Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
sashakunitsyn
/
vlrm-blip2-opt-2.7b
like
17
Image-to-Text
Transformers
TensorBoard
Safetensors
English
blip-2
visual-question-answering
vision
image-captioning
arxiv:
2404.01911
License:
mit
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Deploy
Use this model
d4d23bb
vlrm-blip2-opt-2.7b
1 contributor
History:
3 commits
sashakunitsyn
Upload only fine-tuned weights
d4d23bb
verified
12 months ago
.gitattributes
Safe
1.52 kB
initial commit
12 months ago
README.md
178 Bytes
Update README.md
12 months ago
vlrm-blip2-opt-2.7b.pt
Safe
pickle
Detected Pickle imports (3)
"torch._utils._rebuild_tensor_v2"
,
"torch.HalfStorage"
,
"collections.OrderedDict"
What is a pickle import?
214 MB
LFS
Upload only fine-tuned weights
12 months ago
vlrm-rs-blip2-opt-2.7b.pt
Safe
pickle
Detected Pickle imports (3)
"torch._utils._rebuild_tensor_v2"
,
"collections.OrderedDict"
,
"torch.HalfStorage"
What is a pickle import?
214 MB
LFS
Upload only fine-tuned weights
12 months ago