---
language:
- nl
license: mit
tags:
- trl
- fietje
- alignment-handbook
- sft
- TensorBlock
- GGUF
base_model: BramVanroy/fietje-2-instruct
datasets:
- BramVanroy/ultrachat_200k_dutch
- BramVanroy/no_robots_dutch
- BramVanroy/belebele_dutch
pipeline_tag: text-generation
inference: false
model-index:
- name: fietje-2-instruct
results: []
---
## BramVanroy/fietje-2-instruct - GGUF
This repo contains GGUF format model files for [BramVanroy/fietje-2-instruct](https://huggingface.co/BramVanroy/fietje-2-instruct).
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
```
<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
```
## Model file specification
| Filename | Quant type | File Size | Description |
| -------- | ---------- | --------- | ----------- |
| [fietje-2-instruct-Q2_K.gguf](https://huggingface.co/tensorblock/fietje-2-instruct-GGUF/blob/main/fietje-2-instruct-Q2_K.gguf) | Q2_K | 1.107 GB | smallest, significant quality loss - not recommended for most purposes |
| [fietje-2-instruct-Q3_K_S.gguf](https://huggingface.co/tensorblock/fietje-2-instruct-GGUF/blob/main/fietje-2-instruct-Q3_K_S.gguf) | Q3_K_S | 1.248 GB | very small, high quality loss |
| [fietje-2-instruct-Q3_K_M.gguf](https://huggingface.co/tensorblock/fietje-2-instruct-GGUF/blob/main/fietje-2-instruct-Q3_K_M.gguf) | Q3_K_M | 1.423 GB | very small, high quality loss |
| [fietje-2-instruct-Q3_K_L.gguf](https://huggingface.co/tensorblock/fietje-2-instruct-GGUF/blob/main/fietje-2-instruct-Q3_K_L.gguf) | Q3_K_L | 1.572 GB | small, substantial quality loss |
| [fietje-2-instruct-Q4_0.gguf](https://huggingface.co/tensorblock/fietje-2-instruct-GGUF/blob/main/fietje-2-instruct-Q4_0.gguf) | Q4_0 | 1.599 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [fietje-2-instruct-Q4_K_S.gguf](https://huggingface.co/tensorblock/fietje-2-instruct-GGUF/blob/main/fietje-2-instruct-Q4_K_S.gguf) | Q4_K_S | 1.616 GB | small, greater quality loss |
| [fietje-2-instruct-Q4_K_M.gguf](https://huggingface.co/tensorblock/fietje-2-instruct-GGUF/blob/main/fietje-2-instruct-Q4_K_M.gguf) | Q4_K_M | 1.734 GB | medium, balanced quality - recommended |
| [fietje-2-instruct-Q5_0.gguf](https://huggingface.co/tensorblock/fietje-2-instruct-GGUF/blob/main/fietje-2-instruct-Q5_0.gguf) | Q5_0 | 1.930 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [fietje-2-instruct-Q5_K_S.gguf](https://huggingface.co/tensorblock/fietje-2-instruct-GGUF/blob/main/fietje-2-instruct-Q5_K_S.gguf) | Q5_K_S | 1.930 GB | large, low quality loss - recommended |
| [fietje-2-instruct-Q5_K_M.gguf](https://huggingface.co/tensorblock/fietje-2-instruct-GGUF/blob/main/fietje-2-instruct-Q5_K_M.gguf) | Q5_K_M | 2.000 GB | large, very low quality loss - recommended |
| [fietje-2-instruct-Q6_K.gguf](https://huggingface.co/tensorblock/fietje-2-instruct-GGUF/blob/main/fietje-2-instruct-Q6_K.gguf) | Q6_K | 2.281 GB | very large, extremely low quality loss |
| [fietje-2-instruct-Q8_0.gguf](https://huggingface.co/tensorblock/fietje-2-instruct-GGUF/blob/main/fietje-2-instruct-Q8_0.gguf) | Q8_0 | 2.953 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/fietje-2-instruct-GGUF --include "fietje-2-instruct-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/fietje-2-instruct-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
```