Скачать или смотреть StarCoder 2 Is An AI Code Generator From ServiceNow, Hugging Face, and Nvidia. Here's What's New.

Want to run your own code-generating AI model but don’t want to pay someone else for it? Well, ServiceNow, Hugging Face, and Nvidia have released free code-generating AI models StarCoder2-3B/7B/15B, the first two of which can run on most modern consumer GPUs. Quoting TechCrunch:

StarCoder 2 isn’t a single code-generating model, but rather a family. Released today, it comes in three variants, the first two of which can run on most modern consumer GPUs:

A 3-billion-parameter (3B) model trained by ServiceNow
A 7-billion-parameter (7B) model trained by Hugging Face
A 15-billion-parameter (15B) model trained by Nvidia, the newest supporter of the StarCoder project

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. 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.

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. 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.

ENDQUOTE

Quoting VentureBeat:

While BigCode’s original StarCoder LLM debuted in one 15B-parameter size and was trained on about 80 programming languages, the latest generation step beyond it with models in three different sizes – 3B, 7B and 15B – and training on 619 programming languages. According to BigCode, the training data for the new models, known as The Stack, was more than seven times larger than the one used last time.

More importantly, the BigCode community used new training techniques for the latest generation to ensure that the models can understand and generate low-resource programming languages like COBOL, mathematics and program source code discussions.

While it remains to be seen how well these models perform in different coding scenarios, the companies did note that the performance of the smallest 3B model alone matched that of the original 15B StarCoder LLM. ENDQUOTE

But caveat caveat. Quoting TechCrunch again:

StarCoder 2’s license might prove to be a roadblock for some.

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. 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). Some commentators say RAIL-M’s requirements may be too vague to comply with in any case — and that RAIL-M could conflict with AI-related regulations like the EU AI Act.

#ainews