mradermacher/Qwen-7B-Chat-Cantonese-GGUF
Same weights, converted vs stvlynn/Qwen-7B-Chat-Cantonese. Same weights stored in another dtype (F16 → F16/F32).
Tensors changed: Attention 0/96, Norms 0/65, MLP 0/96, Embeddings 0/1, lm_head 0/1
Same weights, converted vs stvlynn/Qwen-7B-Chat-Cantonese. Same weights stored in another dtype (F16 → F16/F32).
Tensors changed: Attention 0/96, Norms 0/65, MLP 0/96, Embeddings 0/1, lm_head 0/1