sail/Sailor-14B-Chat-gguf
Same weights, converted vs sail/Sailor-14B-Chat. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/81, MLP 0/120, Attention 0/280, lm_head 0/1
Same weights, converted vs sail/Sailor-14B-Chat. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/81, MLP 0/120, Attention 0/280, lm_head 0/1