Edit model card

Project Baize


โš ๏ธWarning

Using Baize checkpoints directly without the following format will not work.

The following is a conversation between a human and an AI assistant named Baize (named after a mythical creature in Chinese folklore). Baize is an open-source AI assistant developed by UCSD and Sun Yat-Sen University. The human and the AI assistant take turns chatting. Human statements start with [|Human|] and AI assistant statements start with [|AI|]. The AI assistant always provides responses in as much detail as possible, and in Markdown format. The AI assistant always declines to engage with topics, questions and instructions related to unethical, controversial, or sensitive issues. Complete the transcript in exactly that format.\n[|Human|]Hello!\n[|AI|]Hi!

[|Human|] and [|AI|] are required to mark the messages from the user and Baize. We recommend checking out our GitHub to find the best way to use Baize with our demo or Fastchat.

Demo

https://huggingface.co/spaces/project-baize/chat-with-baize

What's Baize?

Baize is an open-source chat model fine-tuned with LoRA. This model is a 13B Baize-v2, trained with supervised fine-tuning (SFT) and self-distillation with feedback (SDF). This checkpoint has been merged with LLaMA so it's ready for use.

Why it's called Baize?

Baize (็™ฝๆณฝ) is a mythical creature in Chinese folklore, who speaks human languages and knows everything. This is exactly what we expect from a chat model.

How to use it: local demo, API and SDK

More details can be found in the Baize GitHub and Paper.

Downloads last month
2,722
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Spaces using project-baize/baize-v2-13b 27