andreasjansson / codegen

An open-source model for program synthesis. Competitive with OpenAI Codex.

Cold

Public
1.1K runs
A100 (80GB)
GitHub
Paper
License

Run with an API

Playground API Examples README Versions

Input

context

string

Shift + Return to add a new line

# Implement a function that computes the square of an integer argument.
# 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.

Default: "# Implement a function that computes the square of an integer argument.\n"

prepend_context_to_output

boolean

Whether to prepend your input to the output.

Default: true

num_return_sequences

integer

(minimum: 1, maximum: 10)

Number of code completions to generate from context.

Default: 1

temperature

number

(minimum: 0, maximum: 1)

Increase to improve diversity of outputs, may cause artifacts.

Default: 0.2

prepend_imports

boolean

Whether to prepend a numpy import to the context as in the paper.

Default: true

top_p

number

(minimum: 0, maximum: 1)

Top-p sampling probability.

Default: 0.95

max_length

integer

(minimum: 32, maximum: 2048)

Max length of returned sequences.

Default: 128

seed

integer

Seed for reproducibility. Use -1 for a random seed.

Default: -1

raw_output

boolean

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.

Default: false

Run this model in Node.js with one line of code:

npx create-replicate --model=andreasjansson/codegen

or set up a project from scratch

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import and set up the client:

import Replicate from "replicate";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run andreasjansson/codegen using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "andreasjansson/codegen:211bde4f1da227ce567f2db0fe3811d27435f69b3ac1c37237f3272fa1e79820",
  {
    input: {
      seed: -1,
      top_p: 0.95,
      context: "# Implement a function that computes the square of an integer argument.\n",
      max_length: 128,
      raw_output: false,
      temperature: 0.2,
      prepend_imports: true,
      num_return_sequences: 4,
      prepend_context_to_output: true
    }
  }
);
console.log(output);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import the client:

import replicate

Run andreasjansson/codegen using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "andreasjansson/codegen:211bde4f1da227ce567f2db0fe3811d27435f69b3ac1c37237f3272fa1e79820",
    input={
        "seed": -1,
        "top_p": 0.95,
        "context": "# Implement a function that computes the square of an integer argument.\n",
        "max_length": 128,
        "raw_output": False,
        "temperature": 0.2,
        "prepend_imports": True,
        "num_return_sequences": 4,
        "prepend_context_to_output": True
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Run andreasjansson/codegen using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "211bde4f1da227ce567f2db0fe3811d27435f69b3ac1c37237f3272fa1e79820",
    "input": {
      "seed": -1,
      "top_p": 0.95,
      "context": "# Implement a function that computes the square of an integer argument.\\n",
      "max_length": 128,
      "raw_output": false,
      "temperature": 0.2,
      "prepend_imports": true,
      "num_return_sequences": 4,
      "prepend_context_to_output": true
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

Rendering markdown...

Generated in

3 minutes 55 seconds

Tweak itReport

Run time and cost

This model costs approximately $0.19 to run on Replicate, or 5 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.

This model runs on Nvidia A100 (80GB) GPU hardware. Predictions typically complete within 136 seconds. The predict time for this model varies significantly based on the inputs.

Readme

CodeGen

This is an unofficial implementation not affiliated with Salesforce.

Sample from the codegen-6B-mono checkpoint trained on python.

Arxiv: A Conversational Paradigm for Program Synthesis

Authors: Erik Nijkamp*, Bo Pang*, Hiroaki Hayashi*, Lifu Tu, Huan Wang, Yingbo Zhou, Silvio Savarese, and Caiming Xiong (* indicates equal contribution)

Released models

The models are named in the following format:

codegen-{model-size}-{data}

model-size has 4 options: 350M, 2B, 6B, 16B, which represent the number of parameters in each model.

data has 3 options: nl, multi, mono.

nl models are randomly initialized and trained on The Pile, a 825.18 GB English text corpous.
multi models are initialized from nl models and then trained on a corpus with code data consisting of multiple programming languages.
mono models are initialized from multi models and then trained on a corpus with Python code data.

Download the model parameters

Citation

If you find our code or paper useful, please cite the paper:

@article{Nijkamp2022ACP,
  title={A Conversational Paradigm for Program Synthesis},
  author={Nijkamp, Erik and Pang, Bo and Hayashi, Hiroaki and Tu, Lifu and Wang, Huan and Zhou, Yingbo and Savarese, Silvio and Xiong, Caiming},
  journal={arXiv preprint},
  year={2022}
}

License

Our code is BSD-3 licensed. See LICENSE.txt for details.

Input

Output

Run time and cost

Readme

CodeGen

Released models

Download the model parameters

codegen-350M-nl,multi,mono

codegen-2B-nl,multi,mono

codegen-6B-nl,multi,mono

codegen-16B-nl,multi,mono

Citation

License