Update app.py

app.py

@@ -2,21 +2,26 @@ import gradio as gr
 import fitz  # PyMuPDF
 import torch
 from transformers import AutoTokenizer, AutoModelForCausalLM
+
 from langchain_community.vectorstores import Chroma
 from langchain_community.embeddings import HuggingFaceEmbeddings
 from langchain_text_splitters import RecursiveCharacterTextSplitter
 import os
 from dotenv import load_dotenv
+# Load model directly
+
+tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-2-7b-chat-hf")
+model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-2-7b-chat-hf")
 
 # Load environment variables
 load_dotenv()
 # hf_api_key = os.getenv("HF_TOKEN")
 
-model_name = "openai-community/gpt2"
+#model_name = "openai-community/gpt2"
 # model_name = "google/gemma-2-9b"
 
-tokenizer = AutoTokenizer.from_pretrained(model_name)
-model = AutoModelForCausalLM.from_pretrained(model_name)  # ,use_auth_token=hf_api_key)
+#tokenizer = AutoTokenizer.from_pretrained(model_name)
+#model = AutoModelForCausalLM.from_pretrained(model_name)  # ,use_auth_token=hf_api_key)
 
 
 def get_llm_response(input_prompt, content, prompt):