Add output_attentions for ChatGLMForSequenceClassification

modeling_chatglm.py

@@ -21,7 +21,7 @@ from transformers.modeling_outputs import (
     SequenceClassifierOutputWithPast,
 )
 from transformers.modeling_utils import PreTrainedModel
-from transformers.utils import logging
+from transformers.utils import logging, is_torch_npu_available
 from transformers.generation.logits_process import LogitsProcessor
 from transformers.generation.utils import LogitsProcessorList, StoppingCriteriaList, GenerationConfig, ModelOutput
 
@@ -29,7 +29,7 @@ from .configuration_chatglm import ChatGLMConfig
 
 # flags required to enable jit fusion kernels
 
-if sys.platform != 'darwin':
+if sys.platform != 'darwin' and not is_torch_npu_available():
     torch._C._jit_set_profiling_mode(False)
     torch._C._jit_set_profiling_executor(False)
     torch._C._jit_override_can_fuse_on_cpu(True)
@@ -40,12 +40,6 @@ logger = logging.get_logger(__name__)
 _CHECKPOINT_FOR_DOC = "THUDM/ChatGLM"
 _CONFIG_FOR_DOC = "ChatGLMConfig"
 
-CHATGLM_6B_PRETRAINED_MODEL_ARCHIVE_LIST = [
-    "THUDM/chatglm3-6b",
-    # See all ChatGLM models at https://huggingface.co/models?filter=chatglm
-]
-
-
 def default_init(cls, *args, **kwargs):
     return cls(*args, **kwargs)
 
@@ -740,6 +734,7 @@ class ChatGLMModel(ChatGLMPreTrainedModel):
             past_key_values: Optional[Tuple[Tuple[torch.Tensor, torch.Tensor], ...]] = None,
             inputs_embeds: Optional[torch.Tensor] = None,
             use_cache: Optional[bool] = None,
+            output_attentions: Optional[bool] = None,
             output_hidden_states: Optional[bool] = None,
             return_dict: Optional[bool] = None,
     ):
@@ -1145,6 +1140,7 @@ class ChatGLMForSequenceClassification(ChatGLMPreTrainedModel):
             inputs_embeds: Optional[torch.LongTensor] = None,
             labels: Optional[torch.LongTensor] = None,
             use_cache: Optional[bool] = None,
+            output_attentions: Optional[bool] = None,
             output_hidden_states: Optional[bool] = None,
             return_dict: Optional[bool] = None,
     ) -> Union[Tuple[torch.Tensor, ...], SequenceClassifierOutputWithPast]:
@@ -1158,6 +1154,7 @@ class ChatGLMForSequenceClassification(ChatGLMPreTrainedModel):
             past_key_values=past_key_values,
             inputs_embeds=inputs_embeds,
             use_cache=use_cache,
+            output_attentions=output_attentions,
             output_hidden_states=output_hidden_states,
             return_dict=return_dict,
         )