VideoRefer Suite: Advancing Spatial-Temporal Object Understanding with Video LLM
Paper
•
2501.00599
•
Published
•
40
zhanghang
hangzhang-nlp
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
9 days ago
VideoRefer Suite: Advancing Spatial-Temporal Object Understanding with
Video LLM
upvoted
a
paper
9 days ago
2.5 Years in Class: A Multimodal Textbook for Vision-Language
Pretraining
upvoted
a
paper
23 days ago
Qwen2.5 Technical Report
Organizations
hangzhang-nlp's activity
upvoted
2
papers
9 days ago
upvoted
a
paper
23 days ago
liked
a
dataset
3 months ago
upvoted
2
papers
3 months ago
liked
a
Space
5 months ago
upvoted
a
paper
6 months ago
liked
a
model
6 months ago
liked
a
Space
6 months ago
reacted to
stas's
post with 👍
8 months ago
Post
If you're trying to run MoE Mixtral-8x7b under DeepSpeed w/ HF Transformers it's likely to hang on the first forward.
The solution is here https://github.com/microsoft/DeepSpeed/pull/4966?_x_tr_sl=auto&_x_tr_tl=en&_x_tr_hl=en-US#issuecomment-1989671378
and you need deepspeed>=0.13.0
Thanks to Masahiro Tanaka for the fix.
The solution is here https://github.com/microsoft/DeepSpeed/pull/4966?_x_tr_sl=auto&_x_tr_tl=en&_x_tr_hl=en-US#issuecomment-1989671378
and you need deepspeed>=0.13.0
Thanks to Masahiro Tanaka for the fix.
Where is the GSD dataset?
1
#6 opened 9 months ago
by
hangzhang-nlp
upvoted
an
article
9 months ago
Article
Introducing Idefics2: A Powerful 8B Vision-Language Model for the community
•
171
upvoted
a
collection
9 months ago
upvoted
a
paper
9 months ago
liked
a
dataset
10 months ago
authored
a
paper
about 1 year ago
liked
a
model
about 1 year ago
updated
a
Space
over 1 year ago
upvoted
a
paper
over 1 year ago