Upload model

config.json

@@ -49,6 +49,7 @@
     "max_length": 20,
     "max_position_embeddings": 2048,
     "min_length": 0,
+    "mlp_bias": false,
     "model_type": "llama",
     "no_repeat_ngram_size": 0,
     "num_attention_heads": 12,
@@ -217,5 +218,5 @@
   "model_type": "vision-encoder-decoder",
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.40.2"
+  "transformers_version": "4.42.3"
 }

generation_config.json

@@ -3,5 +3,5 @@
   "bos_token_id": 1,
   "eos_token_id": 2,
   "pad_token_id": 4,
-  "transformers_version": "4.40.2"
+  "transformers_version": "4.42.3"
 }

modelling_uniformer.py

@@ -373,6 +373,7 @@ class MultiUniFormerWithProjectionHead(UniFormerPreTrainedModel):
         pixel_values: Optional[torch.Tensor] = None,
         output_hidden_states: Optional[bool] = None,
         return_dict: Optional[bool] = None,
+        output_attentions: Optional[bool] = None,
     ) -> Union[Tuple, ModelOutput]:
 
         return_dict = return_dict if return_dict is not None else self.config.use_return_dict