Update README.md
Browse files
README.md
CHANGED
|
@@ -20,7 +20,22 @@ This model is fine tuned from **HuggingFaceH4/zephyr-7b-beta** on a small synthe
|
|
| 20 |
|
| 21 |
## Uses
|
| 22 |
|
| 23 |
-
Feel free to experiment and don't limit your creativity.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 24 |
|
| 25 |
```python
|
| 26 |
messages = [
|
|
|
|
| 20 |
|
| 21 |
## Uses
|
| 22 |
|
| 23 |
+
This model supports both conversation chat and tasks. Feel free to experiment and don't limit your creativity.
|
| 24 |
+
|
| 25 |
+
The simplest way to try it is to use the `pipeline` from `transformers`.
|
| 26 |
+
|
| 27 |
+
```python
|
| 28 |
+
import torch
|
| 29 |
+
from transformers import pipeline
|
| 30 |
+
|
| 31 |
+
pipe = pipeline(
|
| 32 |
+
"text-generation",
|
| 33 |
+
model="lamhieu/ghost-7b-v0.9.0",
|
| 34 |
+
torch_dtype=torch.bfloat16,
|
| 35 |
+
)
|
| 36 |
+
```
|
| 37 |
+
|
| 38 |
+
You can then try any of the sample codes below, formatted using the chat template.
|
| 39 |
|
| 40 |
```python
|
| 41 |
messages = [
|