Hugging Face's logo

tensorblock
/
gemma-2-baku-2b-it-GGUF

Text Generation
Transformers
GGUF
Japanese
English
gemma2
conversational
TensorBlock
GGUF
Inference Endpoints
Model card Files Community
gemma-2-baku-2b-it-GGUF / README.md
morriszms's picture
morriszms
Update README.md
3a60a0c verified
preview code
|
raw
history blame contribute delete
4.96 kB
metadata
thumbnail: https://github.com/rinnakk/japanese-pretrained-models/blob/master/rinna.png
license: gemma
language:
  - ja
  - en
tags:
  - gemma2
  - conversational
  - TensorBlock
  - GGUF
base_model: rinna/gemma-2-baku-2b-it
base_model_relation: merge
pipeline_tag: text-generation
library_name: transformers
TensorBlock

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

rinna/gemma-2-baku-2b-it - GGUF

This repo contains GGUF format model files for rinna/gemma-2-baku-2b-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-2-baku-2b-it-Q2_K.gguf Q2_K 1.145 GB smallest, significant quality loss - not recommended for most purposes
gemma-2-baku-2b-it-Q3_K_S.gguf Q3_K_S 1.267 GB very small, high quality loss
gemma-2-baku-2b-it-Q3_K_M.gguf Q3_K_M 1.361 GB very small, high quality loss
gemma-2-baku-2b-it-Q3_K_L.gguf Q3_K_L 1.444 GB small, substantial quality loss
gemma-2-baku-2b-it-Q4_0.gguf Q4_0 1.518 GB legacy; small, very high quality loss - prefer using Q3_K_M
gemma-2-baku-2b-it-Q4_K_S.gguf Q4_K_S 1.526 GB small, greater quality loss
gemma-2-baku-2b-it-Q4_K_M.gguf Q4_K_M 1.591 GB medium, balanced quality - recommended
gemma-2-baku-2b-it-Q5_0.gguf Q5_0 1.753 GB legacy; medium, balanced quality - prefer using Q4_K_M
gemma-2-baku-2b-it-Q5_K_S.gguf Q5_K_S 1.753 GB large, low quality loss - recommended
gemma-2-baku-2b-it-Q5_K_M.gguf Q5_K_M 1.791 GB large, very low quality loss - recommended
gemma-2-baku-2b-it-Q6_K.gguf Q6_K 2.004 GB very large, extremely low quality loss
gemma-2-baku-2b-it-Q8_0.gguf Q8_0 2.593 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-2-baku-2b-it-GGUF --include "gemma-2-baku-2b-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-2-baku-2b-it-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'