Open-Weight Models

Model · Text ranking

Qwen3-Reranker-4B

Qwen

The Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks. Building upon the dense foundational models of the Qwen3 series, it provides a comprehensive range of text embeddings and reranking models in various sizes (0.6B, 4B, and 8B). This series inherits the exceptional multilingual capabilities, long-text understanding, and reasoning skills of its foundational model. The Qwen3 Embedding series represents significant advancements in multiple text embedding and ranking tasks, including text retrieval, code retrieval, text classification, text clustering, and bitext mining. Exceptional Versatility: The…

Model · Image and text to text

Qwen2.5-VL-3B-Instruct

Qwen

licensename: qwen-research licenselink: https://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct/blob/main/LICENSE pipelinetag: image-text-to-text - multimodal libraryname: transformers In the past five months since Qwen2-VL’s release, numerous developers have built new models on the Qwen2-VL vision-language models, providing us with valuable feedback. During this period, we focused on building more useful vision-language models. Today, we are excited to introduce the latest addition to the Qwen family: Qwen2.5-VL. Understanding long videos and capturing events: Qwen2.5-VL can comprehend videos of over 1 hour, and this time it has a new ability of cpaturing event by pinpointing the relevant video…

Model · Image and text to text

Qwen3-VL-8B-Instruct-FP8

Qwen

Meet Qwen3-VL — the most powerful vision-language model in the Qwen series to date. This generation delivers comprehensive upgrades across the board: superior text understanding & generation, deeper visual perception & reasoning, extended context length, enhanced spatial and video dynamics comprehension, and stronger agent interaction capabilities. Available in Dense and MoE architectures that scale from edge to cloud, with Instruct and reasoning‑enhanced Thinking editions for flexible, on‑demand deployment. Text Understanding on par with pure LLMs: Seamless text–vision fusion for lossless, unified comprehension. 1. Interleaved-MRoPE: Full‑frequency allocation over time, width, and height…

Model · Audio classification

wav2vec2-large-robust-24-ft-age-gender

audEERING GmbH

The model expects a raw audio signal as input and outputs predictions for age in a range of approximately 0...1 (0...100 years) and gender expressing the probababilty for being child, female, or male. In addition, it also provides the pooled states of the last transformer layer. The model was created by fine-tuning Wav2Vec2-Large-Robust Timit and For this version of the model we trained all 24 transformer layers. An ONNX export of the model is available from Further details are given in the associated paper and tutorial.

Model · Feature extraction

bge-base-en-v1.5

Joshua

https://huggingface.co/BAAI/bge-base-en-v1.5 with ONNX weights to be compatible with Transformers.js. If you haven't already, you can install the Transformers.js JavaScript library from NPM using: You can then use the model to compute embeddings, as follows: You can also use the model for retrieval. For example: 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 and structuring your repo like this one (with ONNX weights located in a subfolder named onnx).

Model · Speech recognition

wav2vec2-large-xlsr-53-hungarian

Jonatas Grosman

Fine-tuned facebook/wav2vec2-large-xlsr-53 on Hungarian using the train and validation splits of Common Voice 6.1 and CSS10. When using this model, make sure that your speech input is sampled at 16kHz. This model has been fine-tuned thanks to the GPU credits generously given by the OVHcloud:) The script used for training can be found here: https://github.com/jonatasgrosman/wav2vec2-sprint The model can be used directly (without a language model) as follows... Using the HuggingSound library: The model can be evaluated as follows on the Hungarian test data of Common Voice. In the table below I report the Word Error Rate (WER) and the Character Error Rate (CER) of the model. I ran the…

Kronos is the first open-source foundation model for financial candlesticks (K-lines), trained on data from over 45 global exchanges. It is designed to handle the unique, high-noise characteristics of financial data. Kronos is a family of decoder-only foundation models, pre-trained specifically for the "language" of financial markets—K-line sequences. It leverages a novel two-stage framework: 1. A specialized tokenizer first quantizes continuous, multi-dimensional K-line data (OHLCV) into hierarchical discrete tokens. 2. A large, autoregressive Transformer is then pre-trained on these tokens, enabling it to serve as a unified model for diverse quantitative tasks. The success of large-scale…

Model · Speech recognition

faster-whisper-tiny

Systran

This repository contains the conversion of openai/whisper-tiny 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 · Feature extraction

mxbai-embed-large-v1

Mixedbread

Here, we provide several ways to produce sentence embeddings. Please note that you have to provide the prompt Represent this sentence for searching relevant passages: for query if you want to use it for retrieval. Besides that you don't need any prompt. Our model also supports Matryoshka Representation Learning and binary quantization. Here, we provide several ways to produce sentence embeddings. Please note that you have to provide the prompt Represent this sentence for searching relevant passages: for query if you want to use it for retrieval. Besides that you don't need any prompt. If you haven't already, you can install the Transformers.js JavaScript library from NPM using: You can then…

