Merge pull request #52 from UnicornChan/fix-bug-load-config

Fix: None for load config

Merge pull request #52 from UnicornChan/fix-bug-load-config
Fix: None for load config
0f054fe4 · UnicornChan · GitHub · 1f85db3d · b9f0819a · 0f054fe4
Unverified Commit 0f054fe4 authored Aug 22, 2024 by UnicornChan Committed by GitHub Aug 22, 2024
Show whitespace changes
Inline Side-by-side

Showing with 1 addition and 1 deletion

ktransformers/server/backend/interfaces/ktransformers.py ktransformers/server/backend/interfaces/ktransformers.py +1 -1

No files found.
--- a/ktransformers/server/backend/interfaces/ktransformers.py
+++ b/ktransformers/server/backend/interfaces/ktransformers.py
@@ -25,7 +25,7 @@ class KTransformersInterface(TransformersInterface):

        with torch.device("meta"):
            self.model=custom_models[config.architectures[0]](config)
-        if default_args.optimize_config_path is not None:
+        if default_args.optimize_config_path is None:
            optimize_rule_path = default_optimize_rules[config.architectures[0]]
        else:
            optimize_rule_path = args.optimize_config_path