Renjie PI

problem with installing

2

Hi, I. tried to install the program, then there was a problem with nms_cuda.c, the file seems to be missing, is there anything particular that I have to do before...

Inquiry about Sample Efficient Neural architecture search by learning action space

1

Hello, as you have recommended, I studied your new paper and was amazed by the result, and the idea was quite enlightening, however, there are a few things that still...

Code for Rnn predictor

1

Thank you for the code! It would be great if you can share the RNN predictor code as well, because I'd like to try both and see the result. Great...

[Usage] How to load fine-tuned lora checkpoint for CLI inference

15

### Describe the issue Issue: Hi! Could you explain how to load the model weights for lora after fine-tuning? Also the mm_projector seems to need be separately loaded? I did...

when running train.py in /rnn, RuntimeError: One of the differentiated Tensors appears to not have been used in the graph. Set allow_unused=True if this is the desired behavior.

Dear author, Thank you very much for the code, I have a problem when running risk_curve.py, the results I got after running the code using default setting didn't have the...

How to speed up the loop in build_with_representer_proxy_batch

1

Hi, thank you very much for providing the code! I've installed jax with CUDA, so now solving the kernel_fn is faster. However, the build_with_representer_proxy_batch is still quite slow, I assume...

question regarding performance of normal training on corrupted labels

20

Hi, thank you very much for the code. However, for noisy labels, I do not observe significant difference between MWN and normal training (without MWN) when the corruption prob is...

Weird result with openAI config

1

Dear authors, Thank you so much for this in interesting work. I am trying to run vision agent locally with openai config the the following example: from vision_agent.agent import VisionAgentCoderV2...