Open-Weight Models

Model · Image to text

PP-OCRv6_medium_rec

PaddlePaddle

PP-OCRv6: From 1.5M to 34.5M Parameters, Surpassing Billion-Scale VLMs on OCR Tasks PP-OCRv6 is a lightweight OCR system that combines architectural innovation with data-centric optimization. It redesigns the backbone, detection neck, and recognition neck around a unified MetaFormer-style building block with structural reparameterization. Three model tiers (medium, small, tiny) share the same block primitives, covering deployment scenarios from server to edge. 1. Unified and Scalable Model Family: A three-tier OCR model family spanning 1.5M to 34.5M parameters. PP-OCRv6medium achieves 86.2% detection Hmean and 83.2% recognition accuracy, outperforming PP-OCRv5server by +4.6% and +5.1%…

Model · Tabular classification

TabSTAR

Alan Arazi

To fit a pretrained TabSTAR model to your own dataset, install the package: Paper: TabSTAR: A Foundation Tabular Model With Semantically Target-Aware Representations

Model · Image to video

MiniMax-H3-GGUF

Bálint Molnár-Kaló

This repository (molbal/MiniMax-H3-GGUF) provides GGUF quantized versions and necessary component files for the MiniMax H3 model. MiniMax H3 is a general-purpose, omni-modal generative system that supports unified understanding of multimodal contexts composed of text, images, video, and audio. It can generate video with native stereo audio at resolutions up to 2K and durations of up to 15 seconds. This repository includes quantized versions of both the FL2VA (First-and-last-frame mode) and Ref2VA (Omni-reference mode) base models. The FL2VA builds are pruned to FP8 first and then quantized to GGUF. minimaxh3fl2vaprunedfp8Q40.gguf (11.4 GB) minimaxh3fl2vaprunedfp8Q80.gguf (20.2 GB)…

Model · Image text to video

MiniMax-H3-Realism-People-LoRA

Fal

A LoRA adapter for MiniMax H3 specialized in realistic people: faces that hold up in close-up, natural skin texture, believable expressions and gestures, film-style lighting and documentary camera movement. Same prompt, same seed — base model on the left, this adapter on the right: 19 pairs, same prompt, same seed, adapter on vs off — the only variable is the LoRA. The trigger word is present on both sides, so it is not doing the work. Each pair plays the base model first, then freezes and dims while the adapted version plays beside it. Close-up talking faces, arguments, several people speaking at once, weathered skin, children, ritual and travel scenes. Nothing cherry-picked from a larger…

Model · Image and text to text

VLX-Seek-1.5-10B

OmAI Lab

VLX-Seek-1.5-10B is the open-source 10B model in the VLX-Seek 1.5 family, designed for fine-grained perception and visual grounding in embodied scenarios. It targets practical settings such as drones, robots, robotic dogs, surveillance cameras, inspection systems, and other edge-side visual intelligence applications where a model must identify what is present, localize the right instance, and avoid grounding objects that are absent. Unlike coordinate-generation-based VLMs that directly decode bounding-box numbers, VLX-Seek reformulates localization as region retrieval and region reference. Candidate visual regions are represented as addressable entities, and the model answers by selecting…

Model · Translation

madlad400-3b-mt

Google

MADLAD-400-3B-MT is a multilingual machine translation model based on the T5 architecture that was trained on 1 trillion tokens covering over 450 languages using publicly available data. It is competitive with models that are significantly larger. Disclaimer: Juarez Bochi, who was not involved in this research, converted the original weights and wrote the contents of this model card based on the original paper and Flan-T5. Find below some example scripts on how to use the model: First, install the Python packages that are required: pip install transformers accelerate sentencepiece Usage with candle: We also provide a quantized model (1.65 GB vs the original 11.8 GB file): See the research…

Model · Translation

opus-mt-fr-es

Helsinki-NLP Research Group

source languages: fr; target languages: es; OPUS readme: fr-es; dataset: opus; model: transformer-align; pre-processing: normalization + SentencePiece.

Model · Image to text

trocr-large-printed

Microsoft

TrOCR model fine-tuned on the SROIE dataset. It was introduced in the paper TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models by Li et al. and first released in this repository. Disclaimer: The team releasing TrOCR did not write a model card for this model so this model card has been written by the Hugging Face team. The TrOCR model is an encoder-decoder model, consisting of an image Transformer as encoder, and a text Transformer as decoder. The image encoder was initialized from the weights of BEiT, while the text decoder was initialized from the weights of RoBERTa. Images are presented to the model as a sequence of fixed-size patches (resolution 16x16), which…