As Figure 1 illustrates, ColBERT relies on fine-grained contextual late interaction: it encodes each passage into a matrix of token-level embeddings (shown above in blue). Then at search time, it embeds every query into another matrix (shown in green) and efficiently finds passages that contextually match the query using scalable vector-similarity (MaxSim) operators. These rich interactions allow ColBERT to surpass the quality of single-vector representation models, while scaling efficiently to large corpora. You can read more in our papers: ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT (SIGIR'20). Relevance-guided Supervision for OpenQA with…

Model · Text generation

Qwen2.5-14B-Instruct

Qwen

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…

Model · Zero shot image classification

siglip2-giant-opt-patch16-384

Google

SigLIP 2 extends the pretraining objective of SigLIP with prior, independently developed techniques into a unified recipe, for improved semantic understanding, localization, and dense features. You can use the raw model for tasks like zero-shot image classification and image-text retrieval, or as a vision encoder for VLMs (and other vision tasks). Here is how to use this model to perform zero-shot image classification: You can encode an image using the Vision Tower like so: For more code examples, we refer to the siglip documentation. SigLIP 2 adds some clever training objectives on top of SigLIP: SigLIP 2 is pre-trained on the WebLI dataset (Chen et al., 2023). The model was trained on up…

Model · Image and text to text

Qwen3.5-0.8B

Qwen

Over recent months, we have intensified our focus on developing foundation models that deliver exceptional utility and performance. Qwen3.5 represents a significant leap forward, integrating breakthroughs in multimodal learning, architectural efficiency, reinforcement learning scale, and global accessibility to empower developers and enterprises with unprecedented capability and efficiency. For more details, please refer to our blog post Qwen3.5. WMT24++: a harder subset of WMT24 after difficulty labeling and rebalancing; we report the averaged scores on 55 languages using XCOMET-XXL. Empty cells (--) indicate scores not yet available or not applicable. Scores of Qwen3.5 models are reported…

Model

Mistral-7B-Instruct-v0.3

Mistral AI_

The Mistral-7B-Instruct-v0.3 Large Language Model (LLM) is an instruct fine-tuned version of the Mistral-7B-v0.3. Mistral-7B-v0.3 has the following changes compared to Mistral-7B-v0.2 It is recommended to use mistralai/Mistral-7B-Instruct-v0.3 with mistral-inference. For HF transformers code snippets, please keep scrolling. After installing mistralinference, a mistral-chat CLI command should be available in your environment. You can chat with the model using If you want to use Hugging Face transformers to generate text, you can do something like this. To use this example, you'll need transformers version 4.42.0 or higher. Please see the in the transformers docs for more information. Note…

Model · Speech recognition

wav2vec2-large-xlsr-53-arabic

Jonatas Grosman

Fine-tuned facebook/wav2vec2-large-xlsr-53 on Arabic using the train and validation splits of Common Voice 6.1 and Arabic Speech Corpus. When using this model, make sure that your speech input is sampled at 16kHz. This model has been fine-tuned thanks to the GPU credits generously given by the OVHcloud:) The script used for training can be found here: https://github.com/jonatasgrosman/wav2vec2-sprint The model can be used directly (without a language model) as follows... Using the HuggingSound library: The model can be evaluated as follows on the Arabic test data of Common Voice. In the table below I report the Word Error Rate (WER) and the Character Error Rate (CER) of the model. I ran the…

Model · Text ranking

mmarco-mMiniLMv2-L12-H384-v1

Sentence Transformers - Cross-Encoders

This model was trained on the MMARCO dataset. It is a machine translated version of MS MARCO using Google Translate. It was translated to 14 languages. In our experiments, we observed that it performs also well for other languages. As a base model, we used the multilingual MiniLMv2 model. The model can be used for Information Retrieval: Given a query, encode the query will all possible passages (e.g. retrieved with ElasticSearch). Then sort the passages in a decreasing order. See SBERT.net Retrieve & Re-rank for more details. The training code is available here: SBERT.net Training MS Marco The usage becomes easy when you have SentenceTransformers installed. Then, you can use the pre-trained…

