morriszms's picture
Upload folder using huggingface_hub
76a069a verified
metadata
base_model: BioMistral/BioMistral-7B-DARE
library_name: transformers
tags:
  - mergekit
  - merge
  - dare
  - medical
  - biology
  - TensorBlock
  - GGUF
license: apache-2.0
datasets:
  - pubmed
language:
  - en
  - fr
  - nl
  - es
  - it
  - pl
  - ro
  - de
pipeline_tag: text-generation
TensorBlock

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

BioMistral/BioMistral-7B-DARE - GGUF

This repo contains GGUF format model files for BioMistral/BioMistral-7B-DARE.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4242.

Prompt template

<s>[INST] {prompt} [/INST]

Model file specification

Filename Quant type File Size Description
BioMistral-7B-DARE-Q2_K.gguf Q2_K 2.719 GB smallest, significant quality loss - not recommended for most purposes
BioMistral-7B-DARE-Q3_K_S.gguf Q3_K_S 3.165 GB very small, high quality loss
BioMistral-7B-DARE-Q3_K_M.gguf Q3_K_M 3.519 GB very small, high quality loss
BioMistral-7B-DARE-Q3_K_L.gguf Q3_K_L 3.822 GB small, substantial quality loss
BioMistral-7B-DARE-Q4_0.gguf Q4_0 4.109 GB legacy; small, very high quality loss - prefer using Q3_K_M
BioMistral-7B-DARE-Q4_K_S.gguf Q4_K_S 4.140 GB small, greater quality loss
BioMistral-7B-DARE-Q4_K_M.gguf Q4_K_M 4.368 GB medium, balanced quality - recommended
BioMistral-7B-DARE-Q5_0.gguf Q5_0 4.998 GB legacy; medium, balanced quality - prefer using Q4_K_M
BioMistral-7B-DARE-Q5_K_S.gguf Q5_K_S 4.998 GB large, low quality loss - recommended
BioMistral-7B-DARE-Q5_K_M.gguf Q5_K_M 5.131 GB large, very low quality loss - recommended
BioMistral-7B-DARE-Q6_K.gguf Q6_K 5.942 GB very large, extremely low quality loss
BioMistral-7B-DARE-Q8_0.gguf Q8_0 7.696 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/BioMistral-7B-DARE-GGUF --include "BioMistral-7B-DARE-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/BioMistral-7B-DARE-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'