If you want to give the Finegrain Box Segmenter a try, the best way to is take a look at the Finegrain Object Cutter Space we shipped on Hugging Face: it's a fun "prompt to cut out" experience that will enable you to create pixel quality and high resolution cutouts for any object in a photo, by just naming the object. While building Finegrain, we needed a way to create pixel perfect and high resolution cutouts for objects in images. We looked at off-the-shelf solutions, but they simply didn't work for us: - On the one hand, traditional background removal models are great at producing HD cutouts, but unfortunately, different people will have different definitions for background and…
Open weights
mit
95M parameters
refiners
Multi-Scale Efficient Global Context Vision Transformer (MS-EffGCViT) is a hybrid CNN-ViT architecture for deepfake detection. It fuses CNN-driven spatial inductive bias with hierarchical global-context attention to catch both local artifacts (textures, blending seams) and global artifacts (lighting, structural inconsistency). A single architecture ships in two sizes and three domain-tuned checkpoints, working on both static images and video at the frame level. - Frame-level — one model handles both images and videos (frame-level inference + aggregation). - Cross-domain — robust on both East-Asian (KoDF) and Western (Celeb-DF-v2, FaceForensics++) faces. - Two variants — Fast (b0) for…
Open weights
mit
53M parameters
transformers
Multi-Scale Efficient Global Context Vision Transformer (MS-EffGCViT) is a hybrid CNN-ViT architecture for deepfake detection. It fuses CNN-driven spatial inductive bias with hierarchical global-context attention to catch both local artifacts (textures, blending seams) and global artifacts (lighting, structural inconsistency). A single architecture ships in two sizes and three domain-tuned checkpoints, working on both static images and video at the frame level. - Frame-level — one model handles both images and videos (frame-level inference + aggregation). - Cross-domain — robust on both East-Asian (KoDF) and Western (Celeb-DF-v2, FaceForensics++) faces. - Two variants — Fast (b0) for…
Open weights
mit
9M parameters
transformers
Multi-Scale Efficient Global Context Vision Transformer (MS-EffGCViT) is a hybrid CNN-ViT architecture for deepfake detection. It fuses CNN-driven spatial inductive bias with hierarchical global-context attention to catch both local artifacts (textures, blending seams) and global artifacts (lighting, structural inconsistency). A single architecture ships in two sizes and three domain-tuned checkpoints, working on both static images and video at the frame level. - Frame-level — one model handles both images and videos (frame-level inference + aggregation). - Cross-domain — robust on both East-Asian (KoDF) and Western (Celeb-DF-v2, FaceForensics++) faces. - Two variants — Fast (b0) for…
Open weights
mit
9M parameters
transformers
Multi-Scale Efficient Global Context Vision Transformer (MS-EffGCViT) is a hybrid CNN-ViT architecture for deepfake detection. It fuses CNN-driven spatial inductive bias with hierarchical global-context attention to catch both local artifacts (textures, blending seams) and global artifacts (lighting, structural inconsistency). A single architecture ships in two sizes and three domain-tuned checkpoints, working on both static images and video at the frame level. - Frame-level — one model handles both images and videos (frame-level inference + aggregation). - Cross-domain — robust on both East-Asian (KoDF) and Western (Celeb-DF-v2, FaceForensics++) faces. - Two variants — Fast (b0) for…
Open weights
mit
53M parameters
transformers
1. pure torch and huggingface-based implementation of the original microsoft/BiomedCLIP-PubMedBERT256-vitbasepatch16224 2. rename the checkpoint state key names.
