mradermacher/CodeV-R1-Qwen-7B-GGUF
Same weights, converted vs zhuyaoyu/CodeV-R1-RL-Qwen-7B. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, MLP 0/84, Attention 0/196, Norms 0/57, lm_head 0/1
Same weights, converted vs zhuyaoyu/CodeV-R1-RL-Qwen-7B. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, MLP 0/84, Attention 0/196, Norms 0/57, lm_head 0/1