LTX-2: Efficient Joint Audio-Visual Foundation Model Paper β’ 2601.03233 β’ Published 11 days ago β’ 121
view article Article Scaling Real-Time Voice Agents with Cache-Aware Streaming ASR 11 days ago β’ 62
view article Article The Engineering Handbook for GRPO + LoRA with Verl: Training Qwen2.5 on Multi-GPU 15 days ago β’ 12
view article Article Tokenization in Transformers v5: Simpler, Clearer, and More Modular +4 about 1 month ago β’ 114
view reply Hi @kyars is there any part that you think i can improve upon or is it everything?would appreciate any feedback!
view post Post 3799 Mistral's new Ministral 3 models can now be Run & Fine-tuned locally! (16GB RAM)Ministral 3 have vision support and the best-in-class performance for their sizes.14B Instruct GGUF: unsloth/Ministral-3-14B-Instruct-2512-GGUF14B Reasoning GGUF: unsloth/Ministral-3-14B-Reasoning-2512-GGUFπ± Step-by-step Guide: https://docs.unsloth.ai/new/ministral-3All GGUFs, BnB, FP8 etc. variants uploads: https://huggingface.co/collections/unsloth/ministral-3 See translation 3 replies Β· π₯ 17 17 π€ 7 7 β€οΈ 5 5 π 3 3 + Reply
view post Post 2245 ICYMI, transformers v5 is out!Grab a coffee β and go read the announcement blog https://huggingface.co/blog/transformers-v5 See translation π€ 5 5 π 4 4 β€οΈ 1 1 + Reply