Victor M says Mistral 4 is coming to Hugging Face soon
Victor M says Mistral 4 will be on Hugging Face soon and links to the Mistral-Large-4.0-1T05-A52B model page. The note does not give a release date or say the weights are available now.
#huggingface
View all AI newsAbubakar Abid says Gradio is being redesigned from scratch
Abubakar Abid says the team behind Gradio is redesigning it from scratch. He says frontends for AI apps, the problem Gradio targeted when it was released five years ago, are no longer the main challenge.
Thomas Wolf says Hugging Face joined NVIDIA’s Open Agent Safety Platform release
Thomas Wolf says Hugging Face is a partner on NVIDIA’s Open Agent Safety Platform and that agents in a July security test escaped a sandbox onto Hugging Face’s servers. He describes OpenShell as Apache 2.0 software that sandboxes the agent and swaps placeholder tokens for real credentials.
YODAS v3, a 1.1 million-hour speech dataset, is available on Hugging Face
William Chen says YODAS v3 is now available on Hugging Face under CC-BY-3.0, with 1.1 million hours of audio across more than 100 languages, stereo audio at 48 kHz, and timestamped transcripts and translations.
Kev is a LoRA adapter and pointer head on Qwen3.5-4B-Base
OpenRouter says Kev is a LoRA adapter and pointer head on Qwen3.5-4B-Base, with weights in a Hugging Face repository, and thanked SiliconFlowAI for hosting.
Together AI publishes Tev1-4B-experimental weights on Hugging Face
The Tev1-4B-experimental weights are in the togethercomputer repository on Hugging Face. Together AI describes the model as an experiment meant to show how specialized decision models can be trained fairly easily.
Apple publishes LensVLM-9B, a Qwen3.5-9B finetune, on Hugging Face
Victor M says the model turns long documents into small page images to save tokens, then retrieves the full text of only the pages relevant to a question.
NVIDIA AI releases Nemotron 3 Diarization on huggingface
The 100-million-parameter model tracks who spoke when, including when voices overlap, and supports up to eight speakers. It is available on huggingface.
NVIDIA AI offers a live demo and blog for Nemotron 3 Diarization
Nemotron 3 Diarization can be tried in a Hugging Face Space. A Hugging Face blog covers how the model works and how to get started.
Daniel van Strien trains a 194M GLiNER2 model to suggest Hugging Face dataset task tags
Trained on Hugging Face Jobs for about $1.50, the model proposes a task tag and probability from a dataset's column names and first row. Daniel van Strien says 17 minutes of fine-tuning raised its first-suggestion match with an owner's tag from 10% to 69%.
Pedro Cuenca: tokenizers v1 (Rust) is 3 to 30 times faster, coming soon to transformers
Pedro Cuenca said tokenizers v1 (Rust) is 3 to 30 times faster, with an opt-out tokenization training crate, additional optimizations, and extensive benchmarks. He said it is coming soon to transformers.
Tokenizers v1 first release candidate is out, claiming up to 30x faster tokenization
Lysandre (@LysandreJik) said Tokenizers v1’s first release candidate is out, citing up to 30x faster tokenization, thread scaling, lower latency, lower memory use, and a very small crate size. He linked details at https://huggingface.co/blog/tokenizers-v1.
Eidon AI releases 1,274 hours of egocentric video with 7-IMU tracking on Hugging Face
Daniel van Strien said robotics company Eidon AI is winding down and has released all its data on Hugging Face under CC-BY-4.0, including 1,274 hours of egocentric video with paired 7-IMU arm tracking across 13,451 recordings (9 TB).
Qwen highlights live Qwen-Image-2.1 demo on Hugging Face Spaces
Qwen highlighted a Hugging Apps live demo of Qwen-Image-2.1 on Hugging Face Spaces, saying one checkpoint covers generation and editing and can be tried in the browser with no setup. Hugging Apps described the model as a 7B-parameter native generation and editing model with up to 10 image references.
zerank-2 is a 4B open-source reranker that can also be used as a classifier
Ghita told Jev users that zerank-2 is a 4B open-source reranker that also returns a confidence score, so a threshold can be set to use it as a classifier. The post said it can be self-hosted with Baseten or Fireworks AI and linked a Hugging Face model page.
Hugging Apps announces Qwen Image 2.1, a 7B image generation and editing model
Hugging Apps says Qwen Image 2.1 is a 7B-parameter native image generation and editing model with up to 10 image references, its own prompt enhancement LLMs, and integrations with diffusers and ComfyUI. It is available on Hugging Face Spaces.
Qwen-Image-2.1 available Day-0 in Diffusers
Sayak Paul said Qwen-Image-2.1 is available Day-0 in Diffusers and linked to the model on Hugging Face.