Hugging Face launches TRL v1.0 for LLM fine-tuning
Hugging Face has released TRL v1.0 to standardize the post-training workflow behind large language models. The…
3 months ago
The latest AI news tracked under Hugging Face.
Hugging Face has released TRL v1.0 to standardize the post-training workflow behind large language models. The…
NVIDIA framed the future of AI as a mix of open and proprietary models, with orchestration,…
IBM Research, Red Hat, and Google Cloud have donated llm-d, an open-source Kubernetes framework for large…
Nvidia is rolling out new ComfyUI features and upscaling tools that speed up local AI video…
Qwen3.5-27B is a 27B parameter multimodal language model that combines vision, long-context reasoning and tool use,…
Researchers at MIT, the Improbable AI lab and ETH Zurich have introduced self distillation fine tuning,…