KeyaoZhao
KeyaoZhao
How to evaluate the model on image retrieval datasets such as Oxford-H? Thanks a lot!
I wonder what is inpainting_mask in the use of Zero-shot Inpainting? We should mask the raw_pil_image first? And the model will inpaint the mask part? Thanks a lot!
您好,想请问下后续是否有打算公开预训练模型的训练代码呢?非常感谢!
关于数据集制作
您好!我想请问一下在新的小数据集上finetune时可能会遗忘学过的LAION 400M,导致finetune后的模型泛化性能下降。所以我计划在finetune时也加入部分LAION 400M数据,但是我使用LAION 400M聚类到1M时的类id可能和您训练时的不同,这是否会产生冲突呢?请问数据集的这些信息或者原始的制作方法您可以公布下吗?非常感谢~
Great Job! And I wonder does DistriFusion support ControlNet? Can you give a example? Thanks a lot!
The url in json file cannot be opened or download. Can you update the url? Thanks a lot.
Thank you for contributing such outstanding work, I would like to ask InternVideo2 support Chinese text search video? What model do I need to replace the VisionEncoder and TextEncoder with?...
[INFO:swift] Traceback (most recent call last): File "/workspace/ms-swift/swift/llm/dataset/preprocessor/core.py", line 172, in batched_preprocess row = self.preprocess(row) File "/workspace/ms-swift/swift/llm/dataset/utils.py", line 442, in preprocess return self.template.encode(row) File "/opt/conda/envs/swift/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context return...
Hello! I want the Ovis2 model output json format however the prompt is not work all the time. Does this model support "response format"? Thanks a lot~