JEEHYE NA

tran/test split json file for MSR-VTT caption task reproduce

4

Thank you for your wonderful project! Could you provide the train/test split JSON files for the MSR-VTT caption dataset? I am unable to access the following files: • datasets/annotations_all/msrvtt_caption/train.jsonl •...

Thank you for your wonderful project, I'm trying to implement cider optimization on Mplug-2, [(reference)](https://github.com/X-PLUG/mPLUG/blob/main/caption_mplug_scst.py) but I am keep getting an error that "CocoEvaluator is not found in language_evaluation". Can...

Issue Downloading SmartEdit-7B Checkpoint: Missing config.json

1

Thank you for your remarkable work on this project! I am currently trying to download the checkpoint for SmartEdit-7B using the following code: ``` from transformers import AutoTokenizer, AutoModelForCausalLM cache_dir...

Does the model work in scenarios with missing modalities?

2

Thank you for your wonderful project. Can this language-binding model handle scenarios where a modality is missing? Specifically, is it possible to perform inference without the audio modality, and if...

Request of code or guideline to generate preference data using llava critic. (==reproduce llava-onevision-ov-chat)

1

Thank you for your amazing contributions and for sharing such an exciting project. As I understand, the llava-onevision-qwen2-7b-ov-chat model is built upon the llava-onevision-qwen2-7b-ov model, with preference data generated by...

How can I add custom container for VideoLLaMA3 model?

8

### Search before asking - [x] I have searched the jetson-containers [issues](https://github.com/dusty-nv/jetson-containers/issues) and found no similar feature requests. ### Question Hi, I'm trying to run the [VideoLLaMA3 ](https://github.com/DAMO-NLP-SG/VideoLLaMA3)model on Jetson...

Hi, thank you for this interesting project! I’m sorry if this question is not directly related to the project itself, but I’d like to ask about the environment setup you...

Request for script to reproduce naive GRPO baseline

1

Hello, thank you for sharing this great project! 🙏 I would like to reproduce and test the naive GRPO baseline (without the second-pass self-reward) under the same environment and settings...