Open weights
mit
196M parameters
512 tokens
transformers
A fast and efficient 32B model optimized for CPU inference. The model was refactored with BitNet features and an updated tokenizer that includes new Routing, Media, Vision, Sound, Tool call, and Robotics tags. Built on a DeepSeek R1-32B architecture with native ternary (BitNet-style) support and ready-to-run GGUF quantizations. - JiRack is a cloud-ready model that helps save money on cloud infrastructure. It can be used as an expert model in RAG deployments, with the ONNX JiRack Java server as an alternative. - Benefits high quality CPU inference TQ2 on Llama.cpp and Ollama via QAT - Robotcs, Routing, Coding, Multimedia, Advanced tool calling via CMSManhattan/JiRackPrecisionTokenizer…
Open weights
mit
32.8B parameters
131,072 tokens
Multi-Scale Efficient Global Context Vision Transformer (MS-EffGCViT) is a hybrid CNN-ViT architecture for deepfake detection. It fuses CNN-driven spatial inductive bias with hierarchical global-context attention to catch both local artifacts (textures, blending seams) and global artifacts (lighting, structural inconsistency). A single architecture ships in two sizes and three domain-tuned checkpoints, working on both static images and video at the frame level. - Frame-level — one model handles both images and videos (frame-level inference + aggregation). - Cross-domain — robust on both East-Asian (KoDF) and Western (Celeb-DF-v2, FaceForensics++) faces. - Two variants — Fast (b0) for…
Open weights
mit
9M parameters
transformers
This model is fine-tuned version of microsoft/conditional-detr-resnet-50. You can find details of model in this github repo -> fashion-visual-search And you can find fashion image feature extractor model -> yainage90/fashion-image-feature-extractor This model was trained using a combination of two datasets: modanet and fashionpedia The labels are ['bag', 'bottom', 'dress', 'hat', 'shoes', 'outer', 'top'] In the 96th epoch out of total of 100 epochs, the best score was achieved with mAP 0.7542. Therefore, it is believed that there is a little room for performance improvement.
Open weights
mit
44M parameters
1,024 tokens
transformers
This model was produced by fine-tuning the OpenVLA 7B model via LoRA (r=32) on the LIBERO-Spatial dataset from the LIBERO simulation benchmark. We made a few modifications to the training dataset to improve final performance (see the OpenVLA paper for details). Below are the hyperparameters we used for all LIBERO experiments: - No gradient accumulation (i.e. gradaccumulationsteps == 1) - shufflebuffersize == 100000 See the OpenVLA GitHub README for instructions on how to run and evaluate this model in the LIBERO simulator.
Open weights
mit
7.5B parameters
transformers
Models in this series are designed for efficient zeroshot classification with the Hugging Face pipeline. These models can do classification without training data and run on both GPUs and CPUs. An overview of the latest zeroshot classifiers is available in my Zeroshot Classifier Collection. The main update of this zeroshot-v2.0 series of models is that several models are trained on fully commercially-friendly data for users with strict license requirements. These models can do one universal classification task: determine whether a hypothesis is "true" or "not true" given a text (entailment vs. notentailment). This task format is based on the Natural Language Inference task (NLI). The task is…
Open weights
mit
125M parameters
514 tokens
transformers
This is a fine-tunned object detection model for fashion. For more details of the implementation you can check the source code here the dataset used for its training is available here this model supports the following categories: CATS = ['shirt, blouse', 'top, t-shirt, sweatshirt', 'sweater', 'cardigan', 'jacket', 'vest', 'pants', 'shorts', 'skirt', 'coat', 'dress', 'jumpsuit', 'cape', 'glasses', 'hat', 'headband, head covering, hair accessory', 'tie', 'glove', 'watch', 'belt', 'leg warmer', 'tights, stockings', 'sock', 'shoe', 'bag, wallet', 'scarf', 'umbrella', 'hood', 'collar', 'lapel', 'epaulette', 'sleeve', 'pocket', 'neckline', 'buckle', 'zipper', 'applique', 'bead', 'bow', 'flower'…
Open weights
mit
transformers
