Edit model card
TensorBlock

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

refarde/OPEN-SOLAR-KO-10.7B-S-Core - GGUF

This repo contains GGUF format model files for refarde/OPEN-SOLAR-KO-10.7B-S-Core.

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
OPEN-SOLAR-KO-10.7B-S-Core-Q2_K.gguf Q2_K 3.793 GB smallest, significant quality loss - not recommended for most purposes
OPEN-SOLAR-KO-10.7B-S-Core-Q3_K_S.gguf Q3_K_S 4.414 GB very small, high quality loss
OPEN-SOLAR-KO-10.7B-S-Core-Q3_K_M.gguf Q3_K_M 4.909 GB very small, high quality loss
OPEN-SOLAR-KO-10.7B-S-Core-Q3_K_L.gguf Q3_K_L 5.333 GB small, substantial quality loss
OPEN-SOLAR-KO-10.7B-S-Core-Q4_0.gguf Q4_0 5.733 GB legacy; small, very high quality loss - prefer using Q3_K_M
OPEN-SOLAR-KO-10.7B-S-Core-Q4_K_S.gguf Q4_K_S 5.776 GB small, greater quality loss
OPEN-SOLAR-KO-10.7B-S-Core-Q4_K_M.gguf Q4_K_M 6.095 GB medium, balanced quality - recommended
OPEN-SOLAR-KO-10.7B-S-Core-Q5_0.gguf Q5_0 6.974 GB legacy; medium, balanced quality - prefer using Q4_K_M
OPEN-SOLAR-KO-10.7B-S-Core-Q5_K_S.gguf Q5_K_S 6.974 GB large, low quality loss - recommended
OPEN-SOLAR-KO-10.7B-S-Core-Q5_K_M.gguf Q5_K_M 7.160 GB large, very low quality loss - recommended
OPEN-SOLAR-KO-10.7B-S-Core-Q6_K.gguf Q6_K 8.292 GB very large, extremely low quality loss
OPEN-SOLAR-KO-10.7B-S-Core-Q8_0.gguf Q8_0 10.740 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/OPEN-SOLAR-KO-10.7B-S-Core-GGUF --include "OPEN-SOLAR-KO-10.7B-S-Core-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/OPEN-SOLAR-KO-10.7B-S-Core-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
Downloads last month
177
GGUF
Model size
10.9B 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/OPEN-SOLAR-KO-10.7B-S-Core-GGUF

Quantized
(2)
this model

Dataset used to train tensorblock/OPEN-SOLAR-KO-10.7B-S-Core-GGUF