gaianet/Phi-3-medium-128k-instruct-GGUF

Same weights, converted vs microsoft/Phi-3-medium-128k-instruct. Same weights stored in another dtype (BF16 → F16/F32), plus 2 new tensors.

Tensors changed: Embeddings 0/1, Norms 0/81, MLP 0/80, Attention 0/80, lm_head 0/1

On the Hub · Downloads on Model Pulse