Edge 294: Inside StarCoder: Hugging Face's New LLM that Can Generate Code in Over 80 Programming Languages
StarCoder was created by Hugging Face and ServiceNow as part of the BigCode project.
Coding is one of the most interesting applications of modern large language models(LLMs). Programming is a problem significatively more complex than other language tasks given that it involves different forms of reasoning. However, progress in this area has been clearly visible in the last few years.
GitHub CoPilot has become the gold standard for the application of AI to programming, but it’s certainly not the only one. Amazon recently entered the race with Code Whisperer. Salesforce has been super active in the space with solutions such as CodeGen. Most of those solutions remained close source. Recently, Hugging Face and ServiceNow announced StarCoder, a new open source LLM for coding that matches the performance of GPT-4. StarCoder is part of a larger collaboration known as the BigCode project.