llama2

app.py

@@ -1,11 +1,13 @@
 import streamlit as st
 from langchain.prompts import PromptTemplate
 from langchain_community.llms import CTransformers
+from transformers import AutoModel
 
 # load the model
 
+TinyLlamaModel = AutoModel.from_pretrained("NousResearch/Llama-2-7b-hf")
 def getLlamaResponse(input_text, no_words, blog_style):
-    llm=CTransformers(model='TheBloke/TinyLlama-1.1B-Chat-v1.0-GGUF/blob/main/tinyllama-1.1b-chat-v1.0.Q8_0.gguf',
+    llm=CTransformers(model=TinyLlamaModel,
         model_type='llama',
         config={'max_new_tokens':256, 'temperature':0.2})