mradermacher/krx_Qwen2.5-7B-It_1104-GGUF
Same weights, converted vs Q-PING/krx_Qwen2.5-7B-It_1104. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/57, MLP 0/84, Attention 0/196, lm_head 0/1
Same weights, converted vs Q-PING/krx_Qwen2.5-7B-It_1104. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/57, MLP 0/84, Attention 0/196, lm_head 0/1