MistralAI introduces Codestral, their first-ever code model. Codestral is an open-weight generative AI model explicitly designed for code generation tasks.

Codestral-22B-v0.1 is trained on a diverse dataset of 80+ programming languages, including the most popular ones, such as Python, Java, C, C++, JavaScript, and Bash (more details in the Blogpost). The model can be queried:

• As instruct, for instance to answer any questions about a code snippet (write documentation, explain, factorize) or to generate code following specific indications

• As Fill in the Middle (FIM), to predict the middle tokens between a prefix and a suffix (very useful for software development add-ons like in VS Code).

Performance

As a 22B model, Codestral sets a new standard on the performance/latency space for code generation compared to previous models used for coding.

License

Codestral is provided under the custom MNPL-0.1 license.