Upload 4 files

configuration_intern_vit.py

@@ -17,8 +17,10 @@ class InternVisionConfig(PretrainedConfig):
     r"""
     This is the configuration class to store the configuration of a [`InternVisionModel`]. It is used to
     instantiate a vision encoder according to the specified arguments, defining the model architecture.
+
     Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
     documentation from [`PretrainedConfig`] for more information.
+
     Args:
         num_channels (`int`, *optional*, defaults to 3):
             Number of color channels in the input images (e.g., 3 for RGB).
@@ -116,4 +118,3 @@ class InternVisionConfig(PretrainedConfig):
             )
 
         return cls.from_dict(config_dict, **kwargs)
-

configuration_internlm2.py

@@ -29,8 +29,11 @@ class InternLM2Config(PretrainedConfig):
     This is the configuration class to store the configuration of a [`InternLM2Model`]. It is used to instantiate
     an InternLM2 model according to the specified arguments, defining the model architecture. Instantiating a
     configuration with the defaults will yield a similar configuration to that of the InternLM2-7B.
+
     Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
     documentation from [`PretrainedConfig`] for more information.
+
+
     Args:
         vocab_size (`int`, *optional*, defaults to 32000):
             Vocabulary size of the InternLM2 model. Defines the number of different tokens that can be represented by the
@@ -66,6 +69,7 @@ class InternLM2Config(PretrainedConfig):
         tie_word_embeddings(`bool`, *optional*, defaults to `False`):
             Whether to tie weight embeddings
         Example:
+
     """
     model_type = 'internlm2'
     _auto_class = 'AutoConfig'
@@ -144,4 +148,3 @@ class InternLM2Config(PretrainedConfig):
             )
         if rope_scaling_factor is None or not isinstance(rope_scaling_factor, float) or rope_scaling_factor < 1.0:
             raise ValueError(f"`rope_scaling`'s factor field must be a float >= 1, got {rope_scaling_factor}")
-

configuration_internvl_chat.py

@@ -73,6 +73,7 @@ class InternVLChatConfig(PretrainedConfig):
     def to_dict(self):
         """
         Serializes this instance to a Python dictionary. Override the default [`~PretrainedConfig.to_dict`].
+
         Returns:
             `Dict[str, any]`: Dictionary of all the attributes that make up this configuration instance,
         """
@@ -93,4 +94,3 @@ class InternVLChatConfig(PretrainedConfig):
         output['max_dynamic_patch'] = self.max_dynamic_patch
 
         return output
-

modeling_intern_vit.py

@@ -299,6 +299,7 @@ class InternVisionEncoder(nn.Module):
     """
     Transformer encoder consisting of `config.num_hidden_layers` self attention layers. Each layer is a
     [`InternEncoderLayer`].
+
     Args:
         config (`InternConfig`):
             The corresponding vision configuration for the `InternEncoder`.
@@ -426,4 +427,4 @@ class InternVisionModel(PreTrainedModel):
             pooler_output=pooled_output,
             hidden_states=encoder_outputs.hidden_states,
             attentions=encoder_outputs.attentions,
-        )
+        )