WizardLM-2 7B

microsoft/wizardlm-2-7b

About WizardLM-2 7B

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

Specifications

Context Length

32,000

Tokenizer

Mistral

Pricing

Prompt

0.070

Completion

0.070

Image

0

Request

0

Last updated: 4/11/2025