One of the most popular open-source LLMs, Mistral's 7B Instruct model's balance of speed, size, and performance makes it a great general-purpose daily driver.

97.1K Downloads

38 stars

1 fork

Capabilities

Minimum system memory

4GB

Tags

7B
mistral

Last updated

Updated on May 24by
lmmy's profile picture
lmmy

README

Mistral 7B Instruct v0.3 by mistralai

Version 0.3 has a few changes over release 0.2, including:

  • An extended vocabulary (32000 → 32768)
  • A new tokenizer
  • Support for function calling

Function calling support is made possible through the new extended vocabulary, including tokens TOOL_CALLS, AVAILABLE_TOOLS, and TOOL_RESULTS.

This model maintains the v0.2 context length of 32768

Sources

The underlying model files this model uses