reasoning-cues/smollm3-rl
043
Update README.md
Card: merge-and-save for vLLM, load base tokenizer, exact prompt formatting, pin base revision
Update README.md
GRPO RL LoRA adapter for SmolLM3-3B-Base
initial commit
Update README.md
Card: merge-and-save for vLLM, load base tokenizer, exact prompt formatting, pin base revision
Update README.md
GRPO RL LoRA adapter for SmolLM3-3B-Base
initial commit