haowu11/DeepWereWolf-Qwen3-8B-Grpo-Agentic-Chinese

Partial fine-tune vs Qwen/Qwen3-8B. Partial change: 85% of the weights changed (attention, mlp, norms), in 36 of 36 layers.

Tensors changed: Embeddings 0/1, Norms 96/145, MLP 108/108, Attention 144/144, lm_head 0/1

2 derivatives checked

• mradermacher/DeepWereWolf-Qwen3-8B-Grpo-Agentic-Chinese-i1-GGUF: Quantization
• mradermacher/DeepWereWolf-Qwen3-8B-Grpo-Agentic-Chinese-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse