tucano2-commerce / notebooks /v4_instruct_grpo.ipynb
rtferraz's picture
v4: ROOT CAUSE FIX — use standard PEFT not Unsloth get_peft_model (fused LoRA kernels have dtype bug #4891). Revert to load_in_4bit=True, dtype=None matching V3.
521e1d8 verified
Open in Colab
Rendering notebook...