Update README.md
Browse files
README.md
CHANGED
|
@@ -15,10 +15,27 @@ quantized_by: Suparious
|
|
| 15 |
- Model creator: [MaziyarPanahi](https://huggingface.co/MaziyarPanahi)
|
| 16 |
- Original model: [Llama-3-8B-Instruct-DPO-v0.2](https://huggingface.co/MaziyarPanahi/Llama-3-8B-Instruct-DPO-v0.2)
|
| 17 |
|
|
|
|
| 18 |
|
|
|
|
|
|
|
|
|
|
| 19 |
|
| 20 |
## How to use
|
| 21 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 22 |
### Install the necessary packages
|
| 23 |
|
| 24 |
```bash
|
|
|
|
| 15 |
- Model creator: [MaziyarPanahi](https://huggingface.co/MaziyarPanahi)
|
| 16 |
- Original model: [Llama-3-8B-Instruct-DPO-v0.2](https://huggingface.co/MaziyarPanahi/Llama-3-8B-Instruct-DPO-v0.2)
|
| 17 |
|
| 18 |
+
<img src="./llama-3-merges.webp" alt="Goku 8x22B v0.1 Logo" width="500" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
|
| 19 |
|
| 20 |
+
## Model Summary
|
| 21 |
+
|
| 22 |
+
This model is a fine-tune (DPO) of `meta-llama/Meta-Llama-3-8B-Instruct` model.
|
| 23 |
|
| 24 |
## How to use
|
| 25 |
|
| 26 |
+
This model uses `ChatML` prompt template:
|
| 27 |
+
|
| 28 |
+
```
|
| 29 |
+
<|im_start|>system
|
| 30 |
+
{System}
|
| 31 |
+
<|im_end|>
|
| 32 |
+
<|im_start|>user
|
| 33 |
+
{User}
|
| 34 |
+
<|im_end|>
|
| 35 |
+
<|im_start|>assistant
|
| 36 |
+
{Assistant}
|
| 37 |
+
````
|
| 38 |
+
|
| 39 |
### Install the necessary packages
|
| 40 |
|
| 41 |
```bash
|