Merge pull request #4080 from MengqingCao/npu

Add npu option for model exporting

Former-commit-id: 07fc67193ef6bcb8e8a392aff0c57a2eb36832bf

src/llamafactory/hparams/model_args.py

@@ -153,9 +153,9 @@ class ModelArguments:
         default=1,
         metadata={"help": "The file shard size (in GB) of the exported model."},
     )
-    export_device: Literal["cpu", "cuda"] = field(
+    export_device: Literal["cpu", "auto"] = field(
         default="cpu",
-        metadata={"help": "The device used in model export, use cuda to avoid addmm errors."},
+        metadata={"help": "The device used in model export, use `auto` to accelerate exporting."},
     )
     export_quantization_bit: Optional[int] = field(
         default=None,