Update app.py

app.py

@@ -1,16 +1,23 @@
 import gradio as gr
-import torch
+# import torch
 import transformers
-from transformers import AutoTokenizer
+# from transformers import AutoTokenizer
 from langchain import LLMChain, HuggingFacePipeline, PromptTemplate
 import os
+from ctransformers import AutoModelForCausalLM, AutoTokenizer
+
+model = AutoModelForCausalLM.from_pretrained("marella/gpt-2-ggml", hf=True)
+tokenizer = AutoTokenizer.from_pretrained(model)
 
 access_token = os.getenv("Llama2")
 
 def greet(text):
 
-    model = "meta-llama/Llama-2-7b-hf"
-    tokenizer = AutoTokenizer.from_pretrained(model, token=access_token)
+    model = AutoModelForCausalLM.from_pretrained("marella/gpt-2-ggml", hf=True)
+    tokenizer = AutoTokenizer.from_pretrained(model)
+    
+    # model = "meta-llama/Llama-2-7b-hf"
+    # tokenizer = AutoTokenizer.from_pretrained(model, token=access_token)
     
     pipeline = transformers.pipeline(
     "text-generation",