#reasoning
Lightning McQwen3: Making Qwen3-0.6B think more efficiently #llm#reasoning#post-training How I trained Qwen3-0.6B to use 47% fewer tokens for under one point of accuracy, with thinking still on, mostly on one 12 GB GPU.
How I trained Qwen3-0.6B to use 47% fewer tokens for under one point of accuracy, with thinking still on, mostly on one 12 GB GPU.