view post Post 1730 New GRPO + TRL free Colab notebook out! 🔥Fine-tune 7B+ models on T4 GPUs thanks to a ton of memory optimizations for GRPO 7B model uses only 9.2 GB VRAM (~7× reduction) 🤯Try the notebook here 👉 https://colab.research.google.com/github/huggingface/trl/blob/main/examples/notebooks/grpo_trl_lora_qlora.ipynb See translation 🔥 7 7 👍 2 2 + Reply
view article Article Small Yet Mighty: Improve Accuracy In Multimodal Search and Visual Document Retrieval with Llama Nemotron RAG Models 4 days ago • 12
nvidia/nemotron-speech-streaming-en-0.6b Automatic Speech Recognition • Updated 5 days ago • 1.86k • 264