phi-2-GGUF / README.md
morriszms's picture
Upload folder using huggingface_hub
7e7a283 verified
metadata
license: mit
license_name: microsoft-research-license
license_link: LICENSE
tags:
  - TensorBlock
  - GGUF
base_model: susnato/phi-2
TensorBlock

Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server

susnato/phi-2 - GGUF

This repo contains GGUF format model files for susnato/phi-2.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4011.

Prompt template


Model file specification

Filename Quant type File Size Description
phi-2-Q2_K.gguf Q2_K 1.034 GB smallest, significant quality loss - not recommended for most purposes
phi-2-Q3_K_S.gguf Q3_K_S 1.165 GB very small, high quality loss
phi-2-Q3_K_M.gguf Q3_K_M 1.328 GB very small, high quality loss
phi-2-Q3_K_L.gguf Q3_K_L 1.467 GB small, substantial quality loss
phi-2-Q4_0.gguf Q4_0 1.492 GB legacy; small, very high quality loss - prefer using Q3_K_M
phi-2-Q4_K_S.gguf Q4_K_S 1.508 GB small, greater quality loss
phi-2-Q4_K_M.gguf Q4_K_M 1.618 GB medium, balanced quality - recommended
phi-2-Q5_0.gguf Q5_0 1.801 GB legacy; medium, balanced quality - prefer using Q4_K_M
phi-2-Q5_K_S.gguf Q5_K_S 1.801 GB large, low quality loss - recommended
phi-2-Q5_K_M.gguf Q5_K_M 1.865 GB large, very low quality loss - recommended
phi-2-Q6_K.gguf Q6_K 2.128 GB very large, extremely low quality loss
phi-2-Q8_0.gguf Q8_0 2.755 GB very large, extremely low quality loss - not recommended

Downloading instruction

Command line

Firstly, install Huggingface Client

pip install -U "huggingface_hub[cli]"

Then, downoad the individual model file the a local directory

huggingface-cli download tensorblock/phi-2-GGUF --include "phi-2-Q2_K.gguf" --local-dir MY_LOCAL_DIR

If you wanna download multiple model files with a pattern (e.g., *Q4_K*gguf), you can try:

huggingface-cli download tensorblock/phi-2-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'