sync configuration_deepseek.py with upstream

configuration_deepseek.py

@@ -82,11 +82,6 @@ class DeepseekV3Config(PretrainedConfig):
             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/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):
@@ -141,8 +136,6 @@ class DeepseekV3Config(PretrainedConfig):
         first_k_dense_replace = 3,
         norm_topk_prob = True,
         scoring_func = 'sigmoid',
-        aux_loss_alpha = 0.001,
-        seq_aux = True,
         hidden_act="silu",
         max_position_embeddings=4096,
         initializer_range=0.02,
@@ -151,7 +144,6 @@ class DeepseekV3Config(PretrainedConfig):
         pad_token_id=None,
         bos_token_id=0,
         eos_token_id=1,
-        pretraining_tp=1,
         tie_word_embeddings=False,
         rope_theta=10000.0,
         rope_scaling=None,
@@ -184,8 +176,6 @@ class DeepseekV3Config(PretrainedConfig):
         self.first_k_dense_replace = first_k_dense_replace
         self.norm_topk_prob = norm_topk_prob
         self.scoring_func = scoring_func
-        self.aux_loss_alpha = aux_loss_alpha
-        self.seq_aux = seq_aux
         # for backward compatibility
         if num_key_value_heads is None:
             num_key_value_heads = num_attention_heads
@@ -194,7 +184,6 @@ class DeepseekV3Config(PretrainedConfig):
         self.hidden_act = hidden_act
         self.initializer_range = initializer_range
         self.rms_norm_eps = rms_norm_eps
-        self.pretraining_tp = pretraining_tp
         self.use_cache = use_cache
         self.rope_theta = rope_theta
         self.rope_scaling = rope_scaling