Hugging Face's logo
Bram Vanroy's picture
73 3 118

Bram Vanroy PRO

BramVanroy
Moizuddin's profile picture rkennezangue's profile picture Zmu's profile picture
·
https://bramvanroy.github.io/

AI & ML interests

Artificial intelligence, natural language processing, computational linguistics

Organizations

Language and Translation Technology Team's profile picture BigScience Workshop's profile picture How to teach Hugging Face?'s profile picture Hugging Face Fellows's profile picture Blog-explorers's profile picture HPLT's profile picture ZeroGPU Explorers's profile picture TENACITY's profile picture signon-project's profile picture Occiglot's profile picture Social Post Explorers's profile picture Hugging Face Discord Community's profile picture Networks of Ideas and Knowledge in the Ancient World's profile picture

Posts 11

view post
Post
1463
The InstructGPT paper mentions that they insert 10% pretraining data during SFT, which they find improves the effect of PPO (IIUC). Has anyone else done later ablations on this? I've only seen the inverse suggested, mixing in SFT data during pretraining.
view post
Post
2160
All my models seem to be plagued by infinite lists. When you ask a question that requires it to write a list, it most often keeps adding bullet points or enumeration. I am wondering whether this is a result of using chatty GPT-4 as DPO preferences. Any thoughts?
View all posts

Collections 7

Papers 1