Models
Datasets
Spaces
Buckets
Docs
Enterprise
Pricing
- Website
- Community
- Solutions
Log In
Sign Up

Spaces:

Duplicated from myyim/vlm_google_paligemma2_3b

var2
/

florence-2-image-tagging

Running

App Files Files Community

Fetching metadata from the HF Docker repository...

florence-2-image-tagging

28.4 kB

Ctrl+K

Ctrl+K

2 contributors

History: 9 commits

harellevy's picture

feat: split dense-region caption phrases into atomic tags

d588fd2 7 months ago

static
feat: Florence-2 image analysis endpoint + playground 7 months ago
.gitattributes

1.52 kB
initial commit over 1 year ago
Dockerfile

856 Bytes
feat: Florence-2 image analysis endpoint + playground 7 months ago
README.md

2.94 kB
fix: use beam=3 + max_new_tokens=1024 for Florence-2 tag tasks 7 months ago
app.py

9.09 kB
feat: split dense-region caption phrases into atomic tags 7 months ago
requirements.txt

545 Bytes
fix: pin transformers <4.49 and force eager attn for Florence-2 7 months ago