Update app.py

app.py

@@ -9,7 +9,8 @@ from langchain.chains.question_answering import load_qa_chain
 from langchain.prompts import PromptTemplate
 import os
 import json
-from transformers import AutoTokenizer
+
+from transformers import AutoModelForCausalLM, AutoTokenizer, GenerationConfig, TextStreamer
 
 ####CREDIT#####
 #Credit to author (Sri Laxmi) of original code reference: SriLaxmi1993
@@ -19,7 +20,13 @@ from transformers import AutoTokenizer
 os.system("pip install -r requirements.txt")
 
 #some model
-tokenizer = AutoTokenizer.from_pretrained("bofenghuang/vigogne-2-7b-chat")
+#tokenizer = AutoTokenizer.from_pretrained("bofenghuang/vigogne-2-7b-chat")
+model_name_or_path = "bofenghuang/vigogne-2-7b-chat"
+revision = "v2.0"
+
+tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, revision=revision, padding_side="right", use_fast=False)
+model = AutoModelForCausalLM.from_pretrained(model_name_or_path, revision=revision, torch_dtype=torch.float16, device_map="auto")
+
 
 st.set_page_config(page_title="Gemini RAG", layout="wide")