Skip to content

Commit

Permalink
Add one more paper
Browse files Browse the repository at this point in the history
  • Loading branch information
mallamanis committed Sep 23, 2023
1 parent f7513e9 commit e2ae08d
Showing 1 changed file with 12 additions and 0 deletions.
12 changes: 12 additions & 0 deletions _publications/muennighoff2023octopack.markdown
Original file line number Diff line number Diff line change
@@ -0,0 +1,12 @@

---
layout: publication
title: "OctoPack: Instruction Tuning Code Large Language Models"
authors: Niklas Muennighoff, Qian Liu, Armel Zebaze, Qinkai Zheng, Binyuan Hui, Terry Yue Zhuo, Swayam Singh, Xiangru Tang, Leandro von Werra, Shayne Longpre
conference:
year: 2023
additional_links:
- {name: "ArXiV", url: "https://arxiv.org/abs/2308.07124"}
tags: ["dataset", "instruction tuning"]
---
Finetuning large language models (LLMs) on instructions leads to vast performance improvements on natural language tasks. We apply instruction tuning using code, leveraging the natural structure of Git commits, which pair code changes with human instructions. We compile CommitPack: 4 terabytes of Git commits across 350 programming languages. We benchmark CommitPack against other natural and synthetic code instructions (xP3x, Self-Instruct, OASST) on the 16B parameter StarCoder model, and achieve state-of-the-art performance among models not trained on OpenAI outputs, on the HumanEval Python benchmark (46.2% pass@1). We further introduce HumanEvalPack, expanding the HumanEval benchmark to a total of 3 coding tasks (Code Repair, Code Explanation, Code Synthesis) across 6 languages (Python, JavaScript, Java, Go, C++, Rust). Our models, OctoCoder and OctoGeeX, achieve the best performance across HumanEvalPack among all permissive models, demonstrating CommitPack's benefits in generalizing to a wider set of languages and natural coding tasks. Code, models and data are freely available at https://github.com/bigcode-project/octopack.

0 comments on commit e2ae08d

Please sign in to comment.