TensorBlock

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

aisingapore/gemma2-9b-cpt-sea-lionv3-instruct - GGUF

This repo contains GGUF format model files for aisingapore/gemma2-9b-cpt-sea-lionv3-instruct.

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>system
{system_prompt}<end_of_turn>
<start_of_turn>user
{prompt}<end_of_turn>
<start_of_turn>model

Model file specification

Filename Quant type File Size Description
gemma2-9b-cpt-sea-lionv3-instruct-Q2_K.gguf Q2_K 3.805 GB smallest, significant quality loss - not recommended for most purposes
gemma2-9b-cpt-sea-lionv3-instruct-Q3_K_S.gguf Q3_K_S 4.338 GB very small, high quality loss
gemma2-9b-cpt-sea-lionv3-instruct-Q3_K_M.gguf Q3_K_M 4.762 GB very small, high quality loss
gemma2-9b-cpt-sea-lionv3-instruct-Q3_K_L.gguf Q3_K_L 5.132 GB small, substantial quality loss
gemma2-9b-cpt-sea-lionv3-instruct-Q4_0.gguf Q4_0 5.443 GB legacy; small, very high quality loss - prefer using Q3_K_M
gemma2-9b-cpt-sea-lionv3-instruct-Q4_K_S.gguf Q4_K_S 5.479 GB small, greater quality loss
gemma2-9b-cpt-sea-lionv3-instruct-Q4_K_M.gguf Q4_K_M 5.761 GB medium, balanced quality - recommended
gemma2-9b-cpt-sea-lionv3-instruct-Q5_0.gguf Q5_0 6.484 GB legacy; medium, balanced quality - prefer using Q4_K_M
gemma2-9b-cpt-sea-lionv3-instruct-Q5_K_S.gguf Q5_K_S 6.484 GB large, low quality loss - recommended
gemma2-9b-cpt-sea-lionv3-instruct-Q5_K_M.gguf Q5_K_M 6.647 GB large, very low quality loss - recommended
gemma2-9b-cpt-sea-lionv3-instruct-Q6_K.gguf Q6_K 7.589 GB very large, extremely low quality loss
gemma2-9b-cpt-sea-lionv3-instruct-Q8_0.gguf Q8_0 9.827 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/gemma2-9b-cpt-sea-lionv3-instruct-GGUF --include "gemma2-9b-cpt-sea-lionv3-instruct-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/gemma2-9b-cpt-sea-lionv3-instruct-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
Downloads last month
272
GGUF
Model size
9.24B params
Architecture
gemma2

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/gemma2-9b-cpt-sea-lionv3-instruct-GGUF