view article Article The Engineering Handbook for GRPO + LoRA with Verl: Training Qwen2.5 on Multi-GPU 8 days ago • 10
view article Article Tokenization in Transformers v5: Simpler, Clearer, and More Modular +4 23 days ago • 110
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 3756 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-GGUF🐱 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 · 🔥 17 17 🤗 7 7 ❤️ 5 5 🚀 3 3 + Reply
view post Post 2237 ICYMI, transformers v5 is out!Grab a coffee ☕ and go read the announcement blog https://huggingface.co/blog/transformers-v5 See translation 🤗 5 5 🚀 4 4 ❤️ 1 1 + Reply