mm-cot icon indicating copy to clipboard operation
mm-cot copied to clipboard

Official implementation for "Multimodal Chain-of-Thought Reasoning in Language Models" (stay tuned and more will be updated)

Results 60 mm-cot issues
Sort by recently updated
recently updated
newest added

Firstly, thank you for sharing your work. requirements.txt refers to both nltk==3.5 and nltk==3.8. This causes error when installing requirements.txt. For now I am trying to proceed by removing nltk==3.5...

Reformats all the text from the old "%-formatted" and `.format()` formats to the newer f-string format, as defined in PEP 498. This requires Python 3.6+. Flynt 0.76 was used to...

*Issue #, if available: Conflicting versions of nltk and huggingface-hub *Description of changes:* ERROR: Cannot install huggingface-hub==0.0.12 and sentence-transformers==2.2.2 because these package versions have conflicting dependencies. And similarly "rich" By...

Dear authors, Thanks for your exciting and solid work. May I ask why Multimodal Chain-of-Thought is still significantly better than UnifiedQA when there is no visual input (e.g, the text...

Trying to use it as a zero-shot image classification problem. An image where both Adidas and Nike are available, and text input includes ["Adidas", "Nike"], the output is "Adidas". Ideally,...

Dear authors, Thanks for your amazing work. I wonder why the Multimodal-CoT w/o two-stage outperforms the Multimodel on the SOC in Table 5? This is indeed a huge gap and...

Thank u for your great work and code, I have tried it, but got this error, can u help me solve it. It seems that lack of the josn files....

*Issue #1 :* Two versions of nltk *Description of changes:* Removed the older version of nltk By submitting this pull request, I confirm that you can use, modify, copy, and...

*Issue #, if available:* *Description of changes:* By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of your choice.

I can train the model in the first phase, but when it comes to validating, the server will get stuck. ![NombreParaImagen_001](https://user-images.githubusercontent.com/115718053/220289902-ff850ac8-995d-4a21-ab7b-29d5244d10ad.png) The server configuration is as follows: > CPU: Architecture:...