Codestral Mamba
Codestral Mamba is Mistral’s 7B code-generation model built on the Mamba state-space architecture. Its release explores efficient sequence modeling for long code inputs and fast local inference. Apache-2.0 weights and inference support allow adaptation without the original Codestral license restrictions. Mistral tested in-context retrieval up to 256K tokens, but that test should not be interpreted as guaranteed accuracy on every long code task. The model is a coding specialist rather than a general multimodal assistant.
2024-07-16
7B
Mamba-2 state-space language model
Apache-2.0
Specifications
- Parameters
- 7B
- Architecture
- Mamba-2 state-space language model
- License
- Apache-2.0
- Type
- text
- Modalities
- text
Benchmark Scores
Advanced Specifications
- Model Family
- Codestral
- API Access
- Available
- Chat Interface
- Not Available
Capabilities & Limitations
- Capabilities
- code generationlong-sequence inference
- Known Limitations
- Specialized coding modelLong retrieval tests do not establish universal long-context quality
- Notable Use Cases
- local coding assistancecode-model research