Open-Weight Models

Model · Text generation

Qwen1.5-MoE-A2.7B

Qwen

Qwen1.5-MoE is a transformer-based MoE decoder-only language model pretrained on a large amount of data. For more details, please refer to our blog post and GitHub repo. Qwen1.5-MoE employs Mixture of Experts (MoE) architecture, where the models are upcycled from dense language models. For instance, Qwen1.5-MoE-A2.7B is upcycled from Qwen-1.8B. It has 14.3B parameters in total and 2.7B activated parameters during runtime, while achieving comparable performance to Qwen1.5-7B, it only requires 25% of the training resources. We also observed that the inference speed is 1.74 times that of Qwen1.5-7B. The code of Qwen1.5-MoE has been in the latest Hugging face transformers and we advise you to…

This repository hosts the official pretrained model checkpoints, vocabularies, and statistical datasets for the sinlib library—a comprehensive Sinhala NLP toolkit. This repository contains the following files loaded dynamically by sinlib.spellcheck.TypoDetector: bigrudetector.pt: A bidirectional GRU sequence labeling model (BiGRUSequenceLabeler) trained to detect spelling errors and character substitutions at the akshara level. bigrucorrector.pt: A sequence-to-sequence bidirectional GRU encoder-decoder model with Attention (BiGRUSeq2Seq) that performs generative character/akshara corrections. aksharavocab.json: Vocabulary mappings mapping Sinhala phonological units (aksharas) and basic…

Model · Image and text to text

vllm-translategemma-4b-it

Infomaniak Network SA

This is a modified version of google/translategemma-4b-it optimized for deployment with vLLM. The original TranslateGemma model requires a structured payload with dedicated sourcelangcode and targetlangcode fields: However, vLLM does not support these custom content parameters. To maintain compatibility, the chat template has been modified to encode language codes directly in the message content using a delimiter-based format: Format: >>{sourcelang} >>{targetlang} >>{texttotranslate} If you need to provide a custom prompt input The original model uses the new Transformers RoPE configuration format with separate attention type settings: This has been simplified for vLLM compatibility: The…

Model

ltx-2

Comfy Org

Repackaged model files for ComfyUI. Place the files in the following folders: - ltx2-squish.safetensors from ovi054/LTX-2-19b-Squish-LoRA/ trigger word: squish it

Model · Sentence similarity

LaBSE

Sentence Transformers

This is a port of the LaBSE model to PyTorch. It can be used to map 109 languages to a shared vector space. Using this model becomes easy when you have sentence-transformers installed: Then you can use the model like this: Have a look at LaBSE for the respective publication that describes LaBSE.

Model · Text generation

DeepSeek-R1

DeepSeek

We introduce our first-generation reasoning models, DeepSeek-R1-Zero and DeepSeek-R1. DeepSeek-R1-Zero, a model trained via large-scale reinforcement learning (RL) without supervised fine-tuning (SFT) as a preliminary step, demonstrated remarkable performance on reasoning. With RL, DeepSeek-R1-Zero naturally emerged with numerous powerful and interesting reasoning behaviors. However, DeepSeek-R1-Zero encounters challenges such as endless repetition, poor readability, and language mixing. To address these issues and further enhance reasoning performance, we introduce DeepSeek-R1, which incorporates cold-start data before RL. DeepSeek-R1 achieves performance comparable to OpenAI-o1 across…

Model · Speech recognition

faster-whisper-small.en

Systran

This repository contains the conversion of openai/whisper-small.en to the CTranslate2 model format. This model can be used in CTranslate2 or projects based on CTranslate2 such as faster-whisper. The original model was converted with the following command: Note that the model weights are saved in FP16. This type can be changed when the model is loaded using the computetype option in CTranslate2. For more information about the original model, see its model card.

Model · Text to speech

Kokoro-82M-v1.0-ONNX

ONNX Community

Kokoro is a frontier TTS model for its size of 82 million parameters (text in/audio out). First, install the kokoro-js library from NPM using: You can then generate speech as follows: Optionally, save the audio to a file: The model is resilient to quantization, enabling efficient high-quality speech synthesis at a fraction of the original model size.

