Hyeonbin Hwang

While running Mistral 7B inference with n = 4, on 4 x 48GB, the server just keeps dying and the ssh connection just goes off. Could this be related to...

KTOTrainer Hangs even before the first step for Multi-GPU:

3

Hello! is #1342 fixed? I'm experiencing similar issue, yet even before the first step completes. (i'm using accelerate + deepseed) i.e. It hangs here: from `get_batch_loss_metrics()` in `KTOTrainer`: ``` print("this...

About the alpha value

1

Hello :) Thank you for sharing this amazing code! I'm running this code in colab (python3), and I'm changing several things to accomodate to my settings. Everything works fine until...

Dear Authors, Is it possible for you to generously released the pretrained model? Sincerely,

About Oracle Performance

1

Dear Authors, I've tried using DPR with 'answer' option and use that for result replication in Table 11. However, the performance only reaches about 65%. Could you kindly provide the...

Hi guys! :) Thanks for making your code open-source. One quick question. I've realized that in run_spin.py, you use `apply_chat_template` which differs from the format of `generate.py` or `generate_vllm.py `which...