Key capabilities

About this model

Code Llama is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 34 billion parameters. This model is designed for general code synthesis and understanding.

Key model capabilities

Code Llama: base models designed for general code synthesis and understanding
Code Llama - Python: designed specifically for Python
Code Llama - Instruct: for instruction following and safer deployment The base model Code Llama can be adapted for a variety of code synthesis and understanding tasks, Code Llama - Python is designed specifically to handle the Python programming language, and Code Llama - Instruct is intended to be safer to use for code assistant and generation applications.

Use cases

See Responsible AI for additional considerations for responsible use.

Key use cases

Code Llama and its variants is intended for commercial and research use in English and relevant programming languages. The base model Code Llama can be adapted for a variety of code synthesis and understanding tasks, Code Llama - Python is designed specifically to handle the Python programming language, and Code Llama - Instruct is intended to be safer to use for code assistant and generation applications.

Out of scope use cases

Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in languages other than English. Use in any other way that is prohibited by the Acceptable Use Policy and Licensing Agreement for Code Llama and its variants.

Pricing

Pricing is based on a number of factors, including deployment type and tokens used. See pricing details here.

Technical specs

Code Llama is an auto-regressive language model that uses an optimized transformer architecture. Code Llama comes in three model sizes, and three variants: Code Llama: base models designed for general code synthesis and understanding
Code Llama - Python: designed specifically for Python
Code Llama - Instruct: for instruction following and safer deployment All variants are available in sizes of 7B, 13B and 34B parameters.

Training cut-off date

The provider has not supplied this information.

Training time

Code Llama and its variants have been trained between January 2023 and July 2023. In aggregate, training all 9 Code Llama models required 400K GPU hours of computation on hardware of type A100-80GB (TDP of 350-400W). Estimated total emissions were 65.3 tCO2eq, 100% of which were offset by Meta's sustainability program.

Input formats

Models input text only.

Output formats

Models generate text only.

Supported languages

Use in languages other than English.

Sample JSON response

[ 
    { 
        "0": "def fibonacci(n = 0):\n a = 0\n b = 1\n if n <= 1:\n return n\n else:\n c = 0\n for i in range(n-1):\n a = b\n b = c\n c = a + b\n return c\n\n\nfibonacci(10)\n" 
    } 
]

Model architecture

Code Llama is an auto-regressive language model that uses an optimized transformer architecture.

Long context

The provider has not supplied this information.

Optimizing model performance

The provider has not supplied this information.

Additional assets

The provider has not supplied this information.

Training disclosure

Training, testing and validation

All experiments reported here and the released models have been trained and fine-tuned using the same data as Llama 2 with different weights. We used custom training libraries. The training and fine-tuning of the released models have been performed Meta's Research Super Cluster.

Distribution

Distribution channels

The provider has not supplied this information.

More information

Code Llama and its variants are a new technology that carries risks with use. Testing conducted to date has been in English, and has not covered, nor could it cover all scenarios. For these reasons, as with all LLMs, Code Llama's potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate or objectionable responses to user prompts. Therefore, before deploying any applications of Code Llama, developers should perform safety testing and tuning tailored to their specific applications of the model. Please see the Responsible Use Guide available at https://ai.meta.com/llama/responsible-use-guide/ This is a static model trained on an offline dataset. Future versions of Code Llama - Instruct will be released as we improve model safety with community feedback. A custom commercial license is available at: https://ai.meta.com/resources/models-and-libraries/llama-downloads/ See evaluations for the main models and detailed ablations in Section 3 and safety evaluations in Section 4 of the research paper.

Responsible AI considerations

Safety techniques

The provider has not supplied this information.

Safety evaluations

See evaluations for the main models and detailed ablations in Section 3 and safety evaluations in Section 4 of the research paper.

Known limitations

Code Llama and its variants are a new technology that carries risks with use. Testing conducted to date has been in English, and has not covered, nor could it cover all scenarios. For these reasons, as with all LLMs, Code Llama's potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate or objectionable responses to user prompts. Therefore, before deploying any applications of Code Llama, developers should perform safety testing and tuning tailored to their specific applications of the model. Please see the Responsible Use Guide available at https://ai.meta.com/llama/responsible-use-guide/

Acceptable use

Acceptable use policy

Out-of-scope Uses Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in languages other than English. Use in any other way that is prohibited by the Acceptable Use Policy and Licensing Agreement for Code Llama and its variants.

Quality and performance evaluations

Source: Meta See evaluations for the main models and detailed ablations in Section 3 and safety evaluations in Section 4 of the research paper.

Benchmarking methodology

Source: Meta The provider has not supplied this information.

Public data summary

Source: Meta The provider has not supplied this information.