Hugging Face's logo

tensorblock
/
KoSOLAR-10.9B-v0.3-GGUF

GGUF
Korean
mergekit
Merge
LDCC/LDCC-SOLAR-10.7B
hyeogi/SOLAR-10.7B-dpo-v1
TensorBlock
GGUF
Inference Endpoints
Model card Files Community
KoSOLAR-10.9B-v0.3-GGUF / README.md
morriszms's picture
morriszms
Update README.md
9447759 verified
preview code
|
raw
history blame contribute delete
4.77 kB
metadata
language:
  - ko
base_model: rrw-x2/KoSOLAR-10.9B-v0.3
tags:
  - mergekit
  - merge
  - LDCC/LDCC-SOLAR-10.7B
  - hyeogi/SOLAR-10.7B-dpo-v1
  - TensorBlock
  - GGUF
license: apache-2.0
TensorBlock

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

rrw-x2/KoSOLAR-10.9B-v0.3 - GGUF

This repo contains GGUF format model files for rrw-x2/KoSOLAR-10.9B-v0.3.

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
KoSOLAR-10.9B-v0.3-Q2_K.gguf Q2_K 3.799 GB smallest, significant quality loss - not recommended for most purposes
KoSOLAR-10.9B-v0.3-Q3_K_S.gguf Q3_K_S 4.421 GB very small, high quality loss
KoSOLAR-10.9B-v0.3-Q3_K_M.gguf Q3_K_M 4.916 GB very small, high quality loss
KoSOLAR-10.9B-v0.3-Q3_K_L.gguf Q3_K_L 5.339 GB small, substantial quality loss
KoSOLAR-10.9B-v0.3-Q4_0.gguf Q4_0 5.740 GB legacy; small, very high quality loss - prefer using Q3_K_M
KoSOLAR-10.9B-v0.3-Q4_K_S.gguf Q4_K_S 5.783 GB small, greater quality loss
KoSOLAR-10.9B-v0.3-Q4_K_M.gguf Q4_K_M 6.103 GB medium, balanced quality - recommended
KoSOLAR-10.9B-v0.3-Q5_0.gguf Q5_0 6.982 GB legacy; medium, balanced quality - prefer using Q4_K_M
KoSOLAR-10.9B-v0.3-Q5_K_S.gguf Q5_K_S 6.982 GB large, low quality loss - recommended
KoSOLAR-10.9B-v0.3-Q5_K_M.gguf Q5_K_M 7.169 GB large, very low quality loss - recommended
KoSOLAR-10.9B-v0.3-Q6_K.gguf Q6_K 8.301 GB very large, extremely low quality loss
KoSOLAR-10.9B-v0.3-Q8_0.gguf Q8_0 10.751 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/KoSOLAR-10.9B-v0.3-GGUF --include "KoSOLAR-10.9B-v0.3-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/KoSOLAR-10.9B-v0.3-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'