mradermacher/Mistral-10.7B-v0.2-GGUF
Same weights, converted vs Joseph717171/Mistral-10.7B-v0.2. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: MLP 0/144, Attention 0/192, Norms 0/97, Embeddings 0/1, lm_head 0/1
Same weights, converted vs Joseph717171/Mistral-10.7B-v0.2. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: MLP 0/144, Attention 0/192, Norms 0/97, Embeddings 0/1, lm_head 0/1