changes to run on cpu

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, LlamaForCausalLM
+from transformers import AutoTokenizer, TextStreamer, pipeline, AutomodelForCausalLM
 from chatBot.common.pdfToText import loadLatestPdf
 from transformers import LlamaTokenizer
 from langchain.document_loaders import PyPDFLoader
@@ -44,10 +44,10 @@ tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
 #     quantize_config=None,
 # )
 
-model = LlamaForCausalLM.from_pretrained(
-    model_name_or_path,
-    use_safetensors=True,
-)
+model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
+                                             device_map="auto",
+                                             trust_remote_code=False,
+                                             revision="main")
 
 
 DEFAULT_SYSTEM_PROMPT = """