Large modular logic refactoring

examples/modular-transformers/configuration_my_new_model.py

@@ -1,9 +1,9 @@
-#           🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
-#               This file was automatically generated from <path_to_modular_file.py>.
-#         Do NOT edit this file manually as any edits will be overwritten by the generation of
-#         the file from the modular. If any change should be done, please apply the change to the
-#                           modular_xxx.py file directly. One of our CI enforces this
-#           🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
+#                🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
+#           This file was automatically generated from examples/modular-transformers/modular_my_new_model.py.
+#               Do NOT edit this file manually as any edits will be overwritten by the generation of
+#             the file from the modular. If any change should be done, please apply the change to the
+#                          modular_my_new_model.py file directly. One of our CI enforces this.
+#                🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
 
 from ...configuration_utils import PretrainedConfig
 from ...modeling_rope_utils import rope_config_validation
@@ -158,6 +158,13 @@ def __init__(
         new_param=0,
         **kwargs,
     ):
+        super().__init__(
+            pad_token_id=pad_token_id,
+            bos_token_id=bos_token_id,
+            eos_token_id=eos_token_id,
+            tie_word_embeddings=tie_word_embeddings,
+            **kwargs,
+        )
         self.vocab_size = vocab_size
         self.max_position_embeddings = max_position_embeddings
         self.hidden_size = hidden_size
@@ -187,11 +194,3 @@ def __init__(
             self.rope_scaling["rope_type"] = self.rope_scaling["type"]
         rope_config_validation(self)
         self.new_param = new_param
-
-        super().__init__(
-            pad_token_id=pad_token_id,
-            bos_token_id=bos_token_id,
-            eos_token_id=eos_token_id,
-            tie_word_embeddings=tie_word_embeddings,
-            **kwargs,
-        )

examples/modular-transformers/configuration_my_new_model2.py

@@ -1,116 +1,16 @@
-#           🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
-#               This file was automatically generated from <path_to_modular_file.py>.
-#         Do NOT edit this file manually as any edits will be overwritten by the generation of
-#         the file from the modular. If any change should be done, please apply the change to the
-#                           modular_xxx.py file directly. One of our CI enforces this
-#           🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
+#                🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
+#           This file was automatically generated from examples/modular-transformers/modular_my_new_model2.py.
+#               Do NOT edit this file manually as any edits will be overwritten by the generation of
+#             the file from the modular. If any change should be done, please apply the change to the
+#                          modular_my_new_model2.py file directly. One of our CI enforces this.
+#                🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
 
 from ...configuration_utils import PretrainedConfig
 from ...modeling_rope_utils import rope_config_validation
 
