Update app.py

app.py

@@ -6,17 +6,12 @@ import torch
 # Load the model and tokenizer with 4-bit quantization
 @st.cache_resource
 def load_model():
-    tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2-7B")
+    tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen-7B", trust_remote_code=True)
     model = AutoModelForCausalLM.from_pretrained(
-        "Qwen/Qwen2-7B",
+        "Qwen/Qwen-7B",
         load_in_4bit=True,
         device_map="auto",
-        quantization_config=bnb.QuantizationConfig(
-            load_in_4bit=True,
-            bnb_4bit_use_double_quant=True,
-            bnb_4bit_quant_type="nf4",
-            bnb_4bit_compute_dtype=torch.float16
-        )
+        trust_remote_code=True  # Allows custom code execution
     )
     return tokenizer, model