Segments ink directly in 3D in micro-CT of PHerc. Paris 4, where ink is volumetrically visible. This model provides the independent volumetric validation of surface-conditioned ink recovery reported in "Complete virtual unwrapping and reading of a rolled Herculaneum papyrus" (Angelotti et al., arXiv:2606.29085, 2026). (PHerc. Paris 4, 0139, 0500P2, 0814, 0841, 1667, MAN5, 9B); (2) a DINO-guided student using dense ink-likeness from the 3D DINOv2 representation model (3) + background masking; (4) self-distillation. DINO guidance compares each 864-D patch token to a reference ink embedding (avgrefembedding.npy, the L2-normalised mean of 256 expert-clicked tokens stored in…
Open weights
mit
A fast and efficient 7B model optimized for CPU inference. The model was refactored with BitNet features and an updated tokenizer that includes new Routing, Media, Vision, Sound,Tool call, and Robotics tags. Built on a DeepSeek R1 -7B architecture with native ternary (BitNet-style) support and ready-to-run GGUF quantizations. - JiRack is a cloud-ready model that helps save money on cloud infrastructure. It can be used as an expert model in RAG deployments, with the ONNX JiRack Java server as an alternative. - Benefits high quality CPU inference TQ2 on Llama.cpp and Ollama via QAT - Robotcs, Routing, Coding, Multimedia, Advanced tool calling via CMSManhattan/JiRackPrecisionTokenizer…
Open weights
mit
7.6B parameters
131,072 tokens
This model was fine-tuned from the HuggingFace BERT base uncased checkpoint on SQuAD1.1. CPU: Intel(R) Core(TM) i7-6800K CPU @ 3.40GHz Memory: 32 GiB GPUs: 2 GeForce GTX 1070, each with 8GiB memory GPU driver: 418.87.01, CUDA: 10.1 It took about 2 hours to finish. Note that the above results didn't involve any hyperparameter search.
Open weights
mit
109M parameters
512 tokens
transformers
This repository contains the OpenVLA-OFT checkpoint for LIBERO-Object, as described in Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success. OpenVLA-OFT significantly improves upon the base OpenVLA model by incorporating optimized fine-tuning techniques. See here for other OpenVLA-OFT checkpoints: https://huggingface.co/moojink?searchmodels=oft This example demonstrates generating an action chunk using a pretrained OpenVLA-OFT checkpoint. Ensure you have set up the conda environment as described in the GitHub README.
Open weights
mit
7.5B parameters
transformers
alt="Aurora Logo" src="https://cdn-uploads.huggingface.co/production/uploads/66276727368ec2a0b933772c/ytpsIAr98keUvNouoOVmb.png" width="30%" The official code repo of our ICLR 2026 paper: Aurora: Towards Universal Generative Multimodal Time Series Forecasting alt="ICLR 2026" src="https://img.shields.io/badge/ICLR%202026-Aurora-orange" alt="Python" src="https://img.shields.io/badge/Python-3.10%2B-blue" alt="PyTorch" src="https://img.shields.io/badge/PyTorch-2.4.1-blue" alt="GitHub Stars" src="https://img.shields.io/github/stars/decisionintelligence/Aurora?logo=github" alt="GitHub" src="https://img.shields.io/badge/GitHub-Aurora-black?logo=github" Aurora is a highly capable multimodal time…
Open weights
mit
211M parameters
10,000 tokens
This repository contains the OpenVLA-OFT checkpoint for LIBERO-Goal, as described in Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success. OpenVLA-OFT significantly improves upon the base OpenVLA model by incorporating optimized fine-tuning techniques. See here for other OpenVLA-OFT checkpoints: https://huggingface.co/moojink?searchmodels=oft This example demonstrates generating an action chunk using a pretrained OpenVLA-OFT checkpoint. Ensure you have set up the conda environment as described in the GitHub README.
Open weights
mit
7.5B parameters
transformers
Speech emotion recognition for Russian over seven classes: anger, disgust, enthusiasm, fear, happiness, neutral, sadness. Fine-tuned from jonatasgrosman/wav2vec2-large-xlsr-53-russian on Aniemore/resd. Audio resampled to 16 kHz mono, clips capped at 12 s, normalized per utterance, padding masked. UA is macro-averaged recall, WA is accuracy, F1 is macro-averaged. All three test sets went through the same harness, so the rows are comparable to each other. The RESD split matches fold 1 of EmoBox bit for bit. The top entry there is WavLM-large at WA 56.47 / UA 55.87 / F1 55.82. These numbers are higher, but the training protocol differs — EmoBox freezes the encoder and trains a probe, this is a…
Open weights
mit
316M parameters
transformers
Fine-tuned facebook/wav2vec2-base for audio classification of single drum/percussion sounds into 10 classes. - clap, conga, crash, cymbal, hat, kick, ride, rim, snare, tom - Trained on short, single-hit drum sounds. Performance may drop on long mixes, multiple overlapping sounds, or very different recording conditions.
