Upload folder using huggingface_hub

custom_generate/generate.py

@@ -88,8 +88,8 @@ def _dola_decoding(
         logits_processor: LogitsProcessorList,
         stopping_criteria: StoppingCriteriaList,
         generation_config: GenerationConfig,
-        synced_gpus: bool,
-        streamer: "BaseStreamer",
+        synced_gpus: bool = False,
+        streamer: "BaseStreamer" = None,
         **model_kwargs,
     ) -> Union[GenerateNonBeamOutput, torch.LongTensor]:
         r"""
@@ -113,7 +113,7 @@ def _dola_decoding(
                 used to tell if the generation loop should stop.
             generation_config ([`~generation.GenerationConfig`]):
                 The generation configuration to be used as parametrization of the decoding method.
-            synced_gpus (`bool`):
+            synced_gpus (`bool`, *optional*, defaults to `False`):
                 Whether to continue running the while loop until max_length (needed to avoid deadlocking with
                 `FullyShardedDataParallel` and DeepSpeed ZeRO Stage 3).
             streamer (`BaseStreamer`, *optional*):