Mistral: Mixtral 8x7B Instruct
Mistral
Mixtral 8x7B Instruct is a pretrained generative Sparse Mixture of Experts, by Mistral AI, for chat and instruction use. Incorporates 8 experts (feed-forward networks) for a total of 47 billion parameters. Instruct model fine-tuned by Mistral. #moe
Parameters
7B
Context
32768
Modality
text->text
License
open_weights
Open source
Yes
Open Mistral: Mixtral 8x7B Instruct in AIniverse
Compare versions, read real ratings, save to your stack.
Open in App