Update README.md
Browse files
README.md
CHANGED
|
@@ -47,6 +47,16 @@ Since the model is relatively very small, I recommend the larger quantizations.
|
|
| 47 |
|
| 48 |
Base Model: [microsoft/phi-2](https://huggingface.co/microsoft/phi-2)
|
| 49 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 50 |
### MT-bench / heval
|
| 51 |
|
| 52 |
|
|
|
|
| 47 |
|
| 48 |
Base Model: [microsoft/phi-2](https://huggingface.co/microsoft/phi-2)
|
| 49 |
|
| 50 |
+
### Chat template
|
| 51 |
+
|
| 52 |
+
The model uses the same chat template as found in Mistral instruct models:
|
| 53 |
+
|
| 54 |
+
```python
|
| 55 |
+
text = "<|endoftext|>[INST] What is your favourite condiment? [/INST]"
|
| 56 |
+
"Well, I'm quite partial to a good squeeze of fresh lemon juice. It adds just the right amount of zesty flavour to whatever I'm cooking up in the kitchen!<|endoftext|> "
|
| 57 |
+
"[INST] Do you have mayonnaise recipes? [/INST]"
|
| 58 |
+
```
|
| 59 |
+
|
| 60 |
### MT-bench / heval
|
| 61 |
|
| 62 |
|