Rattibha

Introducing: 💫StarCoder
StarCoder is a 15B LLM for code with 8k context and trained only on permissive data in 80+ programming languages. It can be prompted to reach 40% pass@1 on HumanEval and act as a Tech Assistant.
Try it here: shorturl.at
Release thread🧵

shorturl.at/cYZ06r

ShortURL - URL Shortener

ShortURL is a tool to shorten a long link. Use our URL shortener to create a short URL to share on s...

In addition to chatting with StarCoder, it can also help you code in the new VSCode plugin. By pressing CTRL+ESC you can also check if the current code was in the pretraining dataset!
marketplace.visualstudio.com

marketplace.visualstudio.com/items?itemName…

Today we release two open-access models!
StarCoderBase: trained on 1T tokens in 80+ programming languages huggingface.co
StarCoder: additionally trained on 35B Python tokens that can be prompted to reach 40.8% pass@1 huggingface.co

huggingface.co/bigcode/starco…

bigcode/starcoderbase · Hugging Face

We’re on a journey to advance and democratize artificial intelligence through open source and open s...

huggingface.co/bigcode/starco…

bigcode/starcoder · Hugging Face

We’re on a journey to advance and democratize artificial intelligence through open source and open s...

We present the most extensive evaluation of code LLMs to date in the full tech report with 68 (!) authors.
You can also read up on all the details from data preprocessing and governance to training at scale!
drive.google.com

drive.google.com/file/d/1cN-b9G…

StarCoder_paper.pdf

StarCoder was also trained on JupyterNotebooks and with Jupyter plugin from @JiaLi52524397 it can make use of previous code and markdown cells as well as outputs to predict the next cell.
You can install it here or search on chrome store: github.com

github.com/bigcode-projec…

GitHub - bigcode-project/jupytercoder

Contribute to bigcode-project/jupytercoder development by creating an account on GitHub.

We release StarCoder under an OpenRAIL license agreement. This OpenRAIL: (i) makes more viable for companies to use and share the model; and (ii) promotes the sharing of AI documentation along the value chain.
huggingface.co

huggingface.co/spaces/bigcode…

BigCode Model License Agreement - a Hugging Face Space by bigcode

Discover amazing ML apps made by the community

For example the folks at @refact_ai are working on a shiny VSCode extension that can now make use of StarCoder to autocomplete or refactor code as well as writing code from an instruction!
refact.ai

refact.ai/blog/2023/self…

Refact.ai - powerful AI coding assistant that combines completion, refactoring, chat, and more.

Boost your productivity by employing AI to pair program with you or make more fun out of your work b...

With @TolokaAI we recruited 1,399 crowd-workers across 35 countries to annotate a diverse dataset for PII in code. Our PII detection model surpasses regex-based tools, especially for secret keys. PII dataset and model are available via gated access.
hf.co

hf.co/bigcode/starpii

bigcode/starpii · Hugging Face

We’re on a journey to advance and democratize artificial intelligence through open source and open s...

We are excited to see what people are gonna build with StarCoder.
Get started with code examples in this repo to fine-tune and run inference on StarCoder:
github.com
You can find all models/datasets/demos at hf.co

github.com/bigcode-projec…

GitHub - bigcode-project/starcoder: Home of StarCoder: fine-tuning & inference!

Home of StarCoder: fine-tuning & inference! Contribute to bigcode-project/starcoder development by c...

hf.co/bigcode

bigcode (BigCode)

Org profile for BigCode on Hugging Face, the AI community building the future.

Twitter seems to block Hugging Face Chat. So to try the model go to huggingface.co slash chat and select StarCoder.

huggingface.co

Hugging Face – The AI community building the future.

We’re on a journey to advance and democratize artificial intelligence through open source and open s...