README.md

---
language:
- en
- vi
license: other
license_name: ghost-7b
license_link: https://ghost-x.org/ghost-7b-license
library_name: transformers
tags:
- ghost
- tools
- chat
- TensorBlock
- GGUF
pipeline_tag: text-generation
widget:
- text: Why is the sky blue ?
  output:
    text: The sky appears blue because of a phenomenon called Rayleigh scattering.
      Sunlight is composed of all colors of the visible spectrum, but blue light has
      a shorter wavelength than other colors. When sunlight enters the Earth's atmosphere,
      it interacts with molecules of nitrogen and oxygen, which are the main components
      of our atmosphere. These molecules scatter the shorter wavelengths of light,
      such as blue and violet, more than the longer wavelengths, such as red and orange.
      As a result, when we look up at the sky, we see more blue light than other colors
      because the blue light has been scattered more by the molecules in the atmosphere.
base_model: ghost-x/ghost-7b-alpha
---

<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
    <div style="display: flex; flex-direction: column; align-items: flex-start;">
        <p style="margin-top: 0.5em; margin-bottom: 0em;">
            Feedback and support: TensorBlock's  <a href="https://x.com/tensorblock_aoi">Twitter/X</a>, <a href="https://t.me/TensorBlock">Telegram Group</a> and <a href="https://x.com/tensorblock_aoi">Discord server</a>
        </p>
    </div>
</div>

## ghost-x/ghost-7b-alpha - GGUF

This repo contains GGUF format model files for [ghost-x/ghost-7b-alpha](https://huggingface.co/ghost-x/ghost-7b-alpha).

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}</s>
<|user|>
{prompt}</s>
<|assistant|>
```

## Model file specification

| Filename | Quant type | File Size | Description |
| -------- | ---------- | --------- | ----------- |
| [ghost-7b-alpha-Q2_K.gguf](https://huggingface.co/tensorblock/ghost-7b-alpha-GGUF/tree/main/ghost-7b-alpha-Q2_K.gguf) | Q2_K | 2.532 GB | smallest, significant quality loss - not recommended for most purposes |
| [ghost-7b-alpha-Q3_K_S.gguf](https://huggingface.co/tensorblock/ghost-7b-alpha-GGUF/tree/main/ghost-7b-alpha-Q3_K_S.gguf) | Q3_K_S | 2.947 GB | very small, high quality loss |
| [ghost-7b-alpha-Q3_K_M.gguf](https://huggingface.co/tensorblock/ghost-7b-alpha-GGUF/tree/main/ghost-7b-alpha-Q3_K_M.gguf) | Q3_K_M | 3.277 GB | very small, high quality loss |
| [ghost-7b-alpha-Q3_K_L.gguf](https://huggingface.co/tensorblock/ghost-7b-alpha-GGUF/tree/main/ghost-7b-alpha-Q3_K_L.gguf) | Q3_K_L | 3.560 GB | small, substantial quality loss |
| [ghost-7b-alpha-Q4_0.gguf](https://huggingface.co/tensorblock/ghost-7b-alpha-GGUF/tree/main/ghost-7b-alpha-Q4_0.gguf) | Q4_0 | 3.827 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [ghost-7b-alpha-Q4_K_S.gguf](https://huggingface.co/tensorblock/ghost-7b-alpha-GGUF/tree/main/ghost-7b-alpha-Q4_K_S.gguf) | Q4_K_S | 3.856 GB | small, greater quality loss |
| [ghost-7b-alpha-Q4_K_M.gguf](https://huggingface.co/tensorblock/ghost-7b-alpha-GGUF/tree/main/ghost-7b-alpha-Q4_K_M.gguf) | Q4_K_M | 4.068 GB | medium, balanced quality - recommended |
| [ghost-7b-alpha-Q5_0.gguf](https://huggingface.co/tensorblock/ghost-7b-alpha-GGUF/tree/main/ghost-7b-alpha-Q5_0.gguf) | Q5_0 | 4.654 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [ghost-7b-alpha-Q5_K_S.gguf](https://huggingface.co/tensorblock/ghost-7b-alpha-GGUF/tree/main/ghost-7b-alpha-Q5_K_S.gguf) | Q5_K_S | 4.654 GB | large, low quality loss - recommended |
| [ghost-7b-alpha-Q5_K_M.gguf](https://huggingface.co/tensorblock/ghost-7b-alpha-GGUF/tree/main/ghost-7b-alpha-Q5_K_M.gguf) | Q5_K_M | 4.779 GB | large, very low quality loss - recommended |
| [ghost-7b-alpha-Q6_K.gguf](https://huggingface.co/tensorblock/ghost-7b-alpha-GGUF/tree/main/ghost-7b-alpha-Q6_K.gguf) | Q6_K | 5.534 GB | very large, extremely low quality loss |
| [ghost-7b-alpha-Q8_0.gguf](https://huggingface.co/tensorblock/ghost-7b-alpha-GGUF/tree/main/ghost-7b-alpha-Q8_0.gguf) | Q8_0 | 7.167 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/ghost-7b-alpha-GGUF --include "ghost-7b-alpha-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/ghost-7b-alpha-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
```