Audience
Developers interested in an LLM for code generation
About StarCoder
StarCoder and StarCoderBase are Large Language Models for Code (Code LLMs) trained on permissively licensed data from GitHub, including from 80+ programming languages, Git commits, GitHub issues, and Jupyter notebooks. Similar to LLaMA, we trained a ~15B parameter model for 1 trillion tokens. We fine-tuned StarCoderBase model for 35B Python tokens, resulting in a new model that we call StarCoder.
We found that StarCoderBase outperforms existing open Code LLMs on popular programming benchmarks and matches or surpasses closed models such as code-cushman-001 from OpenAI (the original Codex model that powered early versions of GitHub Copilot). With a context length of over 8,000 tokens, the StarCoder models can process more input than any other open LLM, enabling a wide range of interesting applications. For example, by prompting the StarCoder models with a series of dialogues, we enabled them to act as a technical assistant.
Pricing
Starting Price:
Free
Free Version:
Free Version available.
Integrations
Company Information
BigCode
Founded: 2023
huggingface.co/blog/starcoder
Videos and Screen Captures
Granite Code
We introduce the Granite series of decoder-only code models for code generative tasks (e.g., fixing bugs, explaining code, documenting code), trained with code written in 116 programming languages. A comprehensive evaluation of the Granite Code model family on diverse tasks demonstrates that our models consistently reach state-of-the-art performance among available open source code LLMs.
The key advantages of Granite Code models include:
All-rounder Code LLM: Granite Code models achieve competitive or state-of-the-art performance on different kinds of code-related tasks, including code generation, explanation, fixing, editing, translation, and more. Demonstrating their ability to solve diverse coding tasks.
Trustworthy Enterprise-Grade LLM: All our models are trained on license-permissible data collected following IBM's AI Ethics principles and guided by IBM’s Corporate Legal team for trustworthy enterprise usage.
Learn more
Amazon CodeWhisperer
Build apps faster with ML-powered coding companion. Accelerate application development with automatic code recommendations based on the code and comments in your IDE. Empower developers to use artificial intelligence (AI) responsibly to create syntactically correct and secure applications. Generate entire functions and logical code blocks without having to search and customize code snippets from the web. Stay focused and never leave the IDE, with real-time customized code recommendations for all your Java, Python, and JavaScript projects. Amazon CodeWhisperer is a machine learning (ML)–powered service that helps improve developer productivity by generating code recommendations based on their comments in natural language and code in the integrated development environment (IDE). Accelerate frontend and backend development by empowering developers with automatic code recommendations. Save time and effort by using CodeWhisperer to generate code to build and train your ML models.
Learn more
K.Explorer
A state-of-the-art AI that builds better software, cheaper and faster. K.Explorer is an AI powered Code Assistant trained on many millions of private corporate lines of code, for specific domains, and on billions of public and open-source lines of code for general purposes. Its code auto-completion features suggest code completions and entire function bodies as you type or as you search the engine for help. To make development faster and more agile it even supports Natural Language for programmers to get guidance while telling a text story about the code they want to write.
Learn more
CodeGemma
CodeGemma is a collection of powerful, lightweight models that can perform a variety of coding tasks like fill-in-the-middle code completion, code generation, natural language understanding, mathematical reasoning, and instruction following. CodeGemma has 3 model variants, a 7B pre-trained variant that specializes in code completion and generation from code prefixes and/or suffixes, a 7B instruction-tuned variant for natural language-to-code chat and instruction following; and a state-of-the-art 2B pre-trained variant that provides up to 2x faster code completion. Complete lines, and functions, and even generate entire blocks of code, whether you're working locally or using Google Cloud resources. Trained on 500 billion tokens of primarily English language data from web documents, mathematics, and code, CodeGemma models generate code that's not only more syntactically correct but also semantically meaningful, reducing errors and debugging time.
Learn more
You Might Also Like
Boost application security and continuity with SKUDONET ADC, our Open Source Load Balancer, that maximizes IT infrastructure flexibility. Additionally, save up to $470 K per incident with AI and SKUDONET solutions, further enhancing your organization’s risk management and cost-efficiency strategies.
Product Details
Platforms Supported
Windows
Mac
Linux
On-Premises
Training
Documentation