mobiuslabsgmbh
/

Llama-3.1-8b-instruct_4bitgs64_hqq

Text Generation

Model card Files Files and versions Community

mobicham commited on Jul 29

Commit

1064316

•

1 Parent(s): 755fa88

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -49,7 +49,7 @@ Then you can use the sample code below:
 import torch
 from transformers import AutoTokenizer
 from hqq.models.hf.base import AutoHQQHFModel
-from hqq.utils.patching import patch_linearlayers, patch_add_quant_config
 from hqq.core.quantize import *
 from hqq.utils.generation_hf import HFGenerator

 import torch
 from transformers import AutoTokenizer
 from hqq.models.hf.base import AutoHQQHFModel
+from hqq.utils.patching import *
 from hqq.core.quantize import *
 from hqq.utils.generation_hf import HFGenerator