Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
TRI-ML
/
prismatic-vlms
like
15
Follow
Toyota Research Institute
92
Image-to-Text
English
computer vision
natural language processing
vision language models
multimodal models
arxiv:
2402.07865
License:
mit
Model card
Files
Files and versions
Community
eed77c6
prismatic-vlms
/
reproduction-llava-v15+7b
/
checkpoints
2 contributors
History:
2 commits
skaramcheti
Upload first-stage-projector.pt
cc07d7e
verified
10 months ago
first-stage-projector.pt
Safe
83.9 MB
LFS
Upload first-stage-projector.pt
10 months ago
latest-checkpoint.pt
Safe
pickle
Detected Pickle imports (3)
"torch.BFloat16Storage"
,
"torch._utils._rebuild_tensor_v2"
,
"collections.OrderedDict"
What is a pickle import?
13.5 GB
LFS
Upload folder using huggingface_hub
11 months ago