second-state/Qwen1.5-110B-Chat-GGUF
Same weights, converted vs Qwen/Qwen1.5-110B-Chat. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, MLP 0/240, Attention 0/560, Norms 0/161, lm_head 0/1
Same weights, converted vs Qwen/Qwen1.5-110B-Chat. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, MLP 0/240, Attention 0/560, Norms 0/161, lm_head 0/1