search

DAMO-NLP-SG / VideoLLaMA2

VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs
Apache License 2.0
814 stars 56 forks source link

Weights #1

Closed danil31219as closed 1 day ago

danil31219as commented 4 months ago

When will the weights be available?

lixin4ever commented 4 months ago

Thank you for your attention.

We are finalizing the draft of the technical report and the model weights will be online together with the technical report, hopefully by the end of Friday.

lixin4ever commented 4 months ago

@danil31219as The weights are now available at: https://huggingface.co/DAMO-NLP-SG/VideoLLaMA2-7B .

SeanChenxy commented 4 months ago

Hi, what is the difference between Base and Chat weights?

lixin4ever commented 4 months ago

Base refers to the model pre-trained with large-scale caption-only data (i.e., the first-stage model) while Chat model is further fine-tuned from Base model (i.e., the second-stage model).