From 4b86522f8a43407ee9906a4a012aefe30f77e0b7 Mon Sep 17 00:00:00 2001
From: Daoyuan Li <94409450+DaoyuanLi2816@users.noreply.github.com>
Date: Mon, 21 Sep 2026 23:24:55 -0700
Subject: [PATCH] fix: align LoRA inference paths with training output

---
 eval_llm.py                 | 2 +-
 scripts/serve_openai_api.py | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/eval_llm.py b/eval_llm.py
index 13b076c..6339711 100755
--- a/eval_llm.py
+++ b/eval_llm.py
@@ -23,7 +23,7 @@ def init_model(args):
         model.load_state_dict(torch.load(ckp, map_location=args.device), strict=True)
         if args.lora_weight != 'None':
             apply_lora(model)
-            load_lora(model, f'./{args.save_dir}/{args.lora_weight}_{args.hidden_size}.pth')
+            load_lora(model, f'./{args.save_dir}/{args.lora_weight}_{args.hidden_size}{moe_suffix}.pth')
     else:
         model = AutoModelForCausalLM.from_pretrained(args.load_from, trust_remote_code=True)
     get_model_params(model, model.config)
diff --git a/scripts/serve_openai_api.py b/scripts/serve_openai_api.py
index e9cf871..09e7fc1 100644
--- a/scripts/serve_openai_api.py
+++ b/scripts/serve_openai_api.py
@@ -40,7 +40,7 @@ def init_model(args):
         model.load_state_dict(torch.load(ckp, map_location=device), strict=True)
         if args.lora_weight != 'None':
             apply_lora(model)
-            load_lora(model, f'../{args.save_dir}/lora/{args.lora_weight}_{args.hidden_size}.pth')
+            load_lora(model, f'../{args.save_dir}/{args.lora_weight}_{args.hidden_size}{moe_suffix}.pth')
     else:
         model = AutoModelForCausalLM.from_pretrained(args.load_from, trust_remote_code=True)
     print(f'MiniMind模型参数量: {sum(p.numel() for p in model.parameters()) / 1e6:.2f} M(illion)')