Zizheng Pan

Pretrained Weights Release

1

Hi, thanks for this great work. Do you have a plan for releasing the pretrained weights on COCO? E.g., the model weights in Table 1, QueryDet with CSQ, AP 38.36.

Pretrained Weights for DiT-S/B/L

5

Hi, thanks for this excellent work. Can you please also provide the pretrained weights for other DiTs? e.g. DiT-S/B/L?

Retrained model does not get the same SPL on val unseen as reported in paper

4

Hi, We are trying to retrain the EnvDrop model based on this repo, but the results are not same as reported in paper, we have tried different PyTorch versions, our...

InternVL2-8B and InternVL2-26B CUDA error: an illegal memory access was encountered

4

Hi authors, Was trying to run InternVL-8B and InternVL-26B on 4 GPUs, but I got this, ``` File ".cache/huggingface/modules/transformers_modules/main/modeling_internlm2.py", line 656, in forward hidden_states, self_attn_weights, present_key_value = self.attention( File "...python3.8/site-packages/torch/nn/modules/module.py",...

Hi authors, Thanks for this excellent work. Can you please update your scripts a bit for local deployment of ShareCaptioner? Initiailly there was an error as noted [here](https://github.com/huggingface/transformers/issues/26340). After switching...