Update app.py

app.py

@@ -5,7 +5,7 @@ from awq import AutoAWQForCausalLM
 
 model_path = "bragour/Camel-7b-chat-awq"
 
-model  = AutoAWQForCausalLM.from_quantized(model_path, fuse_layers=True, trust_remote_code=False, safetensors=True)
+model = AutoAWQForCausalLM.from_quantized(model_path, fuse_layers=True, trust_remote_code=False, safetensors=True)
 tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=False)
 
 
@@ -17,8 +17,8 @@ def respond(
 ):
     formatted_prompt = f"<s>[INST]{message}[/INST]"
 
-    tokens = tokenizer(formatted_prompt,return_tensors='pt').input_ids.cuda()
-        
+    tokens = tokenizer(formatted_prompt, return_tensors='pt').input_ids.cuda()
+
     # Generate the response from the API
     result = model.generate(
         tokens,
@@ -27,7 +27,7 @@ def respond(
         temperature=temperature,
         top_p=top_p,
     )
-    
+
     response = tokenizer.decode(result[0], skip_special_tokens=True)
 
     return response
@@ -38,7 +38,7 @@ demo = gr.Interface(
     inputs="text",
     outputs=["text"]
 )
-iface.launch(inline = False)
+demo.launch(inline=False)
 
 if __name__ == "__main__":
     demo.launch()