Update app.py

app.py

@@ -14,7 +14,7 @@ os.environ['PYTORCH_CUDA_ALLOC_CONF'] = 'max_split_size_mb:50'
 device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
 model_name = "Salesforce/xgen-7b-8k-base"
 tokenizer = XgenTokenizer.from_pretrained("./")
-model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto")
+model = AutoModelForCausalLM.from_pretrained(model_name,  torch_dtype=torch.bfloat16, use_flash_attention_2=True, device_map="auto", device_map="auto")
 
 class XgenChatBot:
     def __init__(self, model, tokenizer, system_message="You are Xgen, an AI language model created by Tonic-AI. You are a cautious assistant. You carefully follow instructions. You are helpful and harmless and you follow ethical guidelines and promote positive behavior."):
@@ -47,11 +47,11 @@ class XgenChatBot:
         return response
 
 def gradio_predict(user_message, system_message, max_new_tokens, temperature, top_p, repetition_penalty):
-    Orca_bot.set_system_message(system_message)
-    response = Orca_bot.predict(user_message, temperature, max_new_tokens, top_p, repetition_penalty)
+    Xgen_bot.set_system_message(system_message)
+    response = Xgen_bot.predict(user_message, temperature, max_new_tokens, top_p, repetition_penalty)
     return response
     
-Orca_bot = OrcaChatBot(model, tokenizer)
+Xgen_bot = XgenChatBot(model, tokenizer)
 
 iface = gr.Interface(
     fn=gradio_predict,