legraphista/Nxcode-CQ-7B-orpo-IMat-GGUF
Same weights, converted vs NTQAI/Nxcode-CQ-7B-orpo. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/65, MLP 0/96, Attention 0/224, lm_head 0/1
Same weights, converted vs NTQAI/Nxcode-CQ-7B-orpo. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/65, MLP 0/96, Attention 0/224, lm_head 0/1