Fix InternLM2ForCausalLM does not support Flash Attention 2.0 yet

modeling_internlm2.py

@@ -709,6 +709,8 @@ class InternLM2PreTrainedModel(PreTrainedModel):
     supports_gradient_checkpointing = True
     _no_split_modules = ['InternLM2DecoderLayer']
     _skip_keys_device_placement = 'past_key_values'
+    _supports_flash_attn_2 = True
+
 
     def _init_weights(self, module):
         std = self.config.initializer_range