Shubham Agarwal

Data Pre-processing for untrimmed videos on non-standard data

2

Hi, Congratulations on such a nice work! Also, thank you for open-sourcing the code! We are trying to use this code on our raw untrimmed videos and want to use...

Llamav2 inference - confusing prompts

3

Hi, It is not clear if we need to follow the prompt template for inference using pipeline as mentioned [here](https://github.com/huggingface/blog/blob/main/llama2.md#how-to-prompt-llama-2) or do we need to follow the pipeline code without...

DocFormerv2

1

Hi @shabie! Are there any plans to release the DocFormerv2 soon? Great work! Thanks!

Hi! Thank you for open-sourcing the code. Could you please also provide scripts related to the GROBID library and storing in markdown format as mention in the Appendix of the...

Hi @rom1504! Thanks for open-sourcing the code! Great work! The [project page](https://laion.ai/blog/laion-400-open-dataset/) mentions that 3456 samples of the LAION-400M were annotated for identifying NSFW content. Is is possible to download...

Hi @haotian-liu ! Interesting work around LLaVa! Issue: I am trying to finetune LLaVa using 8 X H100. When I try to use DeepSpeed Zero Stage 3, it seems that...

1. Updated README; removing old links 2. Removing hard coded paths in extractor.lua 3. Shell script

Hi @dome272 ! Great work! Congratulations for ICLR! Would it be also possible to please release the evaluation scripts used to report results in Tables 1-3? I am trying to...