mradermacher/microsoft-phi-2-trained-abliterated-QA-1960-all-modules-merged-GGUF

Same weights, converted vs M1LL1X/microsoft-phi-2-trained-abliterated-QA-1960-all-modules-merged. Same weights stored in another dtype (F16 → F16/F32).

Tensors changed: Embeddings 0/1, Norms 0/66, MLP 0/128, Attention 0/256, lm_head 0/2

On the Hub · Downloads on Model Pulse