mistral

The 7B model released by Mistral AI, updated to version 0.2.

275.4K Pulls Updated 2 months ago

Mistral is a 7.3B parameter model, distributed with the Apache license. It is available in both instruct (instruction following) and text completion.

The Mistral AI team has noted that Mistral 7B:

  • Outperforms Llama 2 13B on all benchmarks
  • Outperforms Llama 1 34B on many benchmarks
  • Approaches CodeLlama 7B performance on code, while remaining good at English tasks

Versions

Tag Date Notes
v0.2 latest 12/11/2023 A new minor release of Mistral 7B Instruct
v0.1 09/27/2023 Initial release

Variations

instruct Instruct models follow instructions
text Text models are the base foundation model without any fine-tuning for conversations, and are best used for simple text completion.

Usage

CLI

Instruct:

ollama run mistral

API

Example:

curl -X POST http://localhost:11434/api/generate -d '{
  "model": "mistral",
  "prompt":"Here is a story about llamas eating grass"
 }'

References

HuggingFace

Mistral AI News Release