Hugging Face's logo

tensorblock
/
phi-1_5-GGUF

Text Generation
GGUF
English
nlp
code
TensorBlock
GGUF
Inference Endpoints
Model card Files Community
phi-1_5-GGUF / README.md
morriszms's picture
morriszms
Update README.md
3de2d2a verified
preview code
|
raw
history blame contribute delete
4.35 kB
metadata
license: mit
license_link: https://huggingface.co/microsoft/phi-1_5/resolve/main/LICENSE
language:
  - en
pipeline_tag: text-generation
tags:
  - nlp
  - code
  - TensorBlock
  - GGUF
base_model: microsoft/phi-1_5
TensorBlock

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

microsoft/phi-1_5 - GGUF

This repo contains GGUF format model files for microsoft/phi-1_5.

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-1_5-Q2_K.gguf Q2_K 0.542 GB smallest, significant quality loss - not recommended for most purposes
phi-1_5-Q3_K_S.gguf Q3_K_S 0.609 GB very small, high quality loss
phi-1_5-Q3_K_M.gguf Q3_K_M 0.687 GB very small, high quality loss
phi-1_5-Q3_K_L.gguf Q3_K_L 0.754 GB small, substantial quality loss
phi-1_5-Q4_0.gguf Q4_0 0.772 GB legacy; small, very high quality loss - prefer using Q3_K_M
phi-1_5-Q4_K_S.gguf Q4_K_S 0.780 GB small, greater quality loss
phi-1_5-Q4_K_M.gguf Q4_K_M 0.832 GB medium, balanced quality - recommended
phi-1_5-Q5_0.gguf Q5_0 0.925 GB legacy; medium, balanced quality - prefer using Q4_K_M
phi-1_5-Q5_K_S.gguf Q5_K_S 0.925 GB large, low quality loss - recommended
phi-1_5-Q5_K_M.gguf Q5_K_M 0.956 GB large, very low quality loss - recommended
phi-1_5-Q6_K.gguf Q6_K 1.087 GB very large, extremely low quality loss
phi-1_5-Q8_0.gguf Q8_0 1.407 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-1_5-GGUF --include "phi-1_5-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-1_5-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'