autoprogrammer
/

deepseekv2lite_densemixer

Model card Files Files and versions

autoprogrammer commited on 24 days ago

Commit

f5ab0b8

·

verified ·

1 Parent(s): 8b42d70

Upload DeepSeekV2Lite DenseMixer model

DeepSeekV2Lite model with DenseMixer architecture

Files changed (1) hide show

modeling_deepseek.py +1 -1

modeling_deepseek.py CHANGED Viewed

@@ -54,7 +54,7 @@ from transformers.utils import (
     replace_return_docstrings,
 )
 from transformers.utils.import_utils import is_torch_fx_available
-from configuration_deepseek import DeepseekV2Config
 import torch.distributed as dist
 import numpy as np

     replace_return_docstrings,
 )
 from transformers.utils.import_utils import is_torch_fx_available
+from .configuration_deepseek import DeepseekV2Config
 import torch.distributed as dist
 import numpy as np