Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
Vidensogende
/
image-captioning-with-blip
like
0
Image-to-Text
Transformers
PyTorch
google-tensorflow
TensorFlow
Safetensors
blip
image-text-to-text
image-captioning
Inference Endpoints
arxiv:
2201.12086
License:
bsd-3-clause
Model card
Files
Files and versions
Community
Train
Deploy
Use this model
6ea8640
image-captioning-with-blip
6 contributors
History:
19 commits
Vidensogende
fixed merge issues
6ea8640
11 months ago
.gitattributes
1.59 kB
fixed merge issues
11 months ago
README.md
5.6 kB
fixed merge issues
11 months ago
config.json
4.6 kB
Update config.json (#8)
over 1 year ago
handler.py
846 Bytes
added custom handler
11 months ago
model.safetensors
1.88 GB
LFS
Adding `safetensors` variant of this model (#18)
11 months ago
preprocessor_config.json
445 Bytes
Upload processor
almost 2 years ago
pytorch_model.bin
pickle
Detected Pickle imports (4)
"collections.OrderedDict"
,
"torch.FloatStorage"
,
"torch._utils._rebuild_tensor_v2"
,
"torch.LongStorage"
What is a pickle import?
1.88 GB
LFS
Upload BlipForConditionalGeneration
almost 2 years ago
special_tokens_map.json
125 Bytes
Upload processor
almost 2 years ago
tf_model.h5
1.88 GB
LFS
Add TF weights (#7)
over 1 year ago
tokenizer.json
711 kB
Upload processor
almost 2 years ago
tokenizer_config.json
527 Bytes
Update tokenizer_config.json (#11)
over 1 year ago
vocab.txt
232 kB
Upload processor
almost 2 years ago