update by environment

Author: iosmers

llm/run_pretrain.py

@@ -223,10 +223,6 @@ class ModelArguments:
         default=None,
         metadata={"help": "num_hidden_layers."},
     )
-    use_casual_mask: Optional[bool] = field(
-        default=True,
-        metadata={"help": "whether to use casual mask"},
-    )
 
 
 def create_pretrained_dataset(
@@ -480,7 +476,6 @@ def main():
     config.pp_recompute_interval = model_args.pp_recompute_interval
     config.recompute_use_reentrant = model_args.recompute_use_reentrant
     config.use_recompute = training_args.recompute
-    config.use_casual_mask = model_args.use_casual_mask
 
     config.tensor_parallel_degree = training_args.tensor_parallel_degree
     config.tensor_parallel_rank = training_args.tensor_parallel_rank

paddlenlp/transformers/llama/modeling.py

@@ -115,6 +115,11 @@ def _get_interleave_power_of_2(n):
         )
 
 
+def get_use_casual_mask():
+    """Get the value of the 'USE_CASUAL_MASK' environment variable."""
+    return os.getenv("USE_CASUAL_MASK", "False")
+
+
 def build_alibi_tensor(
     bool_attention_mask: Tensor, num_heads: int, dtype: paddle.dtype, tensor_parallel_degree=1
 ) -> Tensor:
@@ -1532,9 +1537,8 @@ def forward(
         if position_ids is None:
             position_ids = paddle.arange(seq_length, dtype="int64").expand((batch_size, seq_length))
 
-        use_casual_mask = (
-            True if hasattr(self.config, "use_casual_mask") and self.config.use_casual_mask is True else False
-        )
+        use_casual_mask = get_use_casual_mask()
+
         if use_casual_mask:
             attention_mask = None
         else: