Hugging Face's logo

tensorblock
/
llama2-13b.kor.v1-GGUF

Text Generation
GGUF
Korean
llama-2
instruct
instruction
TensorBlock
GGUF
Inference Endpoints
Model card Files Community
llama2-13b.kor.v1-GGUF / README.md
morriszms's picture
morriszms
Upload folder using huggingface_hub
66fa113 verified
preview code
|
raw
history blame contribute delete
4.39 kB
metadata
language:
  - ko
tags:
  - llama-2
  - instruct
  - instruction
  - TensorBlock
  - GGUF
pipeline_tag: text-generation
license: llama2
base_model: sanghwa-na/llama2-13b.kor.v1
TensorBlock

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

sanghwa-na/llama2-13b.kor.v1 - GGUF

This repo contains GGUF format model files for sanghwa-na/llama2-13b.kor.v1.

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
llama2-13b.kor.v1-Q2_K.gguf Q2_K 4.521 GB smallest, significant quality loss - not recommended for most purposes
llama2-13b.kor.v1-Q3_K_S.gguf Q3_K_S 5.270 GB very small, high quality loss
llama2-13b.kor.v1-Q3_K_M.gguf Q3_K_M 5.903 GB very small, high quality loss
llama2-13b.kor.v1-Q3_K_L.gguf Q3_K_L 6.454 GB small, substantial quality loss
llama2-13b.kor.v1-Q4_0.gguf Q4_0 6.860 GB legacy; small, very high quality loss - prefer using Q3_K_M
llama2-13b.kor.v1-Q4_K_S.gguf Q4_K_S 6.913 GB small, greater quality loss
llama2-13b.kor.v1-Q4_K_M.gguf Q4_K_M 7.326 GB medium, balanced quality - recommended
llama2-13b.kor.v1-Q5_0.gguf Q5_0 8.356 GB legacy; medium, balanced quality - prefer using Q4_K_M
llama2-13b.kor.v1-Q5_K_S.gguf Q5_K_S 8.356 GB large, low quality loss - recommended
llama2-13b.kor.v1-Q5_K_M.gguf Q5_K_M 8.596 GB large, very low quality loss - recommended
llama2-13b.kor.v1-Q6_K.gguf Q6_K 9.946 GB very large, extremely low quality loss
llama2-13b.kor.v1-Q8_0.gguf Q8_0 12.881 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/llama2-13b.kor.v1-GGUF --include "llama2-13b.kor.v1-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/llama2-13b.kor.v1-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'