Open weights
mit
95M parameters
This model is a fine-tuned version of facebook/wav2vec2-base-960h for Speech Emotion Recognition (SER). It has been trained using a Frozen Feature Extractor strategy to preserve the model's acoustic understanding while adapting to emotion detection. This approach ensures stable performance and prevents "Catastrophic Forgetting," achieving nearly 80% accuracy on the validation set. Update: The "Calm" and "Neutral" classes have been merged to improve classification consistency, resulting in 7 distinct emotion classes. The model was trained on a combined dataset of ~12,000 audio files from: The model classifies audio into one of the following emotions: 1. Angry 2. Disgust 3. Fear 4. Happy 5.…
Open weights
mit
95M parameters
transformers
This model was fine-tuned using the same pipeline as described in the model card for MoritzLaurer/deberta-v3-large-zeroshot-v1.1-all-33 and in this paper. The foundation model is microsoft/xtremedistil-l6-h256-uncased. The model only has 22 million backbone parameters and 30 million vocabulary parameters. The backbone parameters are the main parameters active during inference, providing a significant speedup over larger models. The model is 25 MB small. This model was trained to provide a very small and highly efficient zeroshot option, especially for edge devices or in-browser use-cases with transformers.js. For usage instructions and other details refer to this model card…
Open weights
mit
13M parameters
512 tokens
transformers
X-CLIP model (large-sized, patch resolution of 14) trained fully-supervised on Kinetics-400. It was introduced in the paper Expanding Language-Image Pretrained Models for General Video Recognition by Ni et al. and first released in this repository. This model was trained using 8 frames per video, at a resolution of 224x224. Disclaimer: The team releasing X-CLIP did not write a model card for this model so this model card has been written by the Hugging Face team. X-CLIP is a minimal extension of CLIP for general video-language understanding. The model is trained in a contrastive way on (video, text) pairs. This allows the model to be used for tasks like zero-shot, few-shot or fully…
Open weights
mit
576M parameters
77 tokens
transformers
haystack's distillation feature was used for training. deepset/roberta-large-squad2 was used as the teacher model. Haystack is an AI orchestration framework to build customizable, production-ready LLM applications. You can use this model in Haystack to do extractive question answering on documents. To load and run the model with Haystack: For a complete example with an extractive question answering pipeline that scales over many documents, check out the corresponding Haystack tutorial. Timo Möller: [email protected] deepset is the company behind the production-ready open-source AI framework Haystack. We also have a Discord community open to everyone!
Open weights
mit
124M parameters
514 tokens
transformers
Open weights
mit
1,024 tokens
transformers
X-CLIP model (base-sized, patch resolution of 16) trained fully-supervised on Kinetics-400. It was introduced in the paper Expanding Language-Image Pretrained Models for General Video Recognition by Ni et al. and first released in this repository. This model was trained using 8 frames per video, at a resolution of 224x224. Disclaimer: The team releasing X-CLIP did not write a model card for this model so this model card has been written by the Hugging Face team. X-CLIP is a minimal extension of CLIP for general video-language understanding. The model is trained in a contrastive way on (video, text) pairs. This allows the model to be used for tasks like zero-shot, few-shot or fully…
Open weights
mit
195M parameters
77 tokens
transformers
A fast and efficient ~1.5B model optimized for CPU inference. The model was refactored with BitNet features and an updated tokenizer that includes new Routing, Tool call, and Robotics tags. Built on a redesigned DeepSeek R1 architecture with native ternary (BitNet-style) support and ready-to-run GGUF quantizations. - JiRack is a cloud-ready model that helps save money on cloud infrastructure. It can be used as an expert model in RAG deployments, with the ONNX JiRack Java server as an alternative. - Benefits high quality CPU inference TQ2 on Llama.cpp and Ollama via QAT - Robotcs, Routing, Coding, Multimedia, Advanced tool calling via CMSManhattan/JiRackPrecisionTokenizer - We are working to…
Open weights
mit
1.8B parameters
131,072 tokens
Model · Object detection
DISCO
Open weights
mit
42M parameters
1,024 tokens
transformers
Open weights
mit
184M parameters
512 tokens
transformers
