NotoriousH2/Qwen3-0.6B-JSON-SFT
Partial fine-tune vs Qwen/Qwen3-0.6B. 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
6 derivatives checked
- NotoriousH2/Qwen3-0.6B-JSON-SFT-GRPO: LoRA-style
- haensumo/Qwen3-0.6B-JSON-SFT-GRPO: LoRA-style
- ohkwon/Qwen3-0.6B-JSON-SFT-GRPO: LoRA-style
- luckysong777/Qwen3-0.6B-JSON-SFT-GRPO: LoRA-style
- Taewan123/Qwen3-0.6B-JSON-SFT-GRPO: LoRA-style
- Biggiraffe/Qwen3-0.6B-JSON-SFT-GRPO: Partial fine-tune