---
license: apache-2.0
tags:
- merge
- mergekit
- lazymergekit
- argilla/distilabeled-Marcoro14-7B-slerp
- mlabonne/NeuralMarcoro14-7B
- TensorBlock
- GGUF
datasets:
- mlabonne/chatml_dpo_pairs
- argilla/distilabel-intel-orca-dpo-pairs
base_model: flemmingmiguel/NeuDist-Ro-7B
---
[](https://tensorblock.co)
[](https://twitter.com/tensorblock_aoi)
[](https://discord.gg/Ej5NmeHFf2)
[](https://github.com/TensorBlock)
[](https://t.me/TensorBlock)
## flemmingmiguel/NeuDist-Ro-7B - GGUF
This repo contains GGUF format model files for [flemmingmiguel/NeuDist-Ro-7B](https://huggingface.co/flemmingmiguel/NeuDist-Ro-7B).
The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4242](https://github.com/ggerganov/llama.cpp/commit/a6744e43e80f4be6398fc7733a01642c846dce1d).
## Our projects
## 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 |
| -------- | ---------- | --------- | ----------- |
| [NeuDist-Ro-7B-Q2_K.gguf](https://huggingface.co/tensorblock/NeuDist-Ro-7B-GGUF/blob/main/NeuDist-Ro-7B-Q2_K.gguf) | Q2_K | 2.719 GB | smallest, significant quality loss - not recommended for most purposes |
| [NeuDist-Ro-7B-Q3_K_S.gguf](https://huggingface.co/tensorblock/NeuDist-Ro-7B-GGUF/blob/main/NeuDist-Ro-7B-Q3_K_S.gguf) | Q3_K_S | 3.165 GB | very small, high quality loss |
| [NeuDist-Ro-7B-Q3_K_M.gguf](https://huggingface.co/tensorblock/NeuDist-Ro-7B-GGUF/blob/main/NeuDist-Ro-7B-Q3_K_M.gguf) | Q3_K_M | 3.519 GB | very small, high quality loss |
| [NeuDist-Ro-7B-Q3_K_L.gguf](https://huggingface.co/tensorblock/NeuDist-Ro-7B-GGUF/blob/main/NeuDist-Ro-7B-Q3_K_L.gguf) | Q3_K_L | 3.822 GB | small, substantial quality loss |
| [NeuDist-Ro-7B-Q4_0.gguf](https://huggingface.co/tensorblock/NeuDist-Ro-7B-GGUF/blob/main/NeuDist-Ro-7B-Q4_0.gguf) | Q4_0 | 4.109 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [NeuDist-Ro-7B-Q4_K_S.gguf](https://huggingface.co/tensorblock/NeuDist-Ro-7B-GGUF/blob/main/NeuDist-Ro-7B-Q4_K_S.gguf) | Q4_K_S | 4.140 GB | small, greater quality loss |
| [NeuDist-Ro-7B-Q4_K_M.gguf](https://huggingface.co/tensorblock/NeuDist-Ro-7B-GGUF/blob/main/NeuDist-Ro-7B-Q4_K_M.gguf) | Q4_K_M | 4.368 GB | medium, balanced quality - recommended |
| [NeuDist-Ro-7B-Q5_0.gguf](https://huggingface.co/tensorblock/NeuDist-Ro-7B-GGUF/blob/main/NeuDist-Ro-7B-Q5_0.gguf) | Q5_0 | 4.998 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [NeuDist-Ro-7B-Q5_K_S.gguf](https://huggingface.co/tensorblock/NeuDist-Ro-7B-GGUF/blob/main/NeuDist-Ro-7B-Q5_K_S.gguf) | Q5_K_S | 4.998 GB | large, low quality loss - recommended |
| [NeuDist-Ro-7B-Q5_K_M.gguf](https://huggingface.co/tensorblock/NeuDist-Ro-7B-GGUF/blob/main/NeuDist-Ro-7B-Q5_K_M.gguf) | Q5_K_M | 5.131 GB | large, very low quality loss - recommended |
| [NeuDist-Ro-7B-Q6_K.gguf](https://huggingface.co/tensorblock/NeuDist-Ro-7B-GGUF/blob/main/NeuDist-Ro-7B-Q6_K.gguf) | Q6_K | 5.942 GB | very large, extremely low quality loss |
| [NeuDist-Ro-7B-Q8_0.gguf](https://huggingface.co/tensorblock/NeuDist-Ro-7B-GGUF/blob/main/NeuDist-Ro-7B-Q8_0.gguf) | Q8_0 | 7.696 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/NeuDist-Ro-7B-GGUF --include "NeuDist-Ro-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:
```shell
huggingface-cli download tensorblock/NeuDist-Ro-7B-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
```
