Update main.py

main.py

@@ -1,6 +1,8 @@
 from flask import Flask, request, jsonify
 from langchain_community.llms import LlamaCpp
 from sentence_transformers import SentenceTransformer
+from transformers import AutoTokenizer, AutoModel
+
 # cosine_similarity
 import torch
 from torch.nn.functional import cosine_similarity
@@ -19,8 +21,9 @@ llm = LlamaCpp(
     verbose=True,
     n_ctx=4096
 )
+model0 = AutoModel.from_pretrained('sentence-transformers/paraphrase-TinyBERT-L6-v2')
 
-model = SentenceTransformer('paraphrase-TinyBERT-L6-v2')
+model = SentenceTransformer('sentence-transformers/paraphrase-TinyBERT-L6-v2')
 
 file_size = os.stat('Phi-3-mini-4k-instruct-q4.gguf')
 print("model size ====> :", file_size.st_size, "bytes")