You're looking at a specific version of this model. Jump to the model overview.
andreasjansson /codegen:211bde4f
Input schema
The fields you can use to run this model with an API. If you don’t give a value for a field its default value will be used.
| Field | Type | Default value | Description |
|---|---|---|---|
| context |
string
|
# Implement a function that computes the square of an integer argument.
|
Some starting python code. CodeGen will try to complete the code provided. Providing examples of what you want to do before your prompt can improve performance.
|
| prepend_context_to_output |
boolean
|
True
|
Whether to prepend your input to the output.
|
| num_return_sequences |
integer
|
1
Min: 1 Max: 10 |
Number of code completions to generate from context.
|
| temperature |
number
|
0.2
Max: 1 |
Increase to improve diversity of outputs, may cause artifacts.
|
| prepend_imports |
boolean
|
True
|
Whether to prepend a numpy import to the context as in the paper.
|
| top_p |
number
|
0.95
Max: 1 |
Top-p sampling probability.
|
| max_length |
integer
|
128
Min: 32 Max: 2048 |
Max length of returned sequences.
|
| seed |
integer
|
-1
|
Seed for reproducibility. Use -1 for a random seed.
|
| raw_output |
boolean
|
False
|
Whether to return a long string (multiple code snippets separated by the string `======`) or a markdown url to be downloaded. May find useful for api.
|
Output schema
The shape of the response you’ll get when you run this model with an API.
Schema
{'description': 'Helper Output class for CodeGen. Allows for output to be '
'markdown file or string.',
'properties': {'markdown': {'format': 'uri',
'title': 'Markdown',
'type': 'string'},
'raw_output': {'title': 'Raw Output', 'type': 'string'}},
'title': 'CodeGenOutput',
'type': 'object'}