llm_layer_config_bugfix (#406)

Signed-off-by: Zhang, Weiwei1 <[email protected]> Co-authored-by: Wenhua Cheng <[email protected]>
intel · Jan 7, 2025 · 7714796 · 7714796
1 parent bf8d68d
commit 7714796
Showing 1 changed file with 0 additions and 1 deletion.
diff --git a/auto_round/script/llm.py b/auto_round/script/llm.py
@@ -400,7 +400,6 @@ def tune(args):
                     f"{n} will not be quantized due to its shape not being divisible by 32,"
                     " resulting in an exporting issue to autogptq")
 
-    layer_config = {}
     not_quantize_layer_names = get_fp_layer_names(model, args.fp_layers)
     for name in not_quantize_layer_names:
         layer_config[name] = {"bits": 16}