morriszms's picture
Update README.md
7cdb9ba verified
|
raw
history blame
4.7 kB
metadata
license: apache-2.0
language:
  - en
  - he
library_name: transformers
base_model: yam-peleg/Hebrew-Mistral-7B
tags:
  - TensorBlock
  - GGUF
TensorBlock

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

yam-peleg/Hebrew-Mistral-7B - GGUF

This repo contains GGUF format model files for yam-peleg/Hebrew-Mistral-7B.

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
Hebrew-Mistral-7B-Q2_K.gguf Q2_K 2.673 GB smallest, significant quality loss - not recommended for most purposes
Hebrew-Mistral-7B-Q3_K_S.gguf Q3_K_S 3.101 GB very small, high quality loss
Hebrew-Mistral-7B-Q3_K_M.gguf Q3_K_M 3.431 GB very small, high quality loss
Hebrew-Mistral-7B-Q3_K_L.gguf Q3_K_L 3.713 GB small, substantial quality loss
Hebrew-Mistral-7B-Q4_0.gguf Q4_0 3.996 GB legacy; small, very high quality loss - prefer using Q3_K_M
Hebrew-Mistral-7B-Q4_K_S.gguf Q4_K_S 4.026 GB small, greater quality loss
Hebrew-Mistral-7B-Q4_K_M.gguf Q4_K_M 4.238 GB medium, balanced quality - recommended
Hebrew-Mistral-7B-Q5_0.gguf Q5_0 4.839 GB legacy; medium, balanced quality - prefer using Q4_K_M
Hebrew-Mistral-7B-Q5_K_S.gguf Q5_K_S 4.839 GB large, low quality loss - recommended
Hebrew-Mistral-7B-Q5_K_M.gguf Q5_K_M 4.964 GB large, very low quality loss - recommended
Hebrew-Mistral-7B-Q6_K.gguf Q6_K 5.735 GB very large, extremely low quality loss
Hebrew-Mistral-7B-Q8_0.gguf Q8_0 7.427 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/Hebrew-Mistral-7B-GGUF --include "Hebrew-Mistral-7B-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/Hebrew-Mistral-7B-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'