jaygala24/Qwen3-1.7B-GRPO-KL-math-reasoning
Partial fine-tune vs Qwen/Qwen3-1.7B. Partial change: 82% of the weights changed (attention, mlp, norms), in 28 of 28 layers.
Tensors changed: Embeddings 0/1, Norms 92/113, MLP 84/84, Attention 112/112
Partial fine-tune vs Qwen/Qwen3-1.7B. Partial change: 82% of the weights changed (attention, mlp, norms), in 28 of 28 layers.
Tensors changed: Embeddings 0/1, Norms 92/113, MLP 84/84, Attention 112/112