-
Change from rbanfield to openai vit model
-
removed debug statement
-
tensor fix
-
changes from bobs repo to line up text embeddings
-
image payload fix
-
Image instance fix
-
getting closer
-
figured out image issue
-
more debugging
-
fixed stupid mistake
-
added debugging
-
added binary image handling and changed output to be a dict
-
Another GPU test
-
Try enabling GPU if available
-
Code is working
-
continue debugging adventures
-
debugging error not seen locally
-
Copy/paste error
-
"inputs" is required
-
Upload 2 files
Upload a handler.py and requirements.txt to run on inference endpoints
