phi-2-GGUF / README.md
kroonen's picture
Update README.md
1091e55
|
raw
history blame
378 Bytes
metadata
license: mit
tags:
  - phi
  - phi2
  - gguf
  - microsoft
  - llama
  - llama2
  - llamacpp

This is a quantized GGUF version of Microsoft Phi-2 to 4_0, 8_0 bits and the converted 16 FP model.

(link to the original model : https://huggingface.co/microsoft/phi-2)

Disclamer : make sure to have the latest version of llama.cpp after commit b9e74f9bca5fdf7d0a22ed25e7a9626335fdfa48