mradermacher/EMPO-Qwen2.5-Math-7B-GGUF
Same weights, converted vs qingyangzhang/EMPO-Qwen2.5-Math-7B. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, MLP 0/84, Norms 0/57, Attention 0/196, lm_head 0/1
Same weights, converted vs qingyangzhang/EMPO-Qwen2.5-Math-7B. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, MLP 0/84, Norms 0/57, Attention 0/196, lm_head 0/1