Multi-Scale Efficient Global Context Vision Transformer (MS-EffGCViT) is a hybrid CNN-ViT architecture for deepfake detection. It fuses CNN-driven spatial inductive bias with hierarchical global-context attention to catch both local artifacts (textures, blending seams) and global artifacts (lighting, structural inconsistency). A single architecture ships in two sizes and three domain-tuned checkpoints, working on both static images and video at the frame level. - Frame-level — one model handles both images and videos (frame-level inference + aggregation). - Cross-domain — robust on both East-Asian (KoDF) and Western (Celeb-DF-v2, FaceForensics++) faces. - Two variants — Fast (b0) for…
Open weights
mit
53M parameters
transformers
This model can be used for the task of Question Answering on Legal Documents. Read: An Open Source Contractual Language Understanding Application Using Machine Learning for detailed information on training procedure, dataset preprocessing and evaluation. See CUAD dataset card for more information. See CUAD dataset card for more information. Used V100/P100 from Google Colab Pro Python, Transformers Mohammed Rakib in collaboration with Ezi Ozoani and the Hugging Face team Use the code below to get started with the model.
Open weights
mit
514 tokens
transformers
This model was produced by fine-tuning the OpenVLA 7B model via LoRA (r=32) on the LIBERO-Object dataset from the LIBERO simulation benchmark. We made a few modifications to the training dataset to improve final performance (see the OpenVLA paper for details). Below are the hyperparameters we used for all LIBERO experiments: - No gradient accumulation (i.e. gradaccumulationsteps == 1) - shufflebuffersize == 100000 See the OpenVLA GitHub README for instructions on how to run and evaluate this model in the LIBERO simulator.
Open weights
mit
7.5B parameters
transformers
This is the flan-t5-base model, fine-tuned using the SQuAD2.0 dataset. It's been trained on question-answer pairs, including unanswerable questions, for the task of Extractive Question Answering. UPDATE: With transformers version 4.31.0 the useremotecode=True is no longer necessary. NOTE: The token must be manually added to the beginning of the question for this model to work properly. It uses the token to be able to make "no answer" predictions. The t5 tokenizer does not automatically add this special token which is why it is added manually. The following hyperparameters were used during training: - learningrate: 2e-05 - trainbatchsize: 16 - evalbatchsize: 8 - gradientaccumulationsteps: 6…
Open weights
mit
223M parameters
transformers
This repository contains the OpenVLA-OFT checkpoint for LIBERO-Long (also called LIBERO-10), as described in Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success. OpenVLA-OFT significantly improves upon the base OpenVLA model by incorporating optimized fine-tuning techniques. See here for other OpenVLA-OFT checkpoints: https://huggingface.co/moojink?searchmodels=oft This example demonstrates generating an action chunk using a pretrained OpenVLA-OFT checkpoint. Ensure you have set up the conda environment as described in the GitHub README.
Open weights
mit
7.5B parameters
transformers
The model was trained on MSP-Podcast for the Odyssey 2024 Emotion Recognition competition baseline This particular model is the multi-attributed based model which predict arousal, dominance and valence in a range of approximately 0...1. CCC based on Test3 and Development sets of the Odyssey Competition
Open weights
mit
319M parameters
transformers
Model · Question answering
VietAI
State-of-the-art pretrained Transformer-based encoder-decoder model for Vietnamese. For more details, do check out our Github repo.
Open weights
mit
transformers
A HuggingFace-format conversion of Meta AI's V-JEPA 2.1 ViT-B/16 video encoder and predictor, operating at 384x384 resolution. The weights are Meta's, copied without modification. This repository provides the transformers-compatible packaging plus a documented numerical validation against the original implementation. An equivalent community port already exists (Dev-Jahn/vjepa2.1-vitb-fpc64-384). This repository adds an independently reproduced conversion together with the validation results below. The only structural change is that the fused QKV projection of each attention block is split into separate query / key / value matrices, following the convention used by transformers. This is a…
Open weights
mit
110M parameters
transformers
Roof detection model for remote sensing imagery, fine-tuned using RT-DETR. The following example shows roof detections produced by the model: Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. Use the code below to get started with the model.
