Shawn/Yuxuan Tong
tongyx361
AI & ML interests
Aiming to build AI systems to better serve every human being, especially for complex intellectual activities.
Specifically interested in the following topics:
1) Large Language Model (LLM)
2) AI for (Advanced) Education (e.g. Eureka Labs) / Research (e.g. SciCode-Bench) / Software Engineering (e.g. SWE-Bench)
3) Scalable Alignment(e.g. Scalable Oversight)
4) Hardware-Algorithm Co-Design (e.g. Flash Attention)
Organizations
tongyx361's activity
Should I use CoT prompting in RL model as instruction-tuned model?
1
#3 opened 5 months ago
by
tongyx361
![](https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/eG4R9-3hgrimttP7ep3dN.jpeg)
The number of data sets is inconsistent with the paper
6
#2 opened 6 months ago
by
ymh233
What are the training hyperparameters?
#4 opened 6 months ago
by
tongyx361
![](https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/eG4R9-3hgrimttP7ep3dN.jpeg)
Why does the config show this is a LLaMA model?
4
#1 opened 6 months ago
by
tongyx361
![](https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/eG4R9-3hgrimttP7ep3dN.jpeg)
Is there any valid method to download the dataset without images or part of it like test split only?
3
#2 opened about 1 year ago
by
tongyx361
![](https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/eG4R9-3hgrimttP7ep3dN.jpeg)