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