Update configuration_minicpm.py

configuration_minicpm.py

@@ -33,11 +33,8 @@ class MiniCPM3Config(PretrainedConfig):
     This is the configuration class to store the configuration of a [`MiniCPMModel`]. It is used to instantiate an MiniCPM
     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 MiniCPM-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 MiniCPM model. Defines the number of different tokens that can be represented by the
@@ -97,16 +94,12 @@ class MiniCPM3Config(PretrainedConfig):
             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.
-
     ```python
     >>> from transformers import MiniCPMModel, MiniCPMConfig
-
     >>> # Initializing a MiniCPM minicpm-7b style configuration
     >>> configuration = MiniCPMConfig()
-
     >>> # Initializing a model from the minicpm-7b style configuration
     >>> model = MiniCPMModel(configuration)
-
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
@@ -174,7 +167,6 @@ class MiniCPM3Config(PretrainedConfig):
         self.use_cache = use_cache
         self.rope_theta = rope_theta
         self.rope_scaling = rope_scaling
-        self._rope_scaling_validation()
         self.attention_bias = attention_bias
         self.attention_dropout = attention_dropout
         self.scale_emb = scale_emb
@@ -193,25 +185,4 @@ class MiniCPM3Config(PretrainedConfig):
             import flash_attn
             self._attn_implementation = "flash_attention_2"
         except:
-            pass
-
-    def _rope_scaling_validation(self):
-        """
-        Validate the `rope_scaling` configuration.
-        """
-        if self.rope_scaling is None:
-            return
-
-        # if not isinstance(self.rope_scaling, dict) or len(self.rope_scaling) != 2:
-        #     raise ValueError(
-        #         "`rope_scaling` must be a dictionary with with two fields, `type` and `factor`, "
-        #         f"got {self.rope_scaling}"
-        #     )
-        # rope_scaling_type = self.rope_scaling.get("type", None)
-        # rope_scaling_factor = self.rope_scaling.get("factor", None)
-        # if rope_scaling_type is None or rope_scaling_type not in ["linear", "dynamic"]:
-        #     raise ValueError(
-        #         f"`rope_scaling`'s type field must be one of ['linear', 'dynamic'], got {rope_scaling_type}"
-        #     )
-        # 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}")
+            pass