Open-Weight Models

Model · Any to any

Qwen2.5-Omni-7B-AWQ

Qwen

Qwen2.5-Omni is an end-to-end multimodal model designed to perceive diverse modalities, including text, images, audio, and video, while simultaneously generating text and natural speech responses in a streaming manner. This model card introduces a series of enhancements designed to improve the Qwen2.5-Omni-7B's operability on devices with constrained GPU memory. Key optimizations include: Implemented 4-bit quantization of the Thinker's weights using AWQ, effectively reducing GPU VRAM usage. Enhanced the inference pipeline to load model weights on-demand for each module and offload them to CPU memory once inference is complete, preventing peak VRAM usage from becoming excessive. Converted…

Model · Time series forecasting

MOMENT-1-small

Auton Lab

MOMENT is a family of foundation models for general-purpose time-series analysis. The models in this family (1) serve as a building block for diverse time-series analysis tasks (e.g., forecasting, classification, anomaly detection, and imputation, etc.), (2) are effective out-of-the-box, i.e., with no (or few) task-specific exemplars (enabling e.g., zero-shot forecasting, few-shot classification, etc.), and (3) are tunable using in-distribution and task-specific data to improve performance. For details on MOMENT models, training data, and experimental results, please refer to the paper MOMENT: A Family of Open Time-series Foundation Models. Recommended Python Version: Python 3.11 (support…

Model · Zero-shot classification

deberta-v3-base-zeroshot-v2.0

Moritz Borrett-Laurer (formerly Laurer)

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…

Model · Zero-shot classification

nli-distilroberta-base

Sentence Transformers - Cross-Encoders

This model was trained using SentenceTransformers Cross-Encoder class. The model was trained on the SNLI and MultiNLI datasets. For a given sentence pair, it will output three scores corresponding to the labels: contradiction, entailment, neutral. For evaluation results, see SBERT.net - Pretrained Cross-Encoder. Pre-trained models can be used like this: You can use the model also directly with Transformers library (without SentenceTransformers library): This model can also be used for zero-shot-classification

Model · Image segmentation

BiRefNet_HR-matting

Peng Zheng

This repo is the official implementation of "Bilateral Reference for High-Resolution Dichotomous Image Segmentation" (CAAI AIR 2024). Visit our GitHub repo: https://github.com/ZhengPeng7/BiRefNet for more details -- codes, docs, and model zoo! This repo contains the weights of BiRefNet proposed in our paper, which has achieved the SOTA performance on three tasks (DIS, HRSOD, and COD). Go to my GitHub page for BiRefNet codes and the latest updates: https://github.com/ZhengPeng7/BiRefNet:) + Online Image Inference on Colab: + Online Inference with GUI on Hugging Face with adjustable resolutions: + Inference and evaluation of your given weights: + Many thanks to @freepik for their generous…

This model is a fine-tuned version of facebook/wav2vec2-base on the None dataset. It achieves the following results on the evaluation set: The following hyperparameters were used during training: - learningrate: 5e-05 - trainbatchsize: 32 - evalbatchsize: 32 - lrschedulertype: linear - numepochs: 2 - Transformers 4.28.0 - Pytorch 2.0.0 - Datasets 2.12.0 - Tokenizers 0.13.3

Model · Robotics

pi0_base

LeRobot

π₀ is a Vision-Language-Action (VLA) foundation model from Physical Intelligence that jointly reasons over vision, language, and actions to control robots, serving as the base architecture that later enabled π₀.₅’s open-world generalization. Original paper: π0: A Vision-Language-Action Flow Model for General Robot Controlion For full installation details (including optional video dependencies such as ffmpeg for torchcodec), see the official documentation: https://huggingface.co/docs/lerobot/installation If you’re training / fine-tuning, you typically call forward(...) to get a loss and then: - -policy.chunksize=... - -policy.nactionsteps=... - -policy.maxactiontokens=...…

Model · Tabular classification

TabPFN-v2-clf

Prior Labs

TabPFN is a transformer-based foundation model for tabular data that leverages prior-data based learning to achieve strong performance on small tabular datasets without requiring task-specific training. For detailed usage examples and best practices, check out: - Python ≥ 3.9 - PyTorch ≥ 2.1 - scikit-learn ≥ 1.0 This repository hosts the production TabPFN-v2 base checkpoints. Files matching the pattern tabpfn-v2-classifier-finetuned-.ckpt are content-identical aliases of the corresponding base checkpoints (e.g. tabpfn-v2-classifier-finetuned-gn2p4bpt-xp6f0iqb.ckpt is identical to tabpfn-v2-classifier-gn2p4bpt.ckpt; tabpfn-v2-classifier-finetuned-zk73skhh.ckpt is identical to…

