add back self.max_position_embeddings = config.max_position_embeddings (

huggingface#33550) * add back self.max_position_embeddings = config.max_position_embeddings * fix-copies
amyeroberts · Oct 2, 2024 · cb26ace · cb26ace
1 parent 905948c
commit cb26ace
Show file tree

Hide file tree

Showing 2 changed files with 2 additions and 0 deletions.
diff --git a/src/transformers/models/qwen2/modeling_qwen2.py b/src/transformers/models/qwen2/modeling_qwen2.py
@@ -310,6 +310,7 @@ def __init__(self, config: Qwen2Config, layer_idx: Optional[int] = None):
         self.head_dim = self.hidden_size // self.num_heads
         self.num_key_value_heads = config.num_key_value_heads
         self.num_key_value_groups = self.num_heads // self.num_key_value_heads
+        self.max_position_embeddings = config.max_position_embeddings
         self.rope_theta = config.rope_theta
         self.is_causal = True
         self.attention_dropout = config.attention_dropout

diff --git a/src/transformers/models/qwen2_moe/modeling_qwen2_moe.py b/src/transformers/models/qwen2_moe/modeling_qwen2_moe.py
@@ -388,6 +388,7 @@ def __init__(self, config: Qwen2MoeConfig, layer_idx: Optional[int] = None):
         self.head_dim = self.hidden_size // self.num_heads
         self.num_key_value_heads = config.num_key_value_heads
         self.num_key_value_groups = self.num_heads // self.num_key_value_heads
+        self.max_position_embeddings = config.max_position_embeddings
         self.rope_theta = config.rope_theta
         self.is_causal = True
         self.attention_dropout = config.attention_dropout