Update README.md
Browse files
README.md
CHANGED
|
@@ -10,6 +10,20 @@ Considerations:
|
|
| 10 |
4. Along with the above, this means the code generated could wind up doing or suggesting just about anything. Run the generated code at own risk...it could be *anything*
|
| 11 |
|
| 12 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
```py
|
| 14 |
-
|
| 15 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
4. Along with the above, this means the code generated could wind up doing or suggesting just about anything. Run the generated code at own risk...it could be *anything*
|
| 11 |
|
| 12 |
|
| 13 |
+
Input to the model is code, up to the context length of 1024, with newlines replaced by `<N>`
|
| 14 |
+
|
| 15 |
+
Here's an example of a quick converter to take your multi-line code and replace the newlines:
|
| 16 |
+
|
| 17 |
```py
|
| 18 |
+
inp = """def do_something():
|
| 19 |
+
print("Hello")
|
| 20 |
+
"""
|
| 21 |
+
|
| 22 |
+
newlinechar = "<N>"
|
| 23 |
+
converted = inp.replace("\n", newlinechar)
|
| 24 |
+
print("length:", len(converted))
|
| 25 |
+
print(converted)```
|
| 26 |
+
|
| 27 |
+
Should give you something like:
|
| 28 |
+
`def do_something():<N> print("Hello")<N>`
|
| 29 |
+
...which is what the model is expecting as input.
|