![]() While less constraining than many other licenses, RAIL-M isn’t truly “open” in the sense that it doesn’t permit developers to use StarCoder 2 for every conceivable application (medical advice-giving apps are strictly off limits, for example). ![]() StarCoder 2 is licensed under the BigCode Open RAIL-M 1.0, which aims to promote responsible use by imposing “light touch” restrictions on both model licensees and downstream users. StarCoder 2’s license might also prove to be a roadblock for some. Elsewhere, a poll from Sonatype, the cybersecurity firm, shows that the majority of developers are concerned about the lack of insight into how code from code generators is produced and “code sprawl” from generators producing too much code to manage. Code generators promise to streamline certain coding tasks - but at a cost.Ī recent Stanford study found that engineers who use code-generating systems are more likely to introduce security vulnerabilities in the apps they develop. Now, I’d venture to say that not every developer would agree with de Vries on the speed and quality points. “With StarCoder2, developers can use its capabilities to make coding more efficient without sacrificing speed or quality.” “StarCoder 2 was created especially for developers who need to build applications quickly,” Harm de Vries, head of ServiceNow’s StarCoder 2 development team, told TechCrunch in an interview. And, because it was trained on a larger and more diverse data set than the original StarCoder (~619 programming languages), StarCoder 2 can make more accurate, context-aware predictions - at least hypothetically. StarCoder 2 can be fine-tuned “in a few hours” using a GPU like the Nvidia A100 on first- or third-party data to create apps such as chatbots and personal coding assistants. ![]() Trained with 4x more data than the original StarCoder (67.5 terabytes versus 6.4 terabytes), StarCoder 2 delivers what Hugging Face, ServiceNow and Nvidia characterize as “significantly” improved performance at lower costs to operate. Like most other code generators, StarCoder 2 can suggest ways to complete unfinished lines of code as well as summarize and retrieve snippets of code when asked in natural language. (Note that “parameters” are the parts of a model learned from training data and essentially define the skill of the model on a problem, in this case generating code.) A 15-billion-parameter (15B) model trained by Nvidia, the newest supporter of the StarCoder project.A 7-billion-parameter (7B) model trained by Hugging Face.A 3-billion-parameter (3B) model trained by ServiceNow.Released today, it comes in three variants, the first two of which can run on most modern consumer GPUs: ![]() StarCoder 2 isn’t a single code-generating model, but rather a family. The original came online early last year, and work has been underway on a follow-up, StarCoder 2, ever since. Perceiving the demand for alternatives, AI startup Hugging Face several years ago teamed up with ServiceNow, the workflow automation platform, to create StarCoder, an open source code generator with a less restrictive license than some of the others out there. ![]() Others are, but only under licenses that preclude them from being used in common commercial contexts. Developers are adopting AI-powered code generators - services like GitHub Copilot and Amazon CodeWhisperer, along with open access models such as Meta’s Code Llama - at an astonishing rate. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |