microsoft
/

Phi-3.5-vision-instruct

Image-Text-to-Text

text-generation

Model card Files Files and versions Community

Resources

View closed (17)

Make model compatible with Transformers v4.49.0

#39 opened 22 days ago by

Update modeling_phi3_v.py for compatibility with transformers 4.49

#37 opened about 1 month ago by

Update modeling_phi3_v.py

#36 opened 2 months ago by

t-shaurysrivastav

Extend eos_token_id

#35 opened 3 months ago by

RuntimeError: shape mismatch: value tensor of shape [4706, 3072] cannot be broadcast to indexing result of shape [9412, 3072]

#34 opened 5 months ago by

RuntimeError: FlashAttention only support fp16 and bf16 data type with Flash attention2

#33 opened 5 months ago by

Support for base image

#32 opened 6 months ago by

How do I use this model along with HuggingfaceInference ?

#31 opened 6 months ago by

Update processing_phi3_v.py

#30 opened 6 months ago by

Adjust generation verbosity

#29 opened 7 months ago by

Can this model give a pixel bound box of the OCR/object detection?

#27 opened 7 months ago by

Fine tuning Phi-3 for OCR

#26 opened 7 months ago by

Batch inference

#25 opened 7 months ago by

Finetuning script for Phi3.5-Vision

#24 opened 7 months ago by

BOS token in front of every text chunk

#22 opened 8 months ago by

Compatibility and Support for NVIDIA RTX™ 6000 Ada Generation GPU

#20 opened 8 months ago by

Stop Bumping your Models on Huggingface, its getting annoying

#19 opened 8 months ago by

Adding audio support

#17 opened 8 months ago by

What is configuration of demo space?

#15 opened 8 months ago by

Open-Source communities needs Microsoft support

#11 opened 8 months ago by

🍭 Fine-Tuning of Phi3.5-vision-instruct

#9 opened 8 months ago by

Ollama availability

#8 opened 8 months ago by