silver
/

chatglm-6b-slim

Inference Endpoints

Model card Files Files and versions Community

zxdu20 commited on Mar 15, 2023

Commit

0101afd

•

1 Parent(s): c3dece3

Update quantization

Files changed (1) hide show

quantization.py +5 -1

quantization.py CHANGED Viewed

@@ -7,7 +7,11 @@ import base64
 import ctypes
 from typing import List
-from cpm_kernels.kernels.base import LazyKernelCModule, KernelFunction, round_up
 class W8A16Linear(torch.autograd.Function):

 import ctypes
 from typing import List
+try:
+    from cpm_kernels.kernels.base import LazyKernelCModule, KernelFunction, round_up
+except:
+    pass
 class W8A16Linear(torch.autograd.Function):