metadata
language:
- en
- ko
license: cc-by-nc-4.0
datasets:
- kyujinpy/KOR-gugugu-platypus-set
base_model: oneonlee/KoSOLAR-v0.2-gugutypus-10.7B
pipeline_tag: text-generation
tags:
- TensorBlock
- GGUF
Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server
oneonlee/KoSOLAR-v0.2-gugutypus-10.7B - GGUF
This repo contains GGUF format model files for oneonlee/KoSOLAR-v0.2-gugutypus-10.7B.
The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4011.
Our projects
| Awesome MCP Servers | TensorBlock Studio |
|---|---|
 |
 |
| A comprehensive collection of Model Context Protocol (MCP) servers. | A lightweight, open, and extensible multi-LLM interaction studio. |
| 👀 See what we built 👀 | 👀 See what we built 👀 |
Model file specification
| Filename | Quant type | File Size | Description |
|---|---|---|---|
| KoSOLAR-v0.2-gugutypus-10.7B-Q2_K.gguf | Q2_K | 3.768 GB | smallest, significant quality loss - not recommended for most purposes |
| KoSOLAR-v0.2-gugutypus-10.7B-Q3_K_S.gguf | Q3_K_S | 4.387 GB | very small, high quality loss |
| KoSOLAR-v0.2-gugutypus-10.7B-Q3_K_M.gguf | Q3_K_M | 4.882 GB | very small, high quality loss |
| KoSOLAR-v0.2-gugutypus-10.7B-Q3_K_L.gguf | Q3_K_L | 5.306 GB | small, substantial quality loss |
| KoSOLAR-v0.2-gugutypus-10.7B-Q4_0.gguf | Q4_0 | 5.703 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| KoSOLAR-v0.2-gugutypus-10.7B-Q4_K_S.gguf | Q4_K_S | 5.746 GB | small, greater quality loss |
| KoSOLAR-v0.2-gugutypus-10.7B-Q4_K_M.gguf | Q4_K_M | 6.065 GB | medium, balanced quality - recommended |
| KoSOLAR-v0.2-gugutypus-10.7B-Q5_0.gguf | Q5_0 | 6.941 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| KoSOLAR-v0.2-gugutypus-10.7B-Q5_K_S.gguf | Q5_K_S | 6.941 GB | large, low quality loss - recommended |
| KoSOLAR-v0.2-gugutypus-10.7B-Q5_K_M.gguf | Q5_K_M | 7.128 GB | large, very low quality loss - recommended |
| KoSOLAR-v0.2-gugutypus-10.7B-Q6_K.gguf | Q6_K | 8.257 GB | very large, extremely low quality loss |
| KoSOLAR-v0.2-gugutypus-10.7B-Q8_0.gguf | Q8_0 | 10.694 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-v0.2-gugutypus-10.7B-GGUF --include "KoSOLAR-v0.2-gugutypus-10.7B-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/KoSOLAR-v0.2-gugutypus-10.7B-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'