Update app.py

app.py

@@ -1,15 +1,15 @@
 import streamlit as st
 from langchain.prompts import PromptTemplate
 from langchain_community.llms import CTransformers
-from ctransformers import AutoModelForCausalLM
 
-# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
-llm1 = AutoModelForCausalLM.from_pretrained("TheBloke/Llama-2-7b-Chat-GGUF", model_file="llama-2-7b-chat.q4_K_M.gguf", model_type="llama", gpu_layers=0)
 
 print(llm("AI is going to"))
 
 def GetLLMResponse(input_text,no_words,blog_type):
-    llm=llm1
+    llm=CTransformers(model="models\llama-2-7b-chat.ggmlv3.q8_0.bin",
+                      model_type='llama',
+                      config={'max_new_tokens':200,
+                              'temperature':0.01})
     
     template=" wtite a blog for {blog_type} on topic of {input_text} in {no_words} words."