Core Francisco Park

Results 5 comments of Core Francisco Park

Hello, I have a perhaps related question. It seems that the model has the full graph in its GCN layer, but is trained so that the generator will match the...

@pzc163 @Cuiunbo @RylanSchaeffer Given the two checkpoints, perhaps one can compute the diff in the weight to see the histogram? (even though it already seems like there is enough evidence)

HI all! @Jiayi-Pan would you have any updates on the timeline for this? The PR [#205](https://github.com/volcengine/verl/pull/205) seems to be stuct? Thanks!!

Hi all! Thank you for your contributions. Is there an expected timeline for this PR to get merged?

@StephenXie I'm not sure if this is the kind of test you are looking for: I have a setting where I do GRPO on MATH, starting from Qwen2.5-1.5B-Instruct. I would...