Model · Image segmentation

coco_panoptic_eomt_large_640

Mobile Perception Systems Lab

EoMT (Encoder-only Mask Transformer) is a Vision Transformer (ViT) architecture designed for high-quality and efficient image segmentation. It was introduced in the CVPR 2025 highlight paper: by Tommie Kerssies, Niccolò Cavagnero, Alexander Hermans, Narges Norouzi, Giuseppe Averta, Bastian Leibe, Gijs Dubbelman, and Daan de Geus. The original implementation can be found in this repository. The HuggingFace model page is available at this link. Here is how to use this model for Panotpic Segmentation: If you find our work useful, please consider citing us as

Model · Text to video

Wan2.1-T2V-14B

Wan-AI

In this repository, we present Wan2.1, a comprehensive and open suite of video foundation models that pushes the boundaries of video generation. Wan2.1 offers these key features: This repository features our T2V-14B model, which establishes a new SOTA performance benchmark among both open-source and closed-source models. It demonstrates exceptional capabilities in generating high-quality visuals with significant motion dynamics. It is also the only video model capable of producing both Chinese and English text and supports video generation at both 480P and 720P resolutions. Your browser does not support the video tag. - Wan2.1 Text-to-Video - [x] Multi-GPU Inference code of the 14B and 1.3B…

Model · Translation

opus-mt-it-es

Helsinki-NLP Research Group

source languages: it; target languages: es; OPUS readme: it-es; dataset: opus; model: transformer-align; pre-processing: normalization + SentencePiece.

Model · Image segmentation

upernet-convnext-tiny

OpenMMLab

UperNet framework for semantic segmentation, leveraging a ConvNeXt backbone. UperNet was introduced in the paper Unified Perceptual Parsing for Scene Understanding by Xiao et al. Combining UperNet with a ConvNeXt backbone was introduced in the paper A ConvNet for the 2020s. Disclaimer: The team releasing UperNet + ConvNeXt did not write a model card for this model so this model card has been written by the Hugging Face team. UperNet is a framework for semantic segmentation. It consists of several components, including a backbone, a Feature Pyramid Network (FPN) and a Pyramid Pooling Module (PPM). Any visual backbone can be plugged into the UperNet framework. The framework predicts a…

Model · Translation

ProstT5

Rostlab

ProstT5 is a protein language model (pLM) which can translate between protein sequence and structure. ProstT5 (Protein structure-sequence T5) is based on ProtT5-XL-U50, a T5 model trained on encoding protein sequences using span corruption applied on billions of protein sequences. ProstT5 finetunes ProtT5-XL-U50 on translating between protein sequence and structure using 17M proteins with high-quality 3D structure predictions from the AlphaFoldDB. Protein structure is converted from 3D to 1D using the 3Di-tokens introduced by Foldseek. In a first step, ProstT5 learnt to represent the newly introduced 3Di-tokens by continuing the original span-denoising objective applied on 3Di- and amino…

Model · Image to text

trocr-large-handwritten

Microsoft

TrOCR model fine-tuned on the IAM dataset. It was introduced in the paper TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models by Li et al. and first released in this repository. Disclaimer: The team releasing TrOCR did not write a model card for this model so this model card has been written by the Hugging Face team. The TrOCR model is an encoder-decoder model, consisting of an image Transformer as encoder, and a text Transformer as decoder. The image encoder was initialized from the weights of BEiT, while the text decoder was initialized from the weights of RoBERTa. Images are presented to the model as a sequence of fixed-size patches (resolution 16x16), which…

Model · Text to speech

MOSS-VoiceGenerator

OpenMOSS

MOSS‑TTS Family is an open‑source speech and sound generation model family from MOSI.AI and the OpenMOSS team. It is designed for high‑fidelity, high‑expressiveness, and complex real‑world scenarios, covering stable long‑form speech, multi‑speaker dialogue, voice/character design, environmental sound effects, and real‑time streaming TTS. When a single piece of audio needs to sound like a real person, pronounce every word accurately, switch speaking styles across content, remain stable over tens of minutes, and support dialogue, role‑play, and real‑time interaction, a single TTS model is often not enough. The MOSS‑TTS Family breaks the workflow into five production‑ready models that can be…

Model · Translation

opus-mt-tr-en

Helsinki-NLP Research Group

source languages: tr; target languages: en; OPUS readme: tr-en; dataset: opus; model: transformer-align; pre-processing: normalization + SentencePiece.

