glm_ocr¶


Model type	`glm_ocr`
Class	`GlmOcrForConditionalGeneration`
Task	`glm-ocr`
Source	`models/glm_ocr.py`

Description¶

GLM-OCR document vision-language model with M-RoPE and cached decoding.

mobius build --model <MODEL_ID> output_dir/

from mobius import build

model = build("<MODEL_ID>")