mradermacher/Mistral-4B-GGUF

Same weights, converted vs fhai50032/Mistral-4B. Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: Embeddings 0/1, Norms 0/33, MLP 0/48, Attention 0/64, lm_head 0/1

On the Hub · Downloads on Model Pulse