TensorBlock

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

cpm-ai/gemma-ko-v01 - GGUF

This repo contains GGUF format model files for cpm-ai/gemma-ko-v01.

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-ko-v01-Q2_K.gguf Q2_K 1.078 GB smallest, significant quality loss - not recommended for most purposes
gemma-ko-v01-Q3_K_S.gguf Q3_K_S 1.200 GB very small, high quality loss
gemma-ko-v01-Q3_K_M.gguf Q3_K_M 1.289 GB very small, high quality loss
gemma-ko-v01-Q3_K_L.gguf Q3_K_L 1.365 GB small, substantial quality loss
gemma-ko-v01-Q4_0.gguf Q4_0 1.445 GB legacy; small, very high quality loss - prefer using Q3_K_M
gemma-ko-v01-Q4_K_S.gguf Q4_K_S 1.453 GB small, greater quality loss
gemma-ko-v01-Q4_K_M.gguf Q4_K_M 1.518 GB medium, balanced quality - recommended
gemma-ko-v01-Q5_0.gguf Q5_0 1.675 GB legacy; medium, balanced quality - prefer using Q4_K_M
gemma-ko-v01-Q5_K_S.gguf Q5_K_S 1.675 GB large, low quality loss - recommended
gemma-ko-v01-Q5_K_M.gguf Q5_K_M 1.713 GB large, very low quality loss - recommended
gemma-ko-v01-Q6_K.gguf Q6_K 1.921 GB very large, extremely low quality loss
gemma-ko-v01-Q8_0.gguf Q8_0 2.486 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-ko-v01-GGUF --include "gemma-ko-v01-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-ko-v01-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
Downloads last month
43
GGUF
Model size
2.51B params
Architecture
gemma

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for tensorblock/gemma-ko-v01-GGUF

Quantized
(1)
this model