unum-cloud/uform
Pocket-Sized Multimodal AI for content understanding and generation across multilingual texts, images, and 🔜 video, up to 5x faster than OpenAI CLIP and LLaVA 🖼️ & 🖋️
PythonApache-2.0
Issues
- 1
- 1
Request for iOS demo.
#67 opened by yujinqiu - 0
Porting JavaScript package to browser
#84 opened by ashvardanian - 0
ONNX Runtime crashes on exit (JavaScript)
#83 opened by ashvardanian - 2
- 3
how can I decode image feature to text?
#77 opened by zshnb - 4
No module named 'uform.models'
#79 opened by ake020675 - 5
README example now invalid
#69 opened by ppbrown - 1
- 1
Problem with Batch Input
#72 opened by afsaneh-ebrahimi - 3
ModuleNotFoundError: No module named 'uform.gen_model'; 'uform' is not a package
#63 opened by karthikra - 1
Caption for Driver's License is incorrect
#61 opened by rxjx - 2
CLIP for Voice
#51 opened by chadbrewbaker - 1
- 1
- 0
Additional dependencies?
#55 opened by Zetaphor - 9
CoreML FP16 model
#50 opened by laclouis5 - 3
How to cite your work
#43 opened by Shubodh - 4
Can not load multilingual model. (ERROR in huggingface transformers library)
#27 opened by javiabellan - 2
Bug: can't load unum-cloud/uform-vl-english
#28 opened by beaugunderson - 0
RPC implementation
#21 opened by ashvardanian - 4
CoreML Model
#7 opened by sandkoan - 2
Releasing training dataset
#5 opened by skull8888888 - 1
Training code?
#6 opened by ScottishFold007