Model · Any to any

Qwen3-Omni-30B-A3B-FP8

Markus

Block-wise FP8 quantization of Qwen/Qwen3-Omni-30B-A3B-Instruct. - Vision encoder (thinker.visual) - Audio tower (thinker.audiotower) - Code2Wav decoder (code2wav) - vLLM >= 0.13.0 with Qwen3-Omni support - 2x 24GB GPUs (e.g., RTX 3090) or equivalent - ~35 GB disk space Block-wise quantization with 128x128 blocks provides better precision than per-tensor quantization while maintaining good compression. Each block has its own scale factor stored as weightscaleinv (inverse scale for efficient multiplication during inference). This is a quantized version of Qwen/Qwen3-Omni-30B-A3B-Instruct. Qwen3-Omni is a natively end-to-end multilingual omni-modal foundation model that processes text…

Model · Object detection

dfine-xlarge-coco

University of Science and Technology of China

The D-FINE model was proposed in D-FINE: Redefine Regression Task in DETRs as Fine-grained Distribution Refinement by Yansong Peng, Hebei Li, Peixi Wu, Yueyi Zhang, Xiaoyan Sun, Feng Wu This model was contributed by VladOS95-cyber with the help of @qubvel-hf This is the HF transformers implementation for D-FINE coco -> model trained on COCO obj365 -> model trained on Object365 obj2coco -> model trained on Object365 and then finetuned on COCO D-FINE, a powerful real-time object detector that achieves outstanding localization precision by redefining the bounding box regression task in DETR models. D-FINE comprises two key components: Fine-grained Distribution Refinement (FDR) and Global…

However, we observe that the speed and accuracy of YOLOs are negatively affected by the NMS. Recently, end-to-end Transformer-based detectors (DETRs) have provided an alternative to eliminating NMS. Nevertheless, the high computational cost limits their practicality and hinders them from fully exploiting the advantage of excluding NMS. In this paper, we propose the Real-Time DEtection TRansformer (RT-DETR), the first real-time end-to-end object detector to our best knowledge that addresses the above dilemma. We build RT-DETR in two steps, drawing on the advanced DETR: first we focus on maintaining accuracy while improving speed, followed by maintaining speed while improving accuracy.…

Model · Time series forecasting

granite-timeseries-patchtst-fm-r1

IBM Granite

PatchTST was originally released prior to the interest in creating pre-trained, zero-shot time series foundation models that were capable of state-of-the-art performance on out of sample datasets. PatchTST-FM (patched time-series transformer-based foundation model) essentially has the architectural simplicity of PatchTST, but differs in some crucial ways. Coupled with a revised training strategy and a significantly larger training corpus, we are able to train a model that achieves state-of-the-art results on GiftEval (see below for recommended filters to view this on the leaderboard). The architecture incorporates the following changes: - residual blocks in the input and output projections…

Model · Video classification

vjepa2-vitl-fpc16-256-ssv2

AI at Meta

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 ViT-L 256 model with video classification head pretrained on Something-Something-V2 dataset. To run V-JEPA 2 model, ensure you have installed the latest transformers

Model · Text to video

Wan2.2-I2V-A14B-Lightning-Diffusers

Mage.Space

We are excited to introduce Wan2.2, a major upgrade to our foundational video models. With Wan2.2, we have focused on incorporating the following innovations: This repository contains our T2V-A14B model, which supports generating 5s videos at both 480P and 720P resolutions. Built with a Mixture-of-Experts (MoE) architecture, it delivers outstanding video generation quality. On our new benchmark Wan-Bench 2.0, the model surpasses leading commercial models across most key evaluation dimensions. Your browser does not support the video tag. If your research or project builds upon Wan2.1 or Wan2.2, we welcome you to share it with us so we can highlight it for the broader community. - Wan2.2…

Model · Robotics

Alpamayo-1.5-10B

NVIDIA

Alpamayo 1.5 is a significant update to NVIDIA’s open 10B-parameter chain-of-thought reasoning VLA model, designed to be an interactive and steerable reasoning engine for the AV community. Alpamayo 1.5 is built on the Cosmos-Reason2 VLM backbone, is RL post-trained, and introduces support for navigation guidance, flexible camera counts, and user question answering. This model is ready for non-commercial use. Commercial licensing available upon request. Model weights: The model weights are released under the OpenMDW-1.1 license. Source code: Apache License 2.0, as provided in the Alpamayo 1.5 source repository. Global Researchers and autonomous-driving practitioners who are developing and…

Model · Any to any

gemma-4-E4B-it-assistant

Google

Gemma is a family of open models built by Google DeepMind. Gemma 4 models are multimodal, handling text and image input (with audio supported on E2B, E4B, and 12B) and generating text output. This release includes open-weights models in both pre-trained and instruction-tuned variants. Gemma 4 features a context window of up to 256K tokens and maintains multilingual support in over 140 languages. Featuring both Dense and Mixture-of-Experts (MoE) architectures, Gemma 4 is well-suited for tasks like text generation, coding, and reasoning. The models are available in five distinct sizes: E2B, E4B, 12B, 26B A4B, and 31B. Their diverse sizes make them deployable in environments ranging from…

Model · Object detection

rf-detr-base

Roboflow

RF-DETR is a real-time detection transformer family introduced in RF-DETR: Neural Architecture Search for Real-Time Detection Transformers by Robinson et al. and integrated in Transformers via PR #36895. RF-DETR is an end-to-end object detection model that combines ideas from LW-DETR and Deformable DETR: a DINOv2-with-registers style ViT backbone (with an RF-DETR windowing pattern for efficient attention), a multi-scale projector between encoder and decoder, and a multi-scale deformable DETR decoder for fast convergence and strong accuracy–latency tradeoffs. You can use the raw model for object detection. See the model hub to look for all available RF-DETR models. Here is how to use this…

Model · Audio classification

mms-lid-256

AI at Meta

This checkpoint is a model fine-tuned for speech language identification (LID) and part of Facebook's Massive Multilingual Speech project. This checkpoint is based on the Wav2Vec2 architecture and classifies raw audio input to a probability distribution over 256 output classes (each class representing a language). The checkpoint consists of 1 billion parameters and has been fine-tuned from facebook/mms-1b on 256 languages. This MMS checkpoint can be used with Transformers to identify the spoken language of an audio. It can recognize the following 256 languages. Let's look at a simple example. First, we install transformers and some other libraries Note: In order to use MMS you need to have…

Model · Image segmentation

sapiens2-seg-0.4b

AI at Meta

Per-pixel body-part segmentation with 29 classes (28 parts + background). This repository contains the 0.4B Body-Part Segmentation checkpoint, finetuned from the Sapiens2-0.4B pretrained backbone. Install the Sapiens2 repo (pip install -e.), download the checkpoint, and run the demo: See the Body-Part Segmentation guide for details on inputs, outputs, and visualization options. See the Sapiens2 Collection for all variants and other downstream task checkpoints. Released under the Sapiens2 License.

Model · Time series forecasting

MOMENT-1-large

Auton Lab

MOMENT is a family of foundation models for general-purpose time-series analysis. The models in this family (1) serve as a building block for diverse time-series analysis tasks (e.g., forecasting, classification, anomaly detection, and imputation, etc.), (2) are effective out-of-the-box, i.e., with no (or few) task-specific exemplars (enabling e.g., zero-shot forecasting, few-shot classification, etc.), and (3) are tunable using in-distribution and task-specific data to improve performance. For details on MOMENT models, training data, and experimental results, please refer to the paper MOMENT: A Family of Open Time-series Foundation Models. Recommended Python Version: Python 3.11 (support…

Model · Time series forecasting

patchtst-fm-r1

IBM Research

This model card is for the non-commercial, research version of PatchTST-FM-r1. Please also check-out the Apache-2.0 licensed IBM Granite version. PatchTST was originally released prior to the interest in creating pre-trained, zero-shot time series foundation models that were capable of state-of-the-art performance on out of sample datasets. PatchTST-FM (patched time-series transformer-based foundation model) essentially has the architectural simplicity of PatchTST, but differs in some crucial ways. Coupled with a revised training strategy and a significantly larger training corpus, we are able to train a model that achieves state-of-the-art results on GiftEval. The architecture incorporates…

Model · Zero-shot classification

distilbart-mnli-12-1

Suraj Patil

distilbart-mnli is the distilled version of bart-large-mnli created using the No Teacher Distillation technique proposed for BART summarisation by Huggingface, here. We just copy alternating layers from bart-large-mnli and finetune more on the same data. This is a very simple and effective technique, as we can see the performance drop is very little. Detailed performace trade-offs will be posted in this sheet. If you want to train these models yourself, clone the distillbart-mnli repo and follow the steps below Clone and install transformers from source Download MNLI data Create student model Start fine-tuning You can find the logs of these trained models in this wandb project.

Model · Tabular classification

mitra-classifier-2

Autogluon

Mitra-v2 classifier is a tabular foundation model that is pre-trained on purely synthetic datasets sampled from a mix of random classifiers, including the new Hybrid SCM prior. It is the second generation of the Mitra classifier (autogluon/mitra-classifier), pre-trained with a 10x longer context, three times as many features, and an improved optimizer. On the TabArena and TALENT benchmarks it delivers state-of-the-art accuracy at the level of TabFM and EXAONE Tabular, while surpassing TabPFN-3 by a wide margin. The regression model is at autogluon/mitra-regressor-2, and the inference and fine-tuning code with our evaluation results is at autogluon/mitra-finetune. Mitra-v2 is based on a…

Model · Image to video

MiniMax-H3-curve-GGUF

Joey

GGUF quantizations of MiniMax-H3's 33B video+audio DiTs, built from MiniMax's pruned checkpoints. Same model, same quant tiers as the original-form repo, about 40% smaller - and a Q80 that fits a 24 GB card. fl2va = text/first-last-frame to video+audio (T2V and I2V). ref2va = reference-conditioned generation (identity from up to 9 images, 3 videos with soundtracks, 3 voice clips). Runs in ComfyUI with ComfyUI-GGUF plus a one-line architecture patch (node pack: ComfyUI-H3-Multishot; workflows: On anything older these will not load at all, because the shape of the modulation weights changed and older builds do not know how to read them. That is the only catch - everything else is a drop-in…