Add Phi-3.5-vision-instruct model

[yatarkan]

Ticket: CVS-152268

[review-notebook-app]

Check out this pull request on 

See visual diffs & provide feedback on Jupyter Notebooks.

---

Powered by ReviewNB

[review-notebook-app]

View / edit / reply to this conversation on ReviewNB

eaidova commented on 2024-09-12T12:33:25Z
----------------------------------------------------------------

>The Phi-3-Vision-128K-Instruct is a lightweight, state-of-the-art open multimodal model built upon datasets which include - synthetic data and filtered publicly available websites - with a focus on very high-quality, reasoning dense data both on text and vision.

Please remove link and change Phi-3-Vision-128k-instruct to Phi-3-vision

[review-notebook-app]

View / edit / reply to this conversation on ReviewNB

eaidova commented on 2024-09-12T12:35:19Z
----------------------------------------------------------------

Line #4.    if not Path("ov_phi3_vision.py").exists():

could you please rename this file per our yesterday agreement (ov_phi3_vision_helper.py)?

[review-notebook-app]

View / edit / reply to this conversation on ReviewNB

eaidova commented on 2024-09-12T15:23:12Z
----------------------------------------------------------------

ov_phi3_model.py script contains helper function for model conversion, please check its content if you interested in conversion details.

ov_phi3_model.py -> ov_phi3_vision_helper.py