EmberJin/Minecraft-Agent-Qwen3.5-9B-Stage3
Partial fine-tune vs Qwen/Qwen3.5-9B. Partial change: 89% of the weights changed (attention, embeddings, lm_head, mlp, norms), in 32 of 32 layers.
Tensors changed: lm_head 1/1, Embeddings 3/4, MLP 207/208, Attention 301/332, Norms 163/215
2 derivatives checked
- sizzlebop/Minecraft-Agent-Qwen3.5-9B-Stage3-GGUF: Same weights, converted
- EmberJin/Minecraft-Agent-CoT-Qwen3.5-9B-Control: Partial fine-tune