mistralai / mistral-7b-instruct-v0.1

An instruction-tuned 7 billion parameter language model from Mistral

  • Public
  • 902.3K runs
  • GitHub
  • Paper
  • License
Run with an API
Playground API Examples README Train Versions

Input

Output

Run time and cost

This model runs on Nvidia A40 (Large) GPU hardware. Predictions typically complete within 21 seconds. The predict time for this model varies significantly based on the inputs.

Readme

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/)