Open weights
mit
77M parameters
transformers
This model was produced by fine-tuning the OpenVLA 7B model via LoRA (r=32) on the LIBERO-10 (LIBERO-Long) dataset from the LIBERO simulation benchmark. We made a few modifications to the training dataset to improve final performance (see the OpenVLA paper for details). Below are the hyperparameters we used for all LIBERO experiments: - No gradient accumulation (i.e. gradaccumulationsteps == 1) - shufflebuffersize == 100000 See the OpenVLA GitHub README for instructions on how to run and evaluate this model in the LIBERO simulator.
Open weights
mit
7.5B parameters
transformers
X-CLIP model (large-sized, patch resolution of 14) trained fully-supervised on Kinetics-400. It was introduced in the paper Expanding Language-Image Pretrained Models for General Video Recognition by Ni et al. and first released in this repository. This model was trained using 16 frames per video, at a resolution of 336x336. Disclaimer: The team releasing X-CLIP did not write a model card for this model so this model card has been written by the Hugging Face team. X-CLIP is a minimal extension of CLIP for general video-language understanding. The model is trained in a contrastive way on (video, text) pairs. This allows the model to be used for tasks like zero-shot, few-shot or fully…
Open weights
mit
77 tokens
transformers
MobileBERT is a thin version of BERTLARGE, while equipped with bottleneck structures and a carefully designed balance between self-attentions and feed-forward networks. This model was fine-tuned from the HuggingFace checkpoint google/mobilebert-uncased on SQuAD1.1. CPU: Intel(R) Core(TM) i7-6800K CPU @ 3.40GHz Memory: 32 GiB GPUs: 2 GeForce GTX 1070, each with 8GiB memory GPU driver: 418.87.01, CUDA: 10.1 It took about 3 hours to finish. Note that the above results didn't involve any hyperparameter search.
Open weights
mit
25M parameters
512 tokens
transformers
Core AI is Apple's on-device ML runtime in iOS 27 / macOS 27 and the successor to Core ML: PyTorch models are exported with Apple's coreai-torch (LLMs: coreai.llm.export) into.aimodel bundles that run on the GPU or the Neural Engine, e.g. Qwen3-8B 4-bit decodes at 94 tok/s on an M4 Max GPU, MLX 90 under the same protocol (apple-silicon-llm-bench, macOS 27 beta 26A5353q, 2026-06-11). This model has no row on DeviceMark, the on-device LLM leaderboard. V-JEPA 2 (Meta AI) running natively on the Apple Core AI engine — the zoo's first world model: a self-supervised video encoder that learns by predicting in representation space (JEPA), here with the Something-Something v2 action head (174…
Open weights
mit
coreai
Benefits high quality CPU inference TQ2 on Llama.cpp and Ollama via QAT - Robotcs, Routing, Coding, Multimedia, Advanced tool calling via JiRackDeltaNetTokenizer - JiRack DeltaNet understand video and images that best for Robotics also A fast and efficient 27B model optimized for CPU inference. Built on a Qwen3.8-style DeltaNet architecture (hybrid attention + SSM), with an updated tokenizer that includes Routing, Media, Vision, Sound, Tool call, and Robotics tags. Ready-to-run GGUF quantizations, and native Ollama support with reasoning disabled by default for fast, direct responses. - JiRack is a cloud-ready model that helps save money on cloud infrastructure. It can be used as an expert…
Open weights
mit
27.3B parameters
262,144 tokens
This model was produced by fine-tuning the OpenVLA 7B model via LoRA (r=32) on the LIBERO-Goal dataset from the LIBERO simulation benchmark. We made a few modifications to the training dataset to improve final performance (see the OpenVLA paper for details). Below are the hyperparameters we used for all LIBERO experiments: - No gradient accumulation (i.e. gradaccumulationsteps == 1) - shufflebuffersize == 100000 See the OpenVLA GitHub README for instructions on how to run and evaluate this model in the LIBERO simulator.
