TensorBlock

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

beomi/llama-2-ko-7b - GGUF

This repo contains GGUF format model files for beomi/llama-2-ko-7b.

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

Prompt template


Model file specification

Filename Quant type File Size Description
llama-2-ko-7b-Q2_K.gguf Q2_K 2.422 GB smallest, significant quality loss - not recommended for most purposes
llama-2-ko-7b-Q3_K_S.gguf Q3_K_S 2.815 GB very small, high quality loss
llama-2-ko-7b-Q3_K_M.gguf Q3_K_M 3.140 GB very small, high quality loss
llama-2-ko-7b-Q3_K_L.gguf Q3_K_L 3.419 GB small, substantial quality loss
llama-2-ko-7b-Q4_0.gguf Q4_0 3.639 GB legacy; small, very high quality loss - prefer using Q3_K_M
llama-2-ko-7b-Q4_K_S.gguf Q4_K_S 3.668 GB small, greater quality loss
llama-2-ko-7b-Q4_K_M.gguf Q4_K_M 3.877 GB medium, balanced quality - recommended
llama-2-ko-7b-Q5_0.gguf Q5_0 4.415 GB legacy; medium, balanced quality - prefer using Q4_K_M
llama-2-ko-7b-Q5_K_S.gguf Q5_K_S 4.415 GB large, low quality loss - recommended
llama-2-ko-7b-Q5_K_M.gguf Q5_K_M 4.537 GB large, very low quality loss - recommended
llama-2-ko-7b-Q6_K.gguf Q6_K 5.240 GB very large, extremely low quality loss
llama-2-ko-7b-Q8_0.gguf Q8_0 6.786 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/llama-2-ko-7b-GGUF --include "llama-2-ko-7b-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/llama-2-ko-7b-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
Downloads last month
80
GGUF
Model size
6.86B params
Architecture
llama

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference Examples
Inference API (serverless) has been turned off for this model.

Model tree for tensorblock/llama-2-ko-7b-GGUF

Quantized
(3)
this model