Sourcify
Effortlessly find and manage open-source dependencies for your projects.
Development
Freemium
From $99/mo
Smart Contract Verification
Dependency Management
Security Auditing
StarCoder2-15B
4.2
Free Generally positive sentiment highlighting the model's code generation capabilities and efficiency, but some users report occasional inaccuracies.
A 15B parameter model trained on 600+ programming languages, designed for code generation and understanding.
0 views
0 saves
|
Refined 2/22/2026
About StarCoder2-15B
StarCoder2-15B is a 15 billion parameter language model trained on over 600 programming languages from The Stack v2 dataset. It leverages a Transformer decoder architecture with grouped-query and sliding window attention mechanisms, enabling it to process context windows of up to 16,384 tokens. The model was trained using the Fill-in-the-Middle objective on over 4 trillion tokens using NVIDIA's NeMo framework on NVIDIA DGX H100 systems. StarCoder2-15B excels in code generation tasks, providing code snippets based on context, though it is not an instruction model and does not work well with natural language instructions directly. It offers quantized versions using bitsandbytes for reduced memory footprint, making it accessible on various hardware configurations, from CPU to multi-GPU setups.
Core Capabilities
StarCoder2-15B is a 15 billion parameter language model trained on over 600 programming languages from The Stack v2 dataset.
Main Tasks
Generate code snippets
Explore all tools that specialize in generate code snippets. This domain focus ensures StarCoder2-15B delivers optimized results for this specific requirement.
