---
license_link: https://mistral.ai/licences/MNPL-0.1.md
tags:
- code
language:
- code
license: apache-2.0
quantized_by: bartowski
pipeline_tag: text-generation
lm_studio:
  param_count: 22b
  use_case: coding
  release_date: 29-05-2024
  model_creator: mistralai
  prompt_template: Mistral Instruct 
  system_prompt: none
  base_model: mistral
  original_repo: mistralai/Codestral-22B-v0.1
base_model: mistralai/Codestral-22B-v0.1
---
## 💫 Community Model> Codestral 22B v0.1 by Mistral AI

*👾 [LM Studio](https://lmstudio.ai) Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on [Discord](https://discord.gg/aPQfnNkxGC)*.

**Model creator:** [Mistral AI](https://huggingface.co/mistralai)<br>
**Original model**: [Codestral-22B-v0.1](https://huggingface.co/mistralai/Codestral-22B-v0.1)<br>
**GGUF quantization:** provided by [bartowski](https://huggingface.co/bartowski) based on `llama.cpp` release [b3024](https://github.com/ggerganov/llama.cpp/releases/tag/b3024)<br>

## Model Summary:

Codestral is a brand new coding model released by the Mistral team. This 22B model is the first of its size and the first ever specialized model released by this team.<br>
Supporting both instruction prompting and popular Fill in the Middle (FIM) tokens for predictions, this model should be all around great for all your coding tasks.

## Prompt template:

Choose the `Mistral Instruct` preset in your LM Studio.

Under the hood, the model will see a prompt that's formatted like so:

```
<s>[INST]  {prompt} [/INST]</s>
```

This model also supports the following FIM tokens:

`[PREFIX]`, `[SUFFIX]`

## Technical Details

Codestral 22B 0.1 is trained on a dataset of 80+ programming languages including of course Python, Java, C++, Javascript, and Bash.

It supports both instruction querying as well as Fill in the Middle querying.

More details and benchmark information can be found on their blogpost here: https://mistral.ai/news/codestral/

## Special thanks

🙏 Special thanks to [Georgi Gerganov](https://github.com/ggerganov) and the whole team working on [llama.cpp](https://github.com/ggerganov/llama.cpp/) 

🙏 Special thanks to [Kalomaze](https://github.com/kalomaze) and [Dampf](https://github.com/Dampfinchen) for their work on the dataset (linked [here](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8)) that was used for calculating the imatrix for all sizes.

## Disclaimers

LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model.  You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models.  LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.