mradermacher/DeepWereWolf-Qwen3-8B-Grpo-Agentic-Chinese-GGUF

Same weights, converted vs haowu11/DeepWereWolf-Qwen3-8B-Grpo-Agentic-Chinese. Same weights stored in another dtype (BF16 → F16/F32).

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

On the Hub · Downloads on Model Pulse