Richard Mao

We're trying to train an autonomous driving model based our own map. We have gpkg map file already but our map file doesn't contain many of the attributes in the...

Negative reward when serving ArmoRM-Llama3-8B-v0.1

4

Hello! When I serve ArmoRM-Llama3-8B-v0.1 using OpenRLHF, the output rewards are almost negative (around -2.0). I've attached some pictures of how I served the reward model. Is the output of...

Missing code for ODIN

1

In ODIN's code, args.correlation_with_length appears in the README.md, but it doesn't appear in other Python scripts or bash files. Did the author forget to push the code of this part...

Can we initialize the solution of qpth with some approximated solution?

1

If I have some solution (which may be inaccurate), can I initialize qpth with this solution to obtain a better solution? I know that some other solvers can set the...