add dummy vision and text transformer config (assumed mcore to be fal…

…se) (#9699) (#9827) * add dummy vision and text transformer config (assumed mcore to be false) * Apply isort and black reformatting --------- Signed-off-by: Rohit Jena <[email protected]> Signed-off-by: rohitrango <[email protected]> Co-authored-by: Rohit Jena <[email protected]>
NVIDIA · Jul 24, 2024 · 3885287 · 3885287
1 parent 1711334
commit 3885287
Showing 1 changed file with 2 additions and 0 deletions.
diff --git a/nemo/collections/multimodal/modules/stable_diffusion/encoders/modules.py b/nemo/collections/multimodal/modules/stable_diffusion/encoders/modules.py
@@ -689,6 +689,8 @@ def load_model(self, cfg, state_dict):
             model_cfg=cfg,
             model_parallel_config=ModelParallelConfig(),
             padded_vocab_size=padded_vocab_size,
+            vision_transformer_config=None,  # assumed mcore to be false
+            text_transformer_config=None,
             pre_process=cfg.text.pre_process,
             post_process=cfg.text.post_process,
         )