01-ai/Yi

poor text handling

pseudotensor opened this issue · 1 comments

pseudotensor commented

Reminder

  • I have searched the Github Discussion and issues and have not found anything similar to this.

Environment

ubuntu 20
python 3.10
torch 2.1.2
cuda 12.1

Current Behavior

296218150-50101668-0353-43d2-863d-40e845b3cfbb

Expected Behavior

No repetition and description of image's text

Steps to Reproduce

image

prompt:

Describe the image in detail.

Tried many other prompts, same kinds of failures.

Anything Else?

No response

Yimi81 commented

The current version of the model does not have enhancements for OCR capabilities at the moment.