 
 class MyNewModel2Config(PretrainedConfig):
     r"""
-    This is the configuration class to store the configuration of a [`MyNewModel2Model`]. It is used to instantiate an MyNewModel2
-    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 MyNewModel2-7B.
-
-    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 MyNewModel2 model. Defines the number of different tokens that can be represented by the
-            `inputs_ids` passed when calling [`MyNewModel2Model`]
-        hidden_size (`int`, *optional*, defaults to 4096):
-            Dimension of the hidden representations.
-        intermediate_size (`int`, *optional*, defaults to 11008):
-            Dimension of the MLP representations.
-        num_hidden_layers (`int`, *optional*, defaults to 32):
-            Number of hidden layers in the Transformer decoder.
-        num_attention_heads (`int`, *optional*, defaults to 32):
-            Number of attention heads for each attention layer in the Transformer decoder.
-        num_key_value_heads (`int`, *optional*):
-            This is the number of key_value heads that should be used to implement Grouped Query Attention. If
-            `num_key_value_heads=num_attention_heads`, the model will use Multi Head Attention (MHA), if
-            `num_key_value_heads=1` the model will use Multi Query Attention (MQA) otherwise GQA is used. When
-            converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed
-            by meanpooling all the original heads within that group. For more details checkout [this
-            paper](https://arxiv.org/pdf/2305.13245.pdf). If it is not specified, will default to
-            `num_attention_heads`.
-        hidden_act (`str` or `function`, *optional*, defaults to `"silu"`):
-            The non-linear activation function (function or string) in the decoder.
-        max_position_embeddings (`int`, *optional*, defaults to 2048):
-            The maximum sequence length that this model might ever be used with. MyNewModel2 1 supports up to 2048 tokens,
-            MyNewModel2 2 up to 4096, CodeMyNewModel2 up to 16384.
-        initializer_range (`float`, *optional*, defaults to 0.02):
-            The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
-        rms_norm_eps (`float`, *optional*, defaults to 1e-06):
-            The epsilon used by the rms normalization layers.
-        use_cache (`bool`, *optional*, defaults to `True`):
-            Whether or not the model should return the last key/values attentions (not used by all models). Only
-            relevant if `config.is_decoder=True`.
-        pad_token_id (`int`, *optional*):
-            Padding token id.
-        bos_token_id (`int`, *optional*, defaults to 1):
-            Beginning of stream token id.
-        eos_token_id (`int`, *optional*, defaults to 2):
-            End of stream token id.
-        pretraining_tp (`int`, *optional*, defaults to 1):
-            Experimental feature. Tensor parallelism rank used during pretraining. Please refer to [this
-            document](https://huggingface.co/docs/transformers/main/perf_train_gpu_many#tensor-parallelism) to
-            understand more about it. This value is necessary to ensure exact reproducibility of the pretraining
-            results. Please refer to [this issue](https://github.com/pytorch/pytorch/issues/76232).
-        tie_word_embeddings (`bool`, *optional*, defaults to `False`):
-            Whether to tie weight embeddings
-        rope_theta (`float`, *optional*, defaults to 10000.0):
-            The base period of the RoPE embeddings.
-        rope_scaling (`Dict`, *optional*):
-            Dictionary containing the scaling configuration for the RoPE embeddings. NOTE: if you apply new rope type
-            and you expect the model to work on longer `max_position_embeddings`, we recommend you to update this value
-            accordingly.
-            Expected contents:
-                `rope_type` (`str`):
-                    The sub-variant of RoPE to use. Can be one of ['default', 'linear', 'dynamic', 'yarn', 'longrope',
-                    'my_new_model23'], with 'default' being the original RoPE implementation.
-                `factor` (`float`, *optional*):
-                    Used with all rope types except 'default'. The scaling factor to apply to the RoPE embeddings. In
-                    most scaling types, a `factor` of x will enable the model to handle sequences of length x *
-                    original maximum pre-trained length.
-                `original_max_position_embeddings` (`int`, *optional*):
-                    Used with 'dynamic', 'longrope' and 'my_new_model23'. The original max position embeddings used during
-                    pretraining.
-                `attention_factor` (`float`, *optional*):
-                    Used with 'yarn' and 'longrope'. The scaling factor to be applied on the attention
-                    computation. If unspecified, it defaults to value recommended by the implementation, using the
-                    `factor` field to infer the suggested value.
-                `beta_fast` (`float`, *optional*):
-                    Only used with 'yarn'. Parameter to set the boundary for extrapolation (only) in the linear
-                    ramp function. If unspecified, it defaults to 32.
-                `beta_slow` (`float`, *optional*):
-                    Only used with 'yarn'. Parameter to set the boundary for interpolation (only) in the linear
-                    ramp function. If unspecified, it defaults to 1.
-                `short_factor` (`List[float]`, *optional*):
-                    Only used with 'longrope'. The scaling factor to be applied to short contexts (<
-                    `original_max_position_embeddings`). Must be a list of numbers with the same length as the hidden
-                    size divided by the number of attention heads divided by 2
-                `long_factor` (`List[float]`, *optional*):
-                    Only used with 'longrope'. The scaling factor to be applied to long contexts (<
-                    `original_max_position_embeddings`). Must be a list of numbers with the same length as the hidden
-                    size divided by the number of attention heads divided by 2
-                `low_freq_factor` (`float`, *optional*):
-                    Only used with 'my_new_model23'. Scaling factor applied to low frequency components of the RoPE
-                `high_freq_factor` (`float`, *optional*):
-                    Only used with 'my_new_model23'. Scaling factor applied to high frequency components of the RoPE
-        attention_bias (`bool`, *optional*, defaults to `False`):
-            Whether to use a bias in the query, key, value and output projection layers during self-attention.
-        attention_dropout (`float`, *optional*, defaults to 0.0):
-            The dropout ratio for the attention probabilities.
-        mlp_bias (`bool`, *optional*, defaults to `False`):
-            Whether to use a bias in up_proj, down_proj and gate_proj layers in the MLP layers.
-        head_dim (`int`, *optional*):
-            The attention head dimension. If None, it will default to hidden_size // num_heads
     This is the configuration class to store the configuration of a [`GemmaModel`]. It is used to instantiate an Gemma
     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 Gemma-7B.
@@ -121,7 +21,6 @@ class MyNewModel2Config(PretrainedConfig):
         vocab_size (`int`, *optional*, defaults to 256000):
             Vocabulary size of the Gemma model. Defines the number of different tokens that can be represented by the
             `inputs_ids` passed when calling [`GemmaModel`]
-
     ```python
     >>> from transformers import GemmaModel, GemmaConfig
     >>> # Initializing a Gemma gemma-7b style configuration

examples/modular-transformers/configuration_new_model.py

@@ -1,9 +1,9 @@
-#           🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
-#               This file was automatically generated from <path_to_modular_file.py>.
-#         Do NOT edit this file manually as any edits will be overwritten by the generation of
-#         the file from the modular. If any change should be done, please apply the change to the
-#                           modular_xxx.py file directly. One of our CI enforces this
-#           🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
+#                🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
+#           This file was automatically generated from examples/modular-transformers/modular_new_model.py.
+#               Do NOT edit this file manually as any edits will be overwritten by the generation of
+#             the file from the modular. If any change should be done, please apply the change to the
+#                          modular_new_model.py file directly. One of our CI enforces this.
+#                🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
 # Example where we only want to overwrite the defaults of an init
 
 from ...configuration_utils import PretrainedConfig
@@ -104,6 +104,13 @@ def __init__(
         attention_dropout=0.0,
         **kwargs,
     ):
+        super().__init__(
+            pad_token_id=pad_token_id,
+            bos_token_id=bos_token_id,
+            eos_token_id=eos_token_id,
+            tie_word_embeddings=tie_word_embeddings,
+            **kwargs,
+        )
         self.vocab_size = vocab_size
         self.max_position_embeddings = max_position_embeddings
         self.hidden_size = hidden_size
@@ -121,14 +128,6 @@ def __init__(
         self.attention_bias = attention_bias
         self.attention_dropout = attention_dropout
 
-        super().__init__(
-            pad_token_id=pad_token_id,
-            bos_token_id=bos_token_id,
-            eos_token_id=eos_token_id,
-            tie_word_embeddings=tie_word_embeddings,
-            **kwargs,
-        )
-
     @property
     def num_heads(self):
         return self.num_attention_heads