Model

answerai-colbert-small-v1

Answer.AI

answerai-colbert-small-v1 is a new, proof-of-concept model by Answer.AI, showing the strong performance multi-vector models with the new JaColBERTv2.5 training recipe and some extra tweaks can reach, even with just 33 million parameters. While being MiniLM-sized, it outperforms all previous similarly-sized models on common benchmarks, and even outperforms much larger popular models such as e5-large-v2 or bge-base-en-v1.5. For more information about this model or how it was trained, head over to the announcement blogpost. This model was designed with the upcoming RAGatouille overhaul in mind. However, it's compatible with all recent ColBERT implementations! This model can be used with…

Model · Image feature extraction

dinov3-vitl16-pretrain-lvd1689m

Camenduru

DINOv3 is a family of versatile vision foundation models that outperforms the specialized state of the art across a broad range of settings, without fine-tuning. DINOv3 produces high-quality dense features that achieve outstanding performance on various vision tasks, significantly surpassing previous self- and weakly-supervised foundation models. These are Vision Transformer and ConvNeXt models trained following the method described in the DINOv3 paper. 12 models are provided: - 10 models pretrained on web data (LVD-1689M dataset) - 1 ViT-7B trained from scratch, - 5 ViT-S/S+/B/L/H+ models distilled from the ViT-7B, - 4 ConvNeXt-{T/S/B/L} models distilled from the ViT-7B, - 2 models…

Model · Speech recognition

VibeVoice-ASR

Microsoft

VibeVoice-ASR is a unified speech-to-text model designed to handle 60-minute long-form audio in a single pass, generating structured transcriptions containing Who (Speaker), When (Timestamps), and What (Content), with support for Customized Hotwords and over 50 languages. - 60-minute Single-Pass Processing: Unlike conventional ASR models that slice audio into short chunks (often losing global context), VibeVoice ASR accepts up to 60 minutes of continuous audio input within 64K token length. This ensures consistent speaker tracking and semantic coherence across the entire hour. Users can provide customized hotwords (e.g., specific names, technical terms, or background info) to guide the…

Model · Text classification

bert-base-multilingual-uncased-sentiment

NLP Town

Visit the NLP Town website for an updated version of this model, with a 40% error reduction on product reviews. This is a bert-base-multilingual-uncased model finetuned for sentiment analysis on product reviews in six languages: English, Dutch, German, French, Spanish, and Italian. It predicts the sentiment of the review as a number of stars (between 1 and 5). This model is intended for direct use as a sentiment analysis model for product reviews in any of the six languages above or for further finetuning on related sentiment analysis tasks. Here is the number of product reviews we used for finetuning the model: The fine-tuned model obtained the following accuracy on 5,000 held-out product…

ViTMatte model trained on Composition-1k. It was introduced in the paper ViTMatte: Boosting Image Matting with Pretrained Plain Vision Transformers by Yao et al. and first released in this repository. Disclaimer: The team releasing ViTMatte did not write a model card for this model so this model card has been written by the Hugging Face team. ViTMatte is a simple approach to image matting, the task of accurately estimating the foreground object in an image. The model consists of a Vision Transformer (ViT) with a lightweight head on top. alt="drawing" width="600"/> You can use the raw model for image matting. See the model hub to look for other fine-tuned versions that may interest you. We…

Model · Image to text

PP-OCRv5_server_det

PaddlePaddle

PP-OCRv5serverdet is one of the PP-OCRv5det series, the latest generation of text detection models developed by the PaddleOCR team. Designed for high-performance applications, it supports the detection of text in diverse scenarios—including handwriting, vertical, rotated, and curved text—across multiple languages such as Simplified Chinese, Traditional Chinese, English, and Japanese. Key features include robust handling of complex layouts, varying text sizes, and challenging backgrounds, making it suitable for practical applications like document analysis, license plate recognition, and scene text detection. The key accuracy metrics are as follow: Please refer to the following commands to…

