF](https://huggingface.co/mradermacher/C2S-Scale-Pythia-1b-pt-i1-GGUF/resolve/main/C2S-Scale-Pythia-1b-pt.i1-IQ2_S.gguf) \| i1-IQ2_S \| 0.5 \| \| \| [GGUF](https://huggingface.co/mradermacher/C2S-Scale-Pythia-1b-pt-i1-GGUF/resolve/main/C2S-Scale-Pythia-1b-pt.i1-IQ2_M.gguf) \| i1-IQ2_M \| 0.5 \| \| \| [GGUF](https://huggingface.co/mradermacher/C2S-Scale-Pythia-1b-pt-i1-GGUF/resolve/main/C2S-Scale-Pythia-1b-pt.i1-Q2_K_S.gguf) \| i1-Q2_K_S \| 0.5 \| very low quality \| \| [GGUF](https://huggingface.co/mradermacher/C2S-Scale-Pythia-1b-pt-i1-GGUF/resolve/main/C2S-Scale-Pythia-1b-pt.i1-Q2_K.gguf) \| i1-Q2_K \| 0.5 \| IQ3_XXS probably better \| \| [GGUF](https://huggingface.co/mradermacher/C2S-Scale-Pythia-1b-pt-i1-GGUF/resolve/main/C2S-Scale-Pythia-1b-pt.i1-IQ3_XXS.gguf) \| i1-IQ3_XXS \| 0.5 \| lower quality \| \| [GGUF](https://huggingface.co/mradermacher/C2S-Scale-Pythia-1b-pt-i1-GGUF/resolve/main/C2S-Scale-Pythia-1b-pt.i1-IQ3_XS.gguf) \| i1-IQ3_XS \| 0.6 \| \| \| [GGUF](https://huggingface.co/mradermacher/C2S-Scale-Pythia-1b-pt-i1-GGUF/resolve/main/C2S-Scale-Pythia-1b-pt.i1-IQ3_S.gguf) \| i1-IQ3_S \| 0.6 \| beats Q3_K* \| \| [GGUF](https://huggingface.co/mradermacher/C2S-Scale-Pythia-1b-pt-i1-GGUF/resolve/main/C2S-Scale-Pythia-1b-pt.i1-Q3_K_S.gguf) \| i1-Q3_K_S \| 0.6 \| IQ3_XS probably better \| \| [GGUF](https://huggingface.co/mradermacher/C2S-Scale-Pythia-1b-pt-i1-GGUF/resolve/main/C2S-Scale-Pythia-1b-pt.i1-IQ3_M.gguf) \| i1-IQ3_M \| 0.6 \| \| \| [GGUF](https://huggingface.co/mradermacher/C2S-Scale-Pythia-1b-pt-i1-GGUF/resolve/main/C2S-Scale-Pythia-1b-pt.i1-Q3_K_M.gguf) \| i1-Q3_K_M \| 0.7 \| IQ3_S probably better \| \| [GGUF](https://huggingface.co/mradermacher/C2S-Scale-Pythia-1b-pt-i1-GGUF/resolve/main/C2S-Scale-Pythia-1b-pt.i1-IQ4_XS.gguf) \| i1-IQ4_XS \| 0.7 \| \| \| [GGUF](https://huggingface.co/mradermacher/C2S-Scale-Pythia-1b-pt-i1-GGUF/resolve/main/C2S-Scale-Pythia-1b-pt.i1-Q3_K_L.gguf) \| i1-Q3_K_L \| 0.7 \| IQ3_M probably better \| \| [GGUF](https://huggingface.co/mradermacher/C2S-Scale-Pythia-1b-pt-i1-GGUF/resolve/main/C2S-Scale-Pythia-1b-pt.i1-IQ4_NL.gguf) \| i1-IQ4_NL \| 0.7 \| prefer IQ4_XS \| \| [GGUF](https://huggingface.co/mradermacher/C2S-Scale-Pythia-1b-pt-i1-GGUF/resolve/main/C2S-Scale-Pythia-1b-pt.i1-Q4_0.gguf) \| i1-Q4_0 \| 0.7 \| fast, low quality \| \| [GGUF](https://huggingface.co/mradermacher/C2S-Scale-Pythia-1b-pt-i1-GGUF/resolve/main/C2S-Scale-Pythia-1b-pt.i1-Q4_K_S.gguf) \| i1-Q4_K_S \| 0.7 \| optimal size/speed/quality \| \| [GGUF](https://huggingface.co/mradermacher/C2S-Scale-Pythia-1b-pt-i1-GGUF/resolve/main/C2S-Scale-Pythia-1b-pt.i1-Q4_1.gguf) \| i1-Q4_1 \| 0.8 \| \| \| [GGUF](https://huggingface.co/mradermacher/C2S-Scale-Pythia-1b-pt-i1-GGUF/resolve/main/C2S-Scale-Pythia-1b-pt.i1-Q4_K_M.gguf) \| i1-Q4_K_M \| 0.8 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/C2S-Scale-Pythia-1b-pt-i1-GGUF/resolve/main/C2S-Scale-Pythia-1b-pt.i1-Q5_K_S.gguf) \| i1-Q5_K_S \| 0.8 \| \| \| [GGUF](https://huggingface.co/mradermacher/C2S-Scale-Pythia-1b-pt-i1-GGUF/resolve/main/C2S-Scale-Pythia-1b-pt.i1-Q5_K_M.gguf) \| i1-Q5_K_M \| 0.9 \| \| \| [GGUF](https://huggingface.co/mradermacher/C2S-Scale-Pythia-1b-pt-i1-GGUF/resolve/main/C2S-Scale-Pythia-1b-pt.i1-Q6_K.gguf) \| i1-Q6_K \| 0.9 \| practically like static Q6_K \| Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. <!-- end -->