Open weights
mit
7.5B parameters
transformers
PTT5 Summ is a fine-tuned PTT5 model to perform Abstractive Summarization in Brazilian Portuguese texts. This model was fine-tuned on the datasets: RecognaSumm, WikiLingua, XL-Sum, TeMário.pdf) and CSTNews. For further information, please go to PTT5 Summ repository.
Open weights
mit
223M parameters
transformers
The model is designed for zero-shot classification with the Hugging Face pipeline. The model can do one universal classification task: determine whether a hypothesis is "true" or "not true" given a text (entailment vs. notentailment). This task format is based on the Natural Language Inference task (NLI). The task is so universal that any classification task can be reformulated into this task. A detailed description of how the model was trained and how it can be used is available in this paper. The model was trained on a mixture of 33 datasets and 387 classes that have been reformatted into this universal format. 1. Five NLI datasets with ~885k texts: "mnli", "anli", "fever", "wanli"…
Open weights
mit
435M parameters
512 tokens
transformers
Model · Zero-shot classification
Recognai
UPDATE, 15.10.2021: Check out our new zero-shot classifiers, much more lightweight and even outperforming this one: zero-shot SELECTRA small and zero-shot SELECTRA medium. This model is a fine-tuned version of the spanish BERT model with the Spanish portion of the XNLI dataset. You can have a look at the training script for details of the training. You can use this model with Hugging Face's zero-shot-classification pipeline
Open weights
mit
110M parameters
512 tokens
transformers
Haystack's distillation feature was used for training. deepset/xlm-roberta-large-squad2 was used as the teacher model. Haystack is an AI orchestration framework to build customizable, production-ready LLM applications. You can use this model in Haystack to do extractive question answering on documents. To load and run the model with Haystack: For a complete example with an extractive question answering pipeline that scales over many documents, check out the corresponding Haystack tutorial. Evaluated on the SQuAD 2.0 dev set Timo Möller: [email protected] deepset is the company behind the production-ready open-source AI framework Haystack. We also have a Discord community open to…
Open weights
mit
277M parameters
514 tokens
transformers
This repository contains the OpenVLA-OFT checkpoint for LIBERO-Spatial, as described in Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success. OpenVLA-OFT significantly improves upon the base OpenVLA model by incorporating optimized fine-tuning techniques. See here for other OpenVLA-OFT checkpoints: https://huggingface.co/moojink?searchmodels=oft This example demonstrates generating an action chunk using a pretrained OpenVLA-OFT checkpoint. Ensure you have set up the conda environment as described in the GitHub README.
Open weights
mit
7.5B parameters
2,048 tokens
transformers
Models in this series are designed for efficient zeroshot classification with the Hugging Face pipeline. These models can do classification without training data and run on both GPUs and CPUs. An overview of the latest zeroshot classifiers is available in my Zeroshot Classifier Collection. The main update of this zeroshot-v2.0 series of models is that several models are trained on fully commercially-friendly data for users with strict license requirements. These models can do one universal classification task: determine whether a hypothesis is "true" or "not true" given a text (entailment vs. notentailment). This task format is based on the Natural Language Inference task (NLI). The task is…
Open weights
mit
435M parameters
512 tokens
transformers
This repository contains the OpenVLA-OFT checkpoint trained on 4 LIBERO task suites combined (-Spatial, -Object, -Goal, -Long), as described in Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success. OpenVLA-OFT significantly improves upon the base OpenVLA model by incorporating optimized fine-tuning techniques. See here for other OpenVLA-OFT checkpoints: https://huggingface.co/moojink?searchmodels=oft This example demonstrates generating an action chunk using a pretrained OpenVLA-OFT checkpoint. Ensure you have set up the conda environment as described in the GitHub README.
