Run-Ze Fan

icon indicating a website link https://rzfan525.github.io/

icon company GAIR icon location Shanghai icon location Research Assistant @GAIR-NLP. Working on LLMs alignment, evaluation, and complex reasoning. Prev. Ms. at UCAS.

Results 5 issues of Run-Ze Fan

Is this model a joint method or pipeline method?

I'm a freshman in Event Extraction. I have learned your code. In the train.py, I think this is a multitask because the loss is the sum of triggers loss and...

Does the WizardLM 13B V1.2 in Alpaca Eval Leaderboard use WizardLM/WizardLM_evol_instruct_V2_196k datasets?

Thank you for your amazing work. I'm going to reproduce WizardLM. However, I'm not sure whether WizardLM 13B V1.2 is trained using WizardLM/WizardLM_evol_instruct_V2_196k datasets? Looking forward to your reply.

Where is the 9k cleaned alpaca data in the paper Alpagasus?

2 comment

Where is the 9k cleaned alpaca data in the paper Alpagasus?

What is the difference between these versions of OpenChat?

8 comment

Thank you for your amazing work! I have some questions below: In alpaca eval leaderboard, there are 5 versions: OpenChatV3.1, OpenChatV2-W, OpenChatV2, OpenChat, OpenChat8192. What is the difference? And what...

Can it run on a Linux system with A100 GPUs?

24 comment