Flo Schneider
floschne
AI & ML interests
Multi Modal Information Retrieval and Representation Learning
Recent Activity
updated
a dataset
3 days ago
floschne/gimmick-vvqa
liked
a model
3 days ago
facebook/dinov2-with-registers-giant
Organizations
floschne's activity
File missing
2
#1 opened 25 days ago
by
floschne
Issues when downloading the dataset
2
#1 opened 2 months ago
by
floschne
Question regarding the Stage 1 training procedure
#1 opened 7 months ago
by
floschne
Librarian Bot: Add language metadata for dataset
#1 opened 8 months ago
by
librarian-bot
What processor to use?
9
#4 opened 8 months ago
by
floschne
Which exact version of Llama 2 was used?
1
#1 opened 9 months ago
by
floschne
Which Vision Encoder was used here?
1
#9 opened 10 months ago
by
floschne
Training data details
#8 opened 10 months ago
by
floschne
What does VIP stand for?
3
#1 opened 11 months ago
by
floschne
RuntimeError: Error(s) in loading state_dict for LlavaForConditionalGeneration
2
#2 opened 11 months ago
by
floschne
Why is `beam_search` not enabled in the samples?
2
#10 opened about 1 year ago
by
floschne
Slow inference
#3 opened almost 2 years ago
by
floschne