Update app.py

app.py

@@ -10,13 +10,16 @@ tokenizer = AutoTokenizer.from_pretrained("TinyLlama/TinyLlama-1.1B-Chat-v1.0")
 
 # Load base model
 base_model = AutoModelForCausalLM.from_pretrained(
-    "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
-    device_map="auto",
-    torch_dtype=torch.float32
+    "TinyLLaMA/TinyLLaMA-1.1B-Chat-v1.0",  # or your exact model name
+    device_map="auto"
 )
 
 # Load LoRA adapter
-model = PeftModel.from_pretrained(base_model, "lora_adapter", device_map="auto")
+model = PeftModel.from_pretrained(
+    base_model,
+    "lora_adapter",  # folder name
+    device_map="auto"
+)
 
 # Load pipeline
 pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)