GraphCanon updated 2w · GitHub synced 2w
Decision brief
CodeGen is a series of open-source large language models designed for program synthesis. Trained on TPUs, CodeGen offers several versions with varying capabilities from basic code generation to advanced infill sampling.
Good fit when
- When you require high-performance model training and code generation that matches or exceeds the performance of OpenAI Codex on specific tasks
- If your project benefits from working with open-source models under Apache License 2.0, providing flexibility in implementation without restrictive licensing terms
Avoid when
- In scenarios where the model's primary use is not centered around code generation or program synthesis, as its specialized training may limit its effectiveness for other types of generative tasks
- If your project strictly requires a smaller memory footprint or simpler deployment because advanced models like CodeGen2.5 require significant computational resources and setup
Observed Jul 12, 2026 · Source: enrich:decision_facts
Verify the decision
Maintenance and security
Full trust report- Maintenance
- Steady (60d since push)
- As of 2w
- Provenance
- Not a fork · Organization account
- As of 2w
- Security (OSV)
- No lockfile
- As of 1mo
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Install
pip install CodeGenSimilar tools
Same-category neighbours. No typed graph edges are catalogued for this tool yet.
Evidence and technical details
Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.
Overview
CodeGen is a series of large language models for code generation and synthesis tasks. These models are trained on TPUs and include versions like CodeGen1, CodeGen2, and CodeGen2.5, each with varying capabilities from simple to advanced code infill sampling.
Capability facts
- Languages
- python
Source: github.language · Aug 2, 2026
Categories
Compatibility
Sourced claims from the README excerpt - not unsourced marketing copy.
Tags
README
CodeGen
Official release for the CodeGen1 and CodeGen2 models (350M, 1B, 3B, 7B 16B) for Program Synthesis by Salesforce AI Research.
News
July 2023
CodeGen2.5 released outperforming 16B parameter models with only 7B.
May 2023
CodeGen2.0 released with strong infill sampling capability.
March 2022
CodeGen1.0 released on par with OpenAI Codex at the time.
Publications
CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis
Erik Nijkamp*, Bo Pang*, Hiroaki Hayashi*, Lifu Tu, Huan Wang, Yingbo Zhou, Silvio Savarese, and Caiming Xiong
ICLR, 2023
CodeGen2: Lessons for Training LLMs on Programming and Natural Languages
Erik Nijkamp*, Hiroaki Hayashi*, Caiming Xiong, Silvio Savarese, and Yingbo Zhou
ICLR, 2023
Usage
The models are available on the Hugging Face Hub.
CodeGen1.0
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("Salesforce/codegen-2B-mono")
model = AutoModelForCausalLM.from_pretrained("Salesforce/codegen-2B-mono")
inputs = tokenizer("# this function prints hello world", return_tensors="pt")
sample = model.generate(**inputs, max_length=128)
print(tokenizer.decode(sample[0], truncate_before_pattern=[r"\n\n^#", "^'''", "\n\n\n"]))
CodeGen2.0
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("Salesforce/codegen2-7B")
model = AutoModelForCausalLM.from_pretrained("Salesforce/codegen2-7B", trust_remote_code=True, revision="main")
inputs = tokenizer("# this function prints hello world", return_tensors="pt")
sample = model.generate(**inputs, max_length=128)
print(tokenizer.decode(sample[0], truncate_before_pattern=[r"\n\n^#", "^'''", "\n\n\n"]))
CodeGen2.5
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("Salesforce/codegen25-7b-mono", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("Salesforce/codegen25-7b-mono")
inputs = tokenizer("# this function prints hello world", return_tensors="pt")
sample = model.generate(**inputs, max_length=128)
print(tokenizer.decode(sample[0]))
Training
The Jaxformer library for data pre-processing, training and fine-tuning the CodeGen models can be found here:
https://github.com/salesforce/jaxformer
Citation
If you find our code or paper useful, please cite the paper:
@article{nijkamp2022codegen,
title={CodeGen: An Open Large Language Model for Code with Multi-Turn 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={ICLR},
year={2023}
}
@article{nijkamp2023codegen2,
title={CodeGen2: Lessons for Training LLMs on Programming and Natural Languages},
author={Ni
For agents
This page has a .md twin and JSON over the API.