Update README.md
Browse files
README.md
CHANGED
|
@@ -126,6 +126,26 @@ User prompt...
|
|
| 126 |
|
| 127 |
In this format, the system section is optional and the conversation can be either single-turn or multi-turn. When applying inference, you always make your input string end with "\<s\>bot\n" to ask the model generating answers.
|
| 128 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 129 |
|
| 130 |
## Quickstart
|
| 131 |
|
|
|
|
| 126 |
|
| 127 |
In this format, the system section is optional and the conversation can be either single-turn or multi-turn. When applying inference, you always make your input string end with "\<s\>bot\n" to ask the model generating answers.
|
| 128 |
|
| 129 |
+
For example, the format used to infer HumanEval is like the following:
|
| 130 |
+
|
| 131 |
+
```python
|
| 132 |
+
<s>human
|
| 133 |
+
# language: Python
|
| 134 |
+
from typing import List
|
| 135 |
+
def separate_paren_groups(paren_string: str) -> List[str]:
|
| 136 |
+
""" Input to this function is a string containing multiple groups of nested parentheses. Your goal is to
|
| 137 |
+
separate those group into separate strings and return the list of those.
|
| 138 |
+
Separate groups are balanced (each open brace is properly closed) and not nested within each other
|
| 139 |
+
Ignore any spaces in the input string.
|
| 140 |
+
>>> separate_paren_groups('( ) (( )) (( )( ))')
|
| 141 |
+
['()', '(())', '(()())']
|
| 142 |
+
"""
|
| 143 |
+
<s>bot
|
| 144 |
+
```
|
| 145 |
+
|
| 146 |
+
Specifically, we also add the Programming Language Tag (e.g. #language: Python for Python) used by CodeGeex models.
|
| 147 |
+
|
| 148 |
+
|
| 149 |
|
| 150 |
## Quickstart
|
| 151 |
|