Biggiraffe/Qwen3-0.6B-JSON-SFT-GRPO

Partial fine-tune vs NotoriousH2/Qwen3-0.6B-JSON-SFT. Partial change: 74% of the weights changed (attention, mlp, norms), in 28 of 28 layers.

Tensors changed: Embeddings 0/1, Norms 60/113, MLP 84/84, Attention 112/112

On the Hub · Downloads on Model Pulse