Model · Speech recognition

Qwen3-ASR-1.7B

Qwen

The Qwen3-ASR family includes Qwen3-ASR-1.7B and Qwen3-ASR-0.6B, which support language identification and ASR for 52 languages and dialects. Both leverage large-scale speech training data and the strong audio understanding capability of their foundation model, Qwen3-Omni. Experiments show that the 1.7B version achieves state-of-the-art performance among open-source ASR models and is competitive with the strongest proprietary commercial APIs. Here are the main features: Novel and strong forced alignment Solution: We introduce Qwen3-ForcedAligner-0.6B, which supports timestamp prediction for arbitrary units within up to 5 minutes of speech in 11 languages. Evaluations show its timestamp…

Uncensored Qwen3.8-27B, published as GGUF quantizations with the multi token prediction (MTP) head retained and verified. Refusal behaviour has been substantially reduced, not eliminated. See Measured behaviour for the numbers. Capabilities, training data, and architecture are otherwise unchanged. - Refusal directions removed with Heretic, which co minimizes refusal count against KL divergence from the base model. No handwritten refusal removal code, no finetuning, no additional training data. - Abliteration runs at bf16 (no 4 bit quantization). the resulting LoRA is merged into the bf16 base, so the published weights are not a quantized round trip. - mtp. tensors are copied verbatim from…

Model · Image and text to text

DeepSeek-OCR

DeepSeek

Inference using Huggingface transformers on NVIDIA GPUs. Requirements tested on python 3.12.9 + CUDA11.8： Refer to GitHub for guidance on model inference acceleration and PDF processing, etc. [2025/10/23] DeepSeek-OCR is now officially supported in upstream vLLM. We would like to thank Vary, GOT-OCR2.0, MinerU, PaddleOCR, OneChart, Slow Perception for their valuable models and ideas. author={Wei, Haoran and Sun, Yaofeng and Li, Yukun}, year={2025}

Model

spkrec-ecapa-voxceleb

SpeechBrain

This repository provides all the necessary tools to perform speaker verification with a pretrained ECAPA-TDNN model using SpeechBrain. The system can be used to extract speaker embeddings as well. It is trained on Voxceleb 1+ Voxceleb2 training data. For a better experience, we encourage you to learn more about SpeechBrain. The model performance on Voxceleb1-test set(Cleaned) is: This system is composed of an ECAPA-TDNN model. It is a combination of convolutional and residual blocks. The embeddings are extracted using attentive statistical pooling. The system is trained with Additive Margin Softmax Loss. Speaker Verification is performed using cosine distance between speaker embeddings.…

Model · Text generation

DeepSeek-V3.2

DeepSeek

We introduce DeepSeek-V3.2, a model that harmonizes high computational efficiency with superior reasoning and agent performance. Our approach is built upon three key technical breakthroughs: 1. DeepSeek Sparse Attention (DSA): We introduce DSA, an efficient attention mechanism that substantially reduces computational complexity while preserving model performance, specifically optimized for long-context scenarios. 2. Scalable Reinforcement Learning Framework: By implementing a robust RL protocol and scaling post-training compute, DeepSeek-V3.2 performs comparably to GPT-5. Notably, our high-compute variant, DeepSeek-V3.2-Speciale, surpasses GPT-5 and exhibits reasoning proficiency on par…

Model · Zero shot image classification

clip-vit-large-patch14-336

OpenAI

This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set: The following hyperparameters were used during training: - trainingprecision: float32 - Transformers 4.21.3 - TensorFlow 2.8.2 - Tokenizers 0.12.1

Qwen3.8-27B uncensored by HauhauCS 0/465 Refusals. This is the Aggressive variant: direct answers, no refusal behavior, and minimal preamble on hard prompts. Every text GGUF preserves Qwen3.8's native NextN head, and this release adds HauhauCS FastMTP: a specific acceleration sidecar qualified across the complete quant lineup at maximum native context. Vision is included through the separate BF16 projector. No changes to datasets or intended capabilities. This release preserves Qwen3.8-27B's text, reasoning, agentic, image, and video capabilities while applying the HauhauCS Aggressive uncensoring profile. Pick Aggressive when you specifically want the model to get to the answer without…

Model · Fill mask

Bio_ClinicalBERT

Emily Alsentzer

The Publicly Available Clinical BERT Embeddings paper contains four unique clinicalBERT models: initialized with BERT-Base (casedL-12H-768A-12) or BioBERT (BioBERT-Base v1.0 + PubMed 200K + PMC 270K) & trained on either all MIMIC notes or only discharge summaries. This model card describes the Bio+Clinical BERT model, which was initialized from BioBERT & trained on all MIMIC notes. The BioClinicalBERT model was trained on all notes from MIMIC III, a database containing electronic health records from ICU patients at the Beth Israel Hospital in Boston, MA. For more details on MIMIC, see here. All notes from the NOTEEVENTS table were included (~880M words). Each note in MIMIC was first split…