fix quant infer and qwen2moe

Former-commit-id: b75d16767f35c36e2cf2aaab8a3844135085bccf
2024-04-09 17:12:59 +08:00
parent 6030a4a720
commit 566d71b7a9
2 changed files with 3 additions and 3 deletions
--- a/src/llmtuner/model/loader.py
+++ b/src/llmtuner/model/loader.py
@@ -109,9 +109,6 @@ def load_model(
    if not is_trainable:
        model.requires_grad_(False)
        model.eval()
-        for param in model.parameters():
-            if param.device.type == "cuda":
-                param.data = param.data.to(model_args.compute_dtype)
    else:
        model.train()