Commit
·
b6c2541
1
Parent(s):
3aabef8
Update README.md
Browse files
README.md
CHANGED
|
@@ -36,6 +36,19 @@ Make sure to install Transformers from the main git branch:
|
|
| 36 |
pip install git+https://github.com/huggingface/transformers.git
|
| 37 |
```
|
| 38 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 39 |
To reproduce our results:
|
| 40 |
|
| 41 |
```python
|
|
|
|
| 36 |
pip install git+https://github.com/huggingface/transformers.git
|
| 37 |
```
|
| 38 |
|
| 39 |
+
## How to Prompt the Model
|
| 40 |
+
**Please note that this model is somewhat instruction-tuned, but not chat-tuned.**
|
| 41 |
+
|
| 42 |
+
Do not try to use the Llama chat markup with this model. Instead, simply tell it what you want and add "\n: " at the end of your task.
|
| 43 |
+
|
| 44 |
+
For example:
|
| 45 |
+
|
| 46 |
+
```
|
| 47 |
+
Write me a linked list implementation: \n
|
| 48 |
+
```
|
| 49 |
+
|
| 50 |
+
## How to reproduce HumanEval Results
|
| 51 |
+
|
| 52 |
To reproduce our results:
|
| 53 |
|
| 54 |
```python
|