mlx-community
/

DeepSeek-OCR-8bit

Image-Text-to-Text

vision-language

8-bit precision

Model card Files Files and versions

Resources

View closed (0)

ValueError: [broadcast_shapes] Shapes (1183,1280) and (1182,1280) cannot be broadcast.

#3 opened 10 days ago by

Fail to run the example due to TypeError: 'KVCache' object is not subscriptable

#2 opened 3 months ago by

Repetitive Output with DeepSeek OCR Model - Potential Missing ngram_norepeat Logic

#1 opened 3 months ago by