Update app.py

app.py

@@ -3,34 +3,22 @@ import asyncio
 import json
 import os
 import pickle
-import torch
-from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline, GenerationConfig
 from langchain_huggingface import HuggingFaceEmbeddings
 from langchain_community.vectorstores import FAISS
 from langchain_core.prompts import PromptTemplate
 from langchain_community.document_loaders import PDFMinerLoader, CSVLoader, JSONLoader
 from langchain.text_splitter import SentenceTransformersTokenTextSplitter
+from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
 
-# Define the model and tokenizer
-MODEL_NAME = "TheBloke/Llama-2-13B-chat-GPTQ"
+MODEL_NAME = "TheBloke/Llama-2-13B"
 
-tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME, use_fast=True)
-model = AutoModelForCausalLM.from_pretrained(
-    MODEL_NAME, torch_dtype=torch.float16, trust_remote_code=True, device_map="auto"
-)
-
-generation_config = GenerationConfig.from_pretrained(MODEL_NAME)
-generation_config.max_new_tokens = 1024
-generation_config.temperature = 0.0001
-generation_config.top_p = 0.95
-generation_config.do_sample = True
-generation_config.repetition_penalty = 1.15
+tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
+model = AutoModelForCausalLM.from_pretrained(MODEL_NAME, device_map="cpu")
 
 text_pipeline = pipeline(
     "text-generation",
     model=model,
-    tokenizer=tokenizer,
-    generation_config=generation_config,
+    tokenizer=tokenizer
 )
 
 # Define the prompt template