WizardLM-2 7B

microsoft/wizardlm-2-7b

Created Apr 16, 202432,000 context
$0.07/M input tokens$0.07/M output tokens

WizardLM-2 7B is the smaller variant of Microsoft AI's latest Wizard model. It is the fastest and achieves comparable performance with existing 10x larger opensource leading models

It is a finetune of Mistral 7B Instruct, using the same technique as WizardLM-2 8x22B.

To read more about the model release, click here.

#moe

    WizardLM-2 7B - API, Providers, Stats | OpenRouter