h31337/Qwen-14B-Chat-GGUF
Same weights, converted vs Qwen/Qwen-14B-Chat. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Attention 0/120, Norms 0/81, MLP 0/120, Embeddings 0/1, lm_head 0/1
Same weights, converted vs Qwen/Qwen-14B-Chat. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Attention 0/120, Norms 0/81, MLP 0/120, Embeddings 0/1, lm_head 0/1