owenpastor21/LawQwen1.5-Big	owenpastor21	2025-04-24T20:20:38Z	0	0	transformers	[ "transformers", "gguf", "qwen2", "text-generation-inference", "unsloth", "en", "license:apache-2.0", "endpoints_compatible", "region:us", "conversational" ]	null	2025-04-24T20:19:55Z	--- base_model: unsloth/qwen2-1.5b-instruct-bnb-4bit tags: - text-generation-inference - transformers - unsloth - qwen2 - gguf license: apache-2.0 language: - en --- # Uploaded model - Developed by: owenpastor21 - License: apache-2.0 - Finetuned from model : unsloth/qwen2-1.5b-instruct-bnb-4bit This qwen2 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
MrezaPRZ/qwen2.5-Coder-7B-Instruct-sql-judge-7b-all-dataset	MrezaPRZ	2025-04-24T19:38:04Z	0	0	transformers	[ "transformers", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2025-04-24T19:38:02Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
Sandhanapandiyan/ResponceGenerator	Sandhanapandiyan	2025-04-24T12:28:03Z	0	0	transformers	[ "transformers", "safetensors", "phi", "text-generation", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "4-bit", "bitsandbytes", "region:us" ]	text-generation	2025-04-24T12:18:05Z	--- 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: Sandhanapandiyan - Funded by [optional]: - 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]: microsoft/phi ### 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 from transformers import AutoTokenizer, AutoModelForCausalLM import torch # Load the model and tokenizer model_path = "/content/drive/MyDrive/sandhanapandiyan/Responce Generator" tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True) model = AutoModelForCausalLM.from_pretrained(model_path, device_map="auto", torch_dtype=torch.float16) # Generate a response def generate_response(user_query, sql_result, max_tokens=150): prompt = f"User: {user_query}\nSQL Result: {sql_result}\nAssistant:" inputs = tokenizer(prompt, return_tensors="pt").to(model.device) with torch.no_grad(): outputs = model.generate( inputs, max_new_tokens=max_tokens, do_sample=True, temperature=0.7, top_p=0.9, eos_token_id=tokenizer.eos_token_id, ) generated_text = tokenizer.decode(outputs[0], skip_special_tokens=True) # Extract only the assistant's response return generated_text.split("Assistant:")[-1].strip() # Example usage user_query = "list all the employee" sql_result = "Emily Watson" response = generate_response(user_query, sql_result) print("🔍 Generated Response:") print(response) [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]
filipesantoscv11/264f943b-26c9-4f3f-bc2b-5bd2eeaad431	filipesantoscv11	2025-04-24T03:09:30Z	0	0	peft	[ "peft", "safetensors", "qwen2", "axolotl", "generated_from_trainer", "base_model:Qwen/Qwen2-7B-Instruct", "base_model:adapter:Qwen/Qwen2-7B-Instruct", "license:apache-2.0", "8-bit", "bitsandbytes", "region:us" ]	null	2025-04-24T02:15:20Z	--- library_name: peft license: apache-2.0 base_model: Qwen/Qwen2-7B-Instruct tags: - axolotl - generated_from_trainer model-index: - name: 264f943b-26c9-4f3f-bc2b-5bd2eeaad431 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> [<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl) <details><summary>See axolotl config</summary> axolotl version: `0.4.1` ```yaml adapter: lora base_model: Qwen/Qwen2-7B-Instruct bf16: true chat_template: llama3 dataset_prepared_path: /workspace/axolotl datasets: - data_files: - 5ae3737b877f9502_train_data.json ds_type: json format: custom path: /workspace/input_data/5ae3737b877f9502_train_data.json