Update modeling_deepseekv2.py

modeling_deepseekv2.py

@@ -34,10 +34,14 @@ from torch.nn import BCEWithLogitsLoss, CrossEntropyLoss, MSELoss
 from transformers.activations import ACT2FN
 from transformers.cache_utils import Cache, DynamicCache
 from transformers.modeling_attn_mask_utils import _prepare_4d_causal_attention_mask
-from transformers.models.llama.modeling_llama import (
-    LlamaAttention,
-    LlamaFlashAttention2
-)
+try:
+    from transformers.models.llama.modeling_llama import LlamaAttention
+except:
+    LlamaAttention = None
+try:
+    from transformers.models.llama.modeling_llama import LlamaFlashAttention2
+except:
+    LlamaFlashAttention2 = None
 from transformers.modeling_outputs import (
     BaseModelOutputWithPast,
     CausalLMOutputWithPast,