Model · Text generation

NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4

NVIDIA

September 2025 \- December 2025 The post-training data has a cutoff date of November 28, 2025\. The pre-training data has a cutoff date of June 25, 2025\. Nemotron-Nano-3-30B-A3B-NVFP4 is a quantized version of Nemotron-Nano-3-30B-A3B and is a large language model (LLM) trained from scratch by NVIDIA, and designed as a unified model for both reasoning and non-reasoning tasks. It responds to user queries and tasks by first generating a reasoning trace and then concluding with a final response. The model's reasoning capabilities can be configured through a flag in the chat template. If the user prefers the model to provide its final answer without intermediate reasoning traces, it can be…

Model · Any to any

Qwen3-Omni-30B-A3B-Instruct

Qwen

Qwen3-Omni is the natively end-to-end multilingual omni-modal foundation models. It processes text, images, audio, and video, and delivers real-time streaming responses in both text and natural speech. We introduce several architectural upgrades to improve performance and efficiency. Key features: Qwen3-Omni supports a wide range of multimodal application scenarios, covering various domain tasks involving audio, image, video, and audio-visual modalities. Below are several cookbooks demonstrating the usage cases of Qwen3-Omni and these cookbooks include our actual execution logs. You can first follow the QuickStart guide to download the model and install the necessary inference environment…

이 모델은 AI 허브 한국어 감정 데이터셋을 활용하여 Hugging Face의 beomi/KcBERT-base 모델을 파인튜닝한 감정 분석 모델입니다. 한국어 텍스트의 감정을 긍정, 부정, 중립 등으로 분류할 수 있도록 설계되었습니다. 이 모델은 고객 리뷰 분석, 소셜 미디어 모니터링, 감정적 맥락 이해 등 다양한 한국어 기반 응용 프로그램에서 활용할 수 있습니다. 기반 모델: beomi/KcBERT-base 프레임워크: Hugging Face Transformers 모델의 파인튜닝 과정은 Jupyter Notebook을 활용하여 수행되었습니다. 관련 코드는 아래 GitHub 링크에서 확인할 수 있습니다. 이 모델과 학습 코드는 MIT 라이센스를 따릅니다. 자유롭게 사용, 수정 및 배포할 수 있습니다. GitHub Issues를 통해 문제를 보고하거나, Pull Request를 통해 기여해 주세요.

This GGUF file is a direct conversion of Wan-AI/Wan2.2-T2V-A14B Since this is a quantized model, all original licensing terms and usage restrictions remain in effect. Usage The model can be used with the ComfyUI custom node ComfyUI-GGUF by city96 Place model files in ComfyUI/models/unet see the GitHub readme for further installation instructions.

Model

flux1-dev

Comfy Org

Repackaged model files for ComfyUI. Place the files in the following folders: This is a smaller checkpoint for flux1-dev that will work better for ComfyUI users with less VRAM (under 24gb). The two text encoders used by Flux are already included in this one safetensor. Use it with the Load Checkpoint node in ComfyUI.

Model · Text generation

deepseek-coder-7b-instruct-v1.5

DeepSeek

Deepseek-Coder-7B-Instruct-v1.5 is continue pre-trained from Deepseek-LLM 7B on 2T tokens by employing a window size of 4K and next token prediction objective, and then fine-tuned on 2B tokens of instruction data. Here give some examples of how to use our model. This code repository is licensed under the MIT License. The use of DeepSeek Coder models is subject to the Model License. DeepSeek Coder supports commercial use. See the LICENSE-MODEL for more details. If you have any questions, please raise an issue or contact us at [email protected].

Model · Image and text to text

gemma-4-12b-it-GGUF

Unsloth AI

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 · Text generation

Ornith-1.5-9B-NVFP4

Ornith

Chirp Chirp! We are introducing Ornith-1.5, a major step toward building foundation models through end-to-end self-improvement. Ornith-1.5 extends Ornith-1.0 (which was developed on top of Qwen3.5 and Gemma4 with additional continued pretraining, mid-training, and post-training) by expanding the self-improvement loop from scaffold and rollout optimization to jointly optimizing task generation, scaffold construction, and solution rollouts. Rather than relying on a fixed set of human-curated tasks and manually designed harnesses, Ornith-1.5 continuously generates new training tasks, discovers effective strategies for solving them, and improves the policy through reinforcement learning. For…

Model · Translation

opus-mt-en-ru

Helsinki-NLP Research Group

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