---
license: cc-by-nc-sa-4.0
datasets:
- Cartinoe5930/KoRAE_filtered_12k
language:
- ko
library_name: transformers
base_model: Cartinoe5930/weak-KoRAE-13b
tags:
- TensorBlock
- GGUF
---
## Cartinoe5930/weak-KoRAE-13b - GGUF
This repo contains GGUF format model files for [Cartinoe5930/weak-KoRAE-13b](https://huggingface.co/Cartinoe5930/weak-KoRAE-13b).
The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4011](https://github.com/ggerganov/llama.cpp/commit/a6744e43e80f4be6398fc7733a01642c846dce1d).
## Prompt template
```
### System:
{system_prompt}
### User:
{prompt}
### Assistant:
```
## Model file specification
| Filename | Quant type | File Size | Description |
| -------- | ---------- | --------- | ----------- |
| [weak-KoRAE-13b-Q2_K.gguf](https://huggingface.co/tensorblock/weak-KoRAE-13b-GGUF/blob/main/weak-KoRAE-13b-Q2_K.gguf) | Q2_K | 4.600 GB | smallest, significant quality loss - not recommended for most purposes |
| [weak-KoRAE-13b-Q3_K_S.gguf](https://huggingface.co/tensorblock/weak-KoRAE-13b-GGUF/blob/main/weak-KoRAE-13b-Q3_K_S.gguf) | Q3_K_S | 5.356 GB | very small, high quality loss |
| [weak-KoRAE-13b-Q3_K_M.gguf](https://huggingface.co/tensorblock/weak-KoRAE-13b-GGUF/blob/main/weak-KoRAE-13b-Q3_K_M.gguf) | Q3_K_M | 5.988 GB | very small, high quality loss |
| [weak-KoRAE-13b-Q3_K_L.gguf](https://huggingface.co/tensorblock/weak-KoRAE-13b-GGUF/blob/main/weak-KoRAE-13b-Q3_K_L.gguf) | Q3_K_L | 6.539 GB | small, substantial quality loss |
| [weak-KoRAE-13b-Q4_0.gguf](https://huggingface.co/tensorblock/weak-KoRAE-13b-GGUF/blob/main/weak-KoRAE-13b-Q4_0.gguf) | Q4_0 | 6.955 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [weak-KoRAE-13b-Q4_K_S.gguf](https://huggingface.co/tensorblock/weak-KoRAE-13b-GGUF/blob/main/weak-KoRAE-13b-Q4_K_S.gguf) | Q4_K_S | 7.008 GB | small, greater quality loss |
| [weak-KoRAE-13b-Q4_K_M.gguf](https://huggingface.co/tensorblock/weak-KoRAE-13b-GGUF/blob/main/weak-KoRAE-13b-Q4_K_M.gguf) | Q4_K_M | 7.421 GB | medium, balanced quality - recommended |
| [weak-KoRAE-13b-Q5_0.gguf](https://huggingface.co/tensorblock/weak-KoRAE-13b-GGUF/blob/main/weak-KoRAE-13b-Q5_0.gguf) | Q5_0 | 8.459 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [weak-KoRAE-13b-Q5_K_S.gguf](https://huggingface.co/tensorblock/weak-KoRAE-13b-GGUF/blob/main/weak-KoRAE-13b-Q5_K_S.gguf) | Q5_K_S | 8.459 GB | large, low quality loss - recommended |
| [weak-KoRAE-13b-Q5_K_M.gguf](https://huggingface.co/tensorblock/weak-KoRAE-13b-GGUF/blob/main/weak-KoRAE-13b-Q5_K_M.gguf) | Q5_K_M | 8.699 GB | large, very low quality loss - recommended |
| [weak-KoRAE-13b-Q6_K.gguf](https://huggingface.co/tensorblock/weak-KoRAE-13b-GGUF/blob/main/weak-KoRAE-13b-Q6_K.gguf) | Q6_K | 10.058 GB | very large, extremely low quality loss |
| [weak-KoRAE-13b-Q8_0.gguf](https://huggingface.co/tensorblock/weak-KoRAE-13b-GGUF/blob/main/weak-KoRAE-13b-Q8_0.gguf) | Q8_0 | 13.027 GB | very large, extremely low quality loss - not recommended |
## Downloading instruction
### Command line
Firstly, install Huggingface Client
```shell
pip install -U "huggingface_hub[cli]"
```
Then, downoad the individual model file the a local directory
```shell
huggingface-cli download tensorblock/weak-KoRAE-13b-GGUF --include "weak-KoRAE-13b-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:
```shell
huggingface-cli download tensorblock/weak-KoRAE-13b-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
```