Update app.py

app.py

@@ -54,20 +54,20 @@ llm_model = "TheBloke/TinyLlama-1.1B-Chat-v1.0-GGUF"
 tokenizer = AutoTokenizer.from_pretrained("TinyLlama/TinyLlama-1.1B-Chat-v1.0")
 #initiate model and tokenizer
 
-generation_config = AutoConfig.from_pretrained(
-    "TheBloke/TinyLlama-1.1B-Chat-v1.0-GGUF",
-    max_new_tokens= 300,
+#generation_config = AutoConfig.from_pretrained(
+#    "TheBloke/TinyLlama-1.1B-Chat-v1.0-GGUF",
+#    max_new_tokens= 300,
   #  do_sample=True,
   #  stream = streamer,
-    top_p=0.95,
-    temperature=0.4,
-    stream = True
+#    top_p=0.95,
+#    temperature=0.4,
+#    stream = True
   #  eos_token_id=terminators
 )
 # send additional parameters to model for generation
 
 #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(
+model = Llama.from_pretrained(
     model_path="./tinyllama-1.1b-chat-v1.0.Q4_K_M.gguf",
     chat_format="llama-2",
     n_gpu_layers = 0,