Thinking-Space/Qwen3-4B-Base-GRPO
Full fine-tune vs Qwen/Qwen3-4B-Base. Fine-tune: 100% of the weights changed, across 36 of 36 layers.
Tensors changed: Embeddings 1/1, Norms 94/145, MLP 108/108, Attention 144/144
Full fine-tune vs Qwen/Qwen3-4B-Base. Fine-tune: 100% of the weights changed, across 36 of 36 layers.
Tensors changed: Embeddings 1/1, Norms 94/145, MLP 108/108, Attention 144/144