mradermacher/phi-3.1-qlora-blend-dpo-abliterated-GGUF

Same weights, converted vs ndavidson/phi-3.1-qlora-blend-dpo-abliterated. Same weights stored in another dtype (F16 → F16/F32).

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/65, MLP 0/64, Attention 0/64

On the Hub · Downloads on Model Pulse