Yonghui Wang
> 十分感谢！这个数据集确实难找。 请问您找到数据集了吗，能否发我一下？谢谢！[email protected]
Who achieved this, can you share me?
> Going to close this and open a discussion. I have the same question
how to optimize the vision encoder? which code should i modify?
> Could you please publish a license for this repo? Sure, I have created it.
> Hi, thank you for the great work! > > I would love to try your model out, but I do not have Baidu account, and I was wondering if...
Sorry for late reply, you can download the ckpt here https://huggingface.co/IDEA-Research/grounding-dino-base
Sorry for the late reply, I can't find the program for generating the JSON file anymore. I only found some draft files and updated them in the 'tool' folder, named...
one is for the doctr geometric model and the other uses the dewarpnet geometric model.
> The full error message looks like below: > > Traceback (most recent call last): File "/cpfs01/shared/XNLP_H800/liurunzhou/ROOT/main.py", line 45, in my_vlm.initialize_llm(checkpoint=config.qwen_checkpoint) File "/cpfs01/shared/XNLP_H800/liurunzhou/ROOT/api/qwen2vl_sft.py", line 22, in initialize_llm self.processor = AutoProcessor.from_pretrained(checkpoint)...