The Mistral-7B-Instruct-v0.1 Large Language Model (LLM) is an instruction-tuned version of the Mistral-7B-v0.1 generative text model using a variety of publicly available conversation datasets.

Instruction format

In order to leverage instruction fine-tuning, your prompt should be surrounded by [INST] and [/INST] tokens. The very first instruction should begin with a begin of sentence id. The next instructions should not. For multi-turn prompts, the assistant’s generation should terminate with the EOS token id.

E.g.

prompt = "<s>[INST] What is your favourite condiment? [/INST]"
"Well, I'm quite partial to a good squeeze of fresh lemon juice. It adds just the right amount of zesty flavour to whatever I'm cooking up in the kitchen!</s> "
"[INST] Do you have mayonnaise recipes? [/INST]"

For further information, see the Mistral-7B launch [blog post].(https://mistral.ai/news/announcing-mistral-7b/)