feat: Added judgment logic to support training with plain text data.

modeling_minicpmv.py

@@ -77,6 +77,8 @@ class MiniCPMV(MiniCPMVPreTrainedModel):
             all_pixel_values = []
             img_cnt = []
             for pixel_values in pixel_values_list:
+                if len(pixel_values) == 0:
+                    continue
                 img_cnt.append(len(pixel_values))
                 all_pixel_values.extend([i.flatten(end_dim=1).permute(1, 0) for i in pixel_values])