Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add support for phi-3-vision-128k-instruct #36

Merged
merged 11 commits into from
Jun 24, 2024
Prev Previous commit
Next Next commit
remove debug print
  • Loading branch information
Blaizzy authored Jun 24, 2024
commit 20cf225c61fb24abf02efedcd664a6e8cd50b092
1 change: 0 additions & 1 deletion mlx_vlm/models/phi3_v/vision.py
Original file line number Diff line number Diff line change
Expand Up @@ -258,7 +258,6 @@ def __call__(
return self.img_processor.vision_model(
img_embeds, output_hidden_states=output_hidden_states
)
# print(0, txt_embeds.shape, img_embeds.shape, img_sizes.shape)
img_embeds = mx.array(img_embeds)
img_sizes = mx.array(img_sizes)
B = img_embeds.shape[0]
Expand Down
Loading