mradermacher/Mistral-7B-Discord-0.1-DPO-GGUF

Same weights, converted vs BlouseJury/Mistral-7B-Discord-0.1-DPO. Same weights stored in another dtype (BF16/F32 → F16/F32).

Tensors changed: MLP 0/96, Embeddings 0/1, Norms 0/65, Attention 0/128, lm_head 0/1

On the Hub · Downloads on Model Pulse