Add application file

app.py

@@ -16,7 +16,10 @@ tokenizer = LlamaTokenizer.from_pretrained("meta-llama/Llama-2-7b-hf", token=acc
 BASE_MODEL = "meta-llama/Llama-2-7b-hf"
 LORA_WEIGHTS = "DSMI/LLaMA-E"
 
-device = "cuda"
+if torch.cuda.is_available():
+    device = "cuda"
+else:
+    device = "cpu"
 
 try:
     if torch.backends.mps.is_available():
@@ -32,7 +35,7 @@ if device == "cuda":
         load_in_8bit=False,
         torch_dtype=torch.float16,
         device_map="auto",
-    ).to('cuda')
+    )
     model = PeftModel.from_pretrained(
         model, LORA_WEIGHTS, torch_dtype=torch.float16, force_download=True
     )
@@ -84,7 +87,7 @@ model.eval()
 if torch.__version__ >= "2":
     model = torch.compile(model)
 
-@spaces.GPU(duration=120)
+
 def evaluate(
     instruction,
     input=None,

requirements.txt

@@ -6,4 +6,4 @@ accelerate
 bitsandbytes
 peft==0.3.0
 scipy
-gradio==4.0.0
+gradio==3.50.0