Update app.py

app.py

@@ -6,9 +6,9 @@ configObj = ctransformers.Config(stop=["\n", 'User'], context_length=2048)
 config = ctransformers.AutoConfig(config=configObj, model_type='llama')
 config.config.stop = ["\n"]
 
-path_to_llm = os.path.abspath("llama-2-7b-chat.ggmlv3.q4_1.bin")
+# path_to_llm = os.path.abspath("llama-2-7b-chat.ggmlv3.q4_1.bin")
 
-llm = ctransformers.AutoModelForCausalLM.from_pretrained(path_to_llm, config=config)
+llm = ctransformers.AutoModelForCausalLM.from_pretrained("TheBloke/Llama-2-7b-Chat-GGUF", model_file="llama-2-7b-chat.q4_K_M.gguf", config=config)
 
 def complete(prompt, stop=["User", "Assistant"]):
   tokens = llm.tokenize(prompt)
@@ -26,7 +26,7 @@ def complete(prompt, stop=["User", "Assistant"]):
   return output
 
 title = "llama2-7b-chat-ggml"
-description = "This space is an attempt to run the GGML 4 bit quantized version of 'llama2-7b-chat' on a CPU"
+description = "This space is an attempt to run the GGUF 4 bit quantized version of 'llama2-7b-chat' on a CPU"
 
 example_1 = "Write a 7 line poem on AI"
 example_2 = "Tell me a joke"