Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | $0.20 |
| Output tokens | $0.20 |
Capabilities
VisionMultimodalReasoningFunction CallingTool UseJSON ModeCode Execution
About CodeLlama 7B Instruct
CodeLlama 7B Instruct is a specialized variant of Meta's CodeLlama family, designed for code synthesis and understanding tasks. With 7 billion parameters, it excels in code completion, infilling, and following instructions, particularly in Python programming. The model has been fine-tuned to generate code based on user prompts, ensuring safer and more reliable outputs. It's part of a broader collection ranging from 7B to 34B parameters, trained on a diverse dataset for handling various coding tasks effectively. AI engineers can leverage this model to integrate advanced code generation capabilities into their applications, enhancing productivity in software development. For more details, visit the model's page on Hugging Face .
Get Started
Model Specs
Released2023-08-24
Parameters7B
Context16K
ArchitectureDecoder Only