# Mistral AI

- Page: https://shared.btbytes.com/p/mistral-ai
- Date: 2023-10-11
- Tags: llm, generative-ai, mistralai

[Mistral AI](https://mistral.ai) is <q>is a European (French?) start-up with a global focus specialising in generative artificial intelligence. Mistral AI aims to develop new models of generative artificial intelligence for companies, combining scientific excellence, an open-source approach, and a socially responsible vision of technology.</q>

## Notes

> If you're using Mistral, I'd suggest playing with [\@Teknium1](https://x.com/Teknium1)'s `OpenHermes2.5 fine-tune`. IMO the best 7B model out there. Together has it.

[See more here](https://x.com/ankrgyl/status/1728942210694201789)

> llama.cpp in server mode which uses mistral 7B GGUF. For all server calls add a field for custom grammar to get the answer in JSON.

[ollama](https://github.com/jmorganca/ollama/blob/main/docs/api.md)


## Papers

The 7Billion parameter model which has outperformed the LLaMa2 from Meta - ([Jiang et al. 2023](https://arxiv.org/abs/2310.06825))

## References

- Jiang, Sablayrolles, Mensch, Bamford, Chaplot, de las Casas, Bressand, Lengyel, Lample, Saulnier, Lavaud, Lachaux, Stock, Scao, Lavril, Wang, Lacroix, Sayed (2023). [Mistral 7B](https://arxiv.org/abs/2310.06825).