diff --git a/server/text_generation_server/models/__init__.py b/server/text_generation_server/models/__init__.py index abab3486..db58d6bf 100644 --- a/server/text_generation_server/models/__init__.py +++ b/server/text_generation_server/models/__init__.py @@ -327,7 +327,7 @@ def get_model( ) elif sharded: raise NotImplementedError( - FLASH_ATT_ERROR_MESSAGE.format("Sharded Golden Gate") + FLASH_ATT_ERROR_MESSAGE.format("Sharded Gemma") ) else: return CausalLM(