Model · Text to speech

higgs-audio-v3-tts-4b-transformers

Apolinário from multimodal AI art

A trustremotecode packaging of bosonai/higgs-audio-v3-tts-4b that loads with plain transformers (no SGLang). The weights are the original checkpoint, copied unchanged; only a small modeling.py / configuration.py pair and an automap were added. The model is a standard Qwen3-4B backbone plus a fused multi-codebook audio embedding/head. Reference-audio encoding and waveform decoding use the transformers-native bosonai/higgs-audio-v2-tokenizer (higgsaudiov2tokenizer), loaded automatically on first use. Requires transformers >= 5.5. generatespeech returns a mono 24 kHz waveform as a CPU float32 tensor [L]. - Generation uses Higgs' delay pattern across 8 codebooks (vocab 1026, incl. BOC/EOC…

Model · Translation

opus-mt-eu-es

Helsinki-NLP Research Group

hfname: eus-spa - sourcelanguages: eus - targetlanguages: spa - opusreadmeurl: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/eus-spa/README.md - originalrepo: Tatoeba-Challenge - srcconstituents: {'eus'} - tgtconstituents: {'spa'} - srcmultilingual: False - tgtmultilingual: False - urlmodel: https://object.pouta.csc.fi/Tatoeba-MT-models/eus-spa/opus-2020-06-17.zip - urltestset: https://object.pouta.csc.fi/Tatoeba-MT-models/eus-spa/opus-2020-06-17.test.txt - srcalpha3: eus - tgtalpha3: spa - shortpair: eu-es - chrF2score: 0.6729999999999999 - brevitypenalty: 0.9640000000000001 - reflen: 12469.0 - srcname: Basque - tgtname: Spanish - traindate: 2020-06-17 - srcalpha2…

Model · Time series forecasting

TimeMoE-50M

Xiaoming Shi

This repository contains the weights of the TimeMoE-50M model of the paper Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts. For details on how to use this model, please visit our GitHub page.

Model · Any to any

gemma-4-E4B-it-ultra-uncensored-heretic-GGUF

LLMfan46

Creating these models takes significant time, work and compute. If you find them useful consider supporting me: Your help will motivate me and would go into further improving my workflow and coverings fees for storage, compute and may even help uncensoring bigger model with rental Cloud GPUs. GGUF quantizations of llmfan46/gemma-4-E4B-it-ultra-uncensored-heretic. attn.oproj Lower refusals indicate fewer content restrictions, while lower KL divergence indicates more closeness to the original model's baseline. Higher refusals cause more rejections, objections, pushbacks, lecturing, censorship, softening and deflections. PIQA (Physical Intuition Question Answering) a ~1,800 questions tests…

Model · Image to text

GLM-OCR-4bit

MLX Community

This model was converted to MLX format from zai-org/GLM-OCR using mlx-vlm version 0.3.10. Refer to the original model card for more details on the model.

F5-TTSRUSSIAN - дообученная версия оригинальной модели F5-TTS, адаптированная для синтеза русской речи. Демо: демо работы модели (F5-TTSRUSSIAN/F5TTSv1Base) и сравнение с XTTS и FishSpeech — F5-TTSRUSSIAN/F5TTSv1Base — первая версия модели, использованная для генерации демо-записей. F5-TTSRUSSIAN/F5TTSv1Baseaccenttune — дообученная версия с полной разметкой ударений (100% предложений в обучающем датасете). Рекомендуется использовать символы ударения для лучшего качества синтеза. F5-TTSRUSSIAN/F5TTSv1Basev2 — дообученная версия (+16 эпох). Добавлена фильтрация данных (удалено ~5% записей с артефактами, soft-clean), с полной разметка ударений в тексте.

Model · Image to text

LightOnOCR-1B-1025

LightOn AI

Full BF16 version of the model. We recommend this variant for inference and further fine-tuning. LightOnOCR-1B is a compact, end-to-end vision–language model for Optical Character Recognition (OCR) and document understanding. It achieves state-of-the-art accuracy in its weight class while being several times faster and cheaper than larger general-purpose VLMs. Highlights LightOnOCR combines a Vision Transformer encoder(Pixtral-based) with a lightweight text decoder(Qwen3-based) distilled from high-quality open VLMs. It is optimized for document parsing tasks, producing accurate, layout-aware text extraction from high-resolution pages. All benchmarks evaluated using vLLM on the Olmo-Bench.…

Model · Time series forecasting

granite-timeseries-ttm-r3

IBM Granite

Building on top of TTM-R1 and TTM-R2, we introduce the next generation of TinyTimeMixer under the Granite time-series foundation model family — Granite-TTM-R3. This release incorporates several novel tiny-neural architectural innovations designed to push the limits of accuracy in high-speed forecasting, a critical requirement for real-world production deployments. Granite-TTM-R3 is a family of pretrained models supporting multiple real-world forecasting scenarios: - Zero-shot forecasting across unseen datasets - Few-shot adaptation effective with as few as ~1K samples - Full fine-tuning for domain-specific optimization - Multivariate time-series forecasting - Exogenous / control variable…