changed settings for cpu workload

app.py

@@ -1,12 +1,11 @@
 from chatBot import create_app
 from threading import Thread
-from flask import render_template
+from flask import redirect, url_for
 app = create_app()
 
-@app.route('/home')
+@app.route('/')
 def index():
-    return render_template('layout.html')
-
+    return redirect(url_for('update.upload'))
 
 def run():
     app.run(host='0.0.0.0', port=7860, debug=False)

chatBot/common/llama.py

@@ -7,7 +7,7 @@ from langchain.embeddings import HuggingFaceInstructEmbeddings
 from langchain.text_splitter import RecursiveCharacterTextSplitter
 from langchain.vectorstores import Chroma
 from pdf2image import convert_from_path
-from transformers import AutoTokenizer, TextStreamer, pipeline
+from transformers import AutoTokenizer, TextStreamer, pipeline, LlamaForCausalLM
 from chatBot.common.pdfToText import loadLatestPdf
 from transformers import LlamaTokenizer
 from langchain.document_loaders import PyPDFLoader
@@ -32,17 +32,21 @@ model_basename = "model"
 
 tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
 
-model = AutoGPTQForCausalLM.from_quantized(
+# model = AutoGPTQForCausalLM.from_quantized(
+#     model_name_or_path,
+#     device_map="auto",
+#     revision="gptq-4bit-128g-actorder_True",
+#     model_basename=model_basename,
+#     use_safetensors=True,
+#     trust_remote_code=True,
+#     inject_fused_attention=False,
+#     device=DEVICE,
+#     quantize_config=None,
+# )
+
+model = LlamaForCausalLM.from_pretrained(
     model_name_or_path,
-    device_map="auto",
-    revision="gptq-4bit-128g-actorder_True",
-    model_basename=model_basename,
     use_safetensors=True,
-    trust_remote_code=True,
-    inject_fused_attention=False,
-    device=DEVICE,
-    quantize_config=None,
-    disable_exllama=True,
 )