Update app.py

app.py

@@ -72,14 +72,14 @@ terminators = [
 # indicates the end of a sequence
 
 #model = llama_cpp.Llama(model_path = tinyllama-1.1b-chat-v1.0.Q4_K_M.gguf AutoModelForCausalLM.from_pretrained(llm_model, model_file = "tinyllama-1.1b-chat-v1.0.Q4_K_M.gguf", model_type="llama", gpu_layers=0, config = generation_config)
-model = Llama.from_pretrained(
+model = Llama(
     model_path="./tinyllama-1.1b-chat-v1.0.Q4_K_M.gguf",
     chat_format="llama-2",
     n_gpu_layers = 0,
     temperature=0.75,
     max_tokens=500,
     top_p=0.95,
-    eos_token_id=terminators
+    eos_tokens=terminators
     # callback_manager=callback_manager,
     # verbose=True,  # Verbose is required to pass to the callback manager
     )