second-state/CodeQwen1.5-7B-Chat-GGUF
Same weights, converted vs Qwen/CodeQwen1.5-7B-Chat. 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 Qwen/CodeQwen1.5-7B-Chat. 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