Hugging Face's logo

tensorblock
/
gemma-7b-it-GGUF

Transformers
GGUF
English
unsloth
gemma
gemma-7b
TensorBlock
GGUF
Inference Endpoints
conversational
Model card Files Community
gemma-7b-it-GGUF / README.md
morriszms's picture
morriszms
Update README.md
20d37bb verified
preview code
|
raw
history blame contribute delete
4.54 kB
metadata
language:
  - en
library_name: transformers
license: apache-2.0
tags:
  - unsloth
  - transformers
  - gemma
  - gemma-7b
  - TensorBlock
  - GGUF
base_model: unsloth/gemma-7b-it
TensorBlock

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

unsloth/gemma-7b-it - GGUF

This repo contains GGUF format model files for unsloth/gemma-7b-it.

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

Prompt template 

<bos><start_of_turn>user
{prompt}<end_of_turn>
<start_of_turn>model

Model file specification

Filename Quant type File Size Description
gemma-7b-it-Q2_K.gguf Q2_K 3.242 GB smallest, significant quality loss - not recommended for most purposes
gemma-7b-it-Q3_K_S.gguf Q3_K_S 3.709 GB very small, high quality loss
gemma-7b-it-Q3_K_M.gguf Q3_K_M 4.069 GB very small, high quality loss
gemma-7b-it-Q3_K_L.gguf Q3_K_L 4.386 GB small, substantial quality loss
gemma-7b-it-Q4_0.gguf Q4_0 4.668 GB legacy; small, very high quality loss - prefer using Q3_K_M
gemma-7b-it-Q4_K_S.gguf Q4_K_S 4.700 GB small, greater quality loss
gemma-7b-it-Q4_K_M.gguf Q4_K_M 4.964 GB medium, balanced quality - recommended
gemma-7b-it-Q5_0.gguf Q5_0 5.570 GB legacy; medium, balanced quality - prefer using Q4_K_M
gemma-7b-it-Q5_K_S.gguf Q5_K_S 5.570 GB large, low quality loss - recommended
gemma-7b-it-Q5_K_M.gguf Q5_K_M 5.723 GB large, very low quality loss - recommended
gemma-7b-it-Q6_K.gguf Q6_K 6.529 GB very large, extremely low quality loss
gemma-7b-it-Q8_0.gguf Q8_0 8.454 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/gemma-7b-it-GGUF --include "gemma-7b-it-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/gemma-7b-it-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'