Update README.md

README.md

@@ -123,7 +123,8 @@ inputs = processor.apply_chat_template(
     padding=True,
 )
 
-inputs = {k: v.to("cuda") for k, v in inputs.items()}
+# Remove token_type_ids: HF uses it to enable bidirectional attention for image tokens; molmoweb is trained with causal attention only
+inputs = {k: v.to("cuda") for k, v in inputs.items() if k != "token_type_ids"} 
 
 with torch.inference_mode():
     output = model.generate(**inputs, max_new_tokens=200)