type: field_instruction: context field_output: target format: '{instruction}' no_input_format: '{instruction}' system_format: '{system}' system_prompt: '' debug: null deepspeed: null early_stopping_patience: null eval_max_new_tokens: 128 eval_table_size: null evals_per_epoch: 1 flash_attention: true fp16: null fsdp: null fsdp_config: null gradient_accumulation_steps: 1 gradient_checkpointing: true gradient_clipping: 0.5 group_by_length: false hub_model_id: filipesantoscv11/264f943b-26c9-4f3f-bc2b-5bd2eeaad431 hub_repo: null hub_strategy: end hub_token: null learning_rate: 5.0e-06 load_in_4bit: false load_in_8bit: true local_rank: null logging_steps: 1 lora_alpha: 128 lora_dropout: 0.05 lora_fan_in_fan_out: null lora_model_dir: null lora_r: 64 lora_target_linear: true lr_scheduler: cosine max_steps: 200 micro_batch_size: 8 mixed_precision: bf16 mlflow_experiment_name: /tmp/5ae3737b877f9502_train_data.json model_type: AutoModelForCausalLM num_epochs: 1 optimizer: adamw_bnb_8bit output_dir: miner_id_24 pad_to_sequence_len: true resume_from_checkpoint: null s2_attention: null sample_packing: false saves_per_epoch: 1 sequence_len: 1024 strict: false tf32: false tokenizer_type: AutoTokenizer train_on_inputs: false trust_remote_code: true val_set_size: 0.05 wandb_entity: null wandb_mode: online wandb_name: 86829976-db41-4364-b9e3-b5734ffc6384 wandb_project: s56-6 wandb_run: your_name wandb_runid: 86829976-db41-4364-b9e3-b5734ffc6384 warmup_steps: 5 weight_decay: 0.01 xformers_attention: true ``` </details><br> # 264f943b-26c9-4f3f-bc2b-5bd2eeaad431 This model is a fine-tuned version of [Qwen/Qwen2-7B-Instruct](https://huggingface.co/Qwen/Qwen2-7B-Instruct) on the None dataset. It achieves the following results on the evaluation set: - Loss: 1.3431 ## 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-06 - train_batch_size: 8 - eval_batch_size: 8 - 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: cosine - lr_scheduler_warmup_steps: 5 - training_steps: 200 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:------:\|:----:\|:---------------:\| \| 1.7541 \| 0.0046 \| 200 \| 1.3431 \| ### Framework versions - PEFT 0.13.2 - Transformers 4.46.0 - Pytorch 2.5.0+cu124 - Datasets 3.0.1 - Tokenizers 0.20.1
aniket-meta/llama-3.1-8B-mkb-lora-sysv3-e5	aniket-meta	2025-04-23T16:21:01Z	0	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-04-23T16:17:39Z	--- 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]
mcrovero/gemma-3-27b-it-custom-merged	mcrovero	2025-04-23T12:55:38Z	29	0	transformers	[ "transformers", "gemma3_text", "text-generation", "text-generation-inference", "unsloth", "gemma3", "conversational", "en", "base_model:unsloth/gemma-3-4b-it-unsloth-bnb-4bit", "base_model:finetune:unsloth/gemma-3-4b-it-unsloth-bnb-4bit", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-generation	2025-04-22T15:38:13Z	--- base_model: unsloth/gemma-3-4b-it-unsloth-bnb-4bit tags: - text-generation-inference - transformers - unsloth - gemma3 license: apache-2.0 language: - en --- # Uploaded finetuned model - Developed by: mcrovero - License: apache-2.0 - Finetuned from model : unsloth/gemma-3-4b-it-unsloth-bnb-4bit This gemma3 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)
mwulaflaga/potpot	mwulaflaga	2025-04-23T06:34:12Z	0	0	null	[ "license:bigscience-bloom-rail-1.0", "region:us" ]	null	2025-04-23T06:34:12Z	--- license: bigscience-bloom-rail-1.0 ---

Subsets and Splits