Code Llama
About
Code Llama is a family of large language models developed by Meta AI, designed for code generation and understanding tasks. Building upon the Llama 2 architecture, Code Llama offers variations to accommodate diverse needs, featuring model sizes with 7B, 13B, 34B, and 70B parameters that adjust complexity and capability. The family comprises the foundational model for general code tasks, Code Llama - Python for tasks specific to the Python language, and Code Llama - Instruct, which is fine-tuned for interpreting natural language instructions. Trained on extensive code and related data, these models excel in code completion, debugging, and generating code from natural language prompts. Larger models tend to provide enhanced performance, albeit at the cost of increased computational demands 12.
Specifications(12 models)
| Model | Released | Context | Parameters | Structured Outputs |
|---|---|---|---|---|
| CodeLlama 70B Python | 2024-01 | 16K | 70B | Yes |
| CodeLlama 70B Instruct | 2024-01 | 16K | 70B | No |
| CodeLlama 34B | 2023-08 | 100K | 34B | Yes |
| CodeLlama 13B | 2023-08 | 100K | 13B | Yes |
| CodeLlama 7B | 2023-08 | 100K | 7B | Yes |
| CodeLlama 34B Python | 2023-08 | 100K | 34B | Yes |
| CodeLlama 13B Python | 2023-08 | 100K | 13B | Yes |
| CodeLlama 7B Python | 2023-08 | 100K | 7B | Yes |
| CodeLlama 34B Instruct | 2023-08 | 16K | 34B | No |
| CodeLlama 13B Instruct | 2023-08 | 16K | 13B | No |
| CodeLlama 7B Instruct | 2023-08 | 16K | 7B | No |
Available From(8 providers)
Pricing
Frequently Asked Questions
- What is Code Llama?
- Code Llama is a family of large language models developed by Meta AI, designed for code generation and understanding tasks. Building upon the Llama 2 architecture, Code Llama offers variations to accommodate diverse needs, featuring model sizes with 7B, 13B, 34B, and 70B parameters that adjust complexity and capability. The family comprises the foundational model for general code tasks, Code Llama - Python for tasks specific to the Python language, and Code Llama - Instruct, which is fine-tuned for interpreting natural language instructions. Trained on extensive code and related data, these models excel in code completion, debugging, and generating code from natural language prompts. Larger models tend to provide enhanced performance, albeit at the cost of increased computational demands 12.
- How many models are in the Code Llama family?
- The Code Llama family contains 12 models.
- What is the latest Code Llama model?
- The latest model is CodeLlama 70B, released in 2024-01.
- How much does Code Llama cost?
- Code Llama models range from $0.05/1M to $3.78/1M input tokens depending on the model and provider.
Models(12)
CodeLlama 70B Python
CodeLlama 70B Instruct
CodeLlama 34B
CodeLlama 13B
CodeLlama 7B
CodeLlama 34B Python
CodeLlama 13B Python
CodeLlama 7B Python
CodeLlama 34B Instruct
CodeLlama 13B Instruct
CodeLlama 7B Instruct






