fixup

src/transformers/models/qwen2_moe/configuration_qwen2_moe.py

@@ -20,10 +20,6 @@
 
 logger = logging.get_logger(__name__)
 
-QWEN2MOE_PRETRAINED_CONFIG_ARCHIVE_MAP = {
-    "Qwen/Qwen1.5-MoE-A2.7B": "https://huggingface.co/Qwen/Qwen1.5-MoE-A2.7B/resolve/main/config.json",
-}
-
 
 class Qwen2MoeConfig(PretrainedConfig):
     r"""
@@ -151,10 +147,6 @@ def __init__(
         self.sliding_window = sliding_window
         self.max_window_layers = max_window_layers
 
-        # for backward compatibility
-        if num_key_value_heads is None:
-            num_key_value_heads = num_attention_heads
-
         self.num_key_value_heads = num_key_value_heads
         self.hidden_act = hidden_act
         self.initializer_range = initializer_range

src/transformers/models/qwen2_moe/modeling_qwen2_moe.py

@@ -56,11 +56,6 @@
 _CHECKPOINT_FOR_DOC = "Qwen/Qwen1.5-MoE-A2.7B"
 _CONFIG_FOR_DOC = "Qwen2MoeConfig"
 
-QWEN2MOE_PRETRAINED_MODEL_ARCHIVE_LIST = [
-    "Qwen/Qwen1.5-MoE-A2.7B",
-    # See all Qwen2 models at https://huggingface.co/models?filter=qwen2
-]
-
 
 # Copied from transformers.models.mixtral.modeling_mixtral.load_balancing_loss_func
 def load_balancing_loss_func(
@@ -1492,6 +1487,7 @@ def _reorder_cache(past_key_values, beam_idx):
     """,
     QWEN2MOE_START_DOCSTRING,
 )
+# Copied from transformers.models.llama.modeling_llama.LlamaForSequenceClassification with Llama->Qwen2Moe, LLAMA->QWEN2MOE
 class Qwen2MoeForSequenceClassification(Qwen2MoePreTrainedModel):
     def __init__(self, config):
         super().__init__(config)