Update README.md

README.md

@@ -10,7 +10,7 @@ base_model:
 ---
 
 - **Repository:** [https://github.com/arijitray1993/mull-tokens]
-- **Paper [optional]:** [https://arxiv.org/abs/2512.10941]
+- **Paper:** [https://arxiv.org/abs/2512.10941]
 
 
 ## How to Get Started with the Model
@@ -31,8 +31,13 @@ We use a custom Qwen2.5 VL model. There is no change to the architecture, just s
 ```
 % pip install qwen-vl-utils[decord]==0.0.8
 
+import importlib
 from transformers import Qwen2_5_VLForConditionalGeneration, AutoProcessor
 
+Qwen2_5_VLForConditionalGeneration = importlib.import_module(
+            'models.mmlatentdiscrete_qwen_vl'
+        ).Qwen2_5_VLForConditionalGeneration
+
 model = Qwen2_5_VLForConditionalGeneration.from_pretrained("array/Qwen2.5-VL-MullGRPO")
 processor = AutoProcessor.from_pretrained(
     "array/Qwen2.5-VL-MullGRPO",