Mistral AI Models

Mistral AI develops fully open source foundation models. They also expose their models behind a hosted API including ones not released as OSS.

Supported Variants

Airtrain supports 5 variants of Mistral AI models.

Mistral-7B-Instruct-v0.3

This is an instruction-tuned variant of Mistral 7b. It uses open datasets available on Hugging Face. To see the full model card, refer to Hugging Face.

Mixtral-8x7b-Instruct-v0.1

This is an instruction-tuned variant of Mixtral-8x7b, a sparse mixture of experts model with performance rivaling GPT-3.5-turbo. To see the full model card, refer to Hugging Face.

Mixtral-8x22B-Instruct-v0.1

This is an instruction-tuned variant of Mixtral-8x22b, a sparse mixture of experts model with performance surpassing GPT-3.5-turbo. To see the full model card, refer to Hugging Face.

open-mistral-nemo-2407

A 12b open-weight multilingual model with 128k context length. To see the full model card, refer to Hugging Face .

mistral-large-2407

mistral-large is a model Mistral only offers via their API. It is considered a GPT-4 class multilingual model, though it slightly under-performs GPT-4 on most standard benchmarks. It supports function calling.