Open weights
mit
7.5B parameters
transformers
This repository houses a fine-tuned VideoMAE (Base) model optimized for multi-class Vietnamese Sign Language Recognition (VSLR). The model architecture adapts self-supervised video representations to accurately classify short video clips of sign gestures into distinct Vietnamese text labels. The model processes short video sequences by partitioning them into spatiotemporal patches, mapping sequential gestures (such as "Ăn", "Bệnh viện", "Xin lỗi") to their corresponding semantic classes. The training routine was monitored closely across key evaluation metrics to prevent overfitting while maximizing classification accuracy on the validation split. The plot below illustrates the progression…
Open weights
mit
86M parameters
transformers
Model · Text generation
Lamapi
Next-1B is a 1-billion parameter causal language model based on Gemma 3, designed for efficiency, low-resource deployment, and reasoning-focused natural language understanding. Extremely lightweight — can run on consumer GPUs with low VRAM. Optimized for text reasoning, summarization, and creative generation. Supports Turkish natively while remaining multilingual. Open-source and transparent for research and applications. Ideal for developers, students, and organizations needing fast, reliable, and low-resource text-generation. 1. Lightweight Efficiency: Run smoothly on low-resource devices. 2. Reasoning-Focused: Provide logical and coherent text outputs. 3. Accessibility: Fully open-source…
Open weights
mit
1B parameters
32,768 tokens
transformers
A frontier video understanding model developed by FAIR, Meta, which extends the pretraining objectives of VJEPA, resulting in state-of-the-art video understanding capabilities, leveraging data and model sizes at scale. The code is released in this repository. This is V-JEPA 2 model with video classification head pretrained on Something-Something-V2 dataset. To run V-JEPA 2 model, ensure you have installed the latest transformers
Open weights
mit
375M parameters
transformers
A frontier video understanding model developed by FAIR, Meta, which extends the pretraining objectives of VJEPA, resulting in state-of-the-art video understanding capabilities, leveraging data and model sizes at scale. The code is released in this repository. To run V-JEPA 2 model, ensure you have installed the latest transformers: V-JEPA 2 is intended to represent any video (and image) to perform video classification, retrieval, or as a video encoder for VLMs. To load a video, sample the number of frames according to the model. For this model, we use 64. To load an image, simply copy the image to the desired number of frames. For more code examples, please refer to the V-JEPA 2…
Open weights
mit
654M parameters
transformers
[[Paper]](https://arxiv.org/pdf/2505.13441) [[arXiv]](https://arxiv.org/abs/2505.13441) [[Project Website]](https://abhaybd.github.io/GraspMolmo/) [[Data]](https://huggingface.co/datasets/allenai/PRISM) GraspMolmo is a generalizable open-vocabulary task-oriented grasping (TOG) model for robotic manipulation. Given an image and a task to complete (e.g. "Pour me some tea"), GraspMolmo will point to the most appropriate grasp location, which can then be matched to the closest stable grasp. Running the above code could result in the following output: To predict a grasp point and match it to one of the candidate grasps, refer to the GraspMolmo class. First, install graspmolmo with and then…
Open weights
mit
8B parameters
4,096 tokens
weighted/imatrix quants of https://huggingface.co/nikhilchandak/LlamaForecaster-8B For a convenient overview and download list, visit our model page for this model. static quants are available at https://huggingface.co/mradermacher/LlamaForecaster-8B-GGUF If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files. (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) Here is a handy graph by ikawrakow comparing some lower-quality quant And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 See…
Open weights
mit
transformers
Model · Question answering
VietAI
State-of-the-art pretrained Transformer-based encoder-decoder model for Vietnamese. For more details, do check out our Github repo.
Open weights
mit
transformers
The model was trained by SberDevices. The model is trained on a mix of open summarisation data RussianNLP/Mixed-Summarization-Dataset for the Russian language and use prefix tokenen '\ '
Open weights
mit
1.7B parameters
transformers
We trained a German question answering model with a gelectra-base model as its basis. - The dataset is GermanQuAD, a new, German language dataset, which we hand-annotated and published online. - The training dataset is one-way annotated and contains 11518 questions and 11518 answers, while the test dataset is three-way annotated so that there are 2204 questions and with 2204·3−76 = 6536answers, because we removed 76 wrong answers. See https://deepset.ai/germanquad for more details and dataset download in SQuAD format. Haystack is an AI orchestration framework to build customizable, production-ready LLM applications. You can use this model in Haystack to do extractive question answering on…
Open weights
mit
109M parameters
512 tokens
transformers
