.

app.py

@@ -72,15 +72,20 @@ class QwenModelHandler:
                 )
                 
                 # Load with standard precision on CPU
-                self.model = AutoModelForCausalLM.from_pretrained(
-                    model_path,
-                    torch_dtype=torch.float32,
-                    device_map="cpu",
-                    trust_remote_code=True,
-                    # Explicitly disable quantization
-                    load_in_8bit=False,
-                    load_in_4bit=False
-                )
+                from peft import PeftModel
+                from transformers import AutoModelForCausalLM
+
+                base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-Coder-1.5B-Instruct")
+                self.model = PeftModel.from_pretrained(base_model, "tuandunghcmut/Qwen25_Coder_MultipleChoice_v4")
+                # self.model = AutoModelForCausalLM.from_pretrained(
+                #     model_path,
+                #     torch_dtype=torch.float32,
+                #     device_map="cpu",
+                #     trust_remote_code=True,
+                #     # Explicitly disable quantization
+                #     load_in_8bit=False,
+                #     load_in_4bit=False
+                # )
                 
                 if self.tokenizer.pad_token is None and self.tokenizer.eos_token is not None:
                     self.tokenizer.pad_token = self.tokenizer.eos_token

requirements.txt

@@ -4,4 +4,4 @@ transformers
 pyyaml
 accelerate
 peft
-bitsandbytes
+# bitsandbytes

temp.py

@@ -0,0 +1,5 @@
+from peft import PeftModel
+from transformers import AutoModelForCausalLM
+
+base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-Coder-1.5B-Instruct")
+model = PeftModel.from_pretrained(base_model, "tuandunghcmut/Qwen25_Coder_MultipleChoice_v4")