This is just a conversion of the Mistral-7B-v0.2 model shared by the Mistral team during the SF hackathon.

The script used was from transformers

Safetensors

Model size

7.24B params

Tensor type

BF16

Inference Providers NEW

This model is not currently available via any of the supported Inference Providers.

Model tree for wandb/Mistral-7B-v0.2

Finetunes

Quantizations