Update app.py

app.py

@@ -1,8 +1,6 @@
 import os
 from transformers import AutoTokenizer
 from optimum.intel.openvino import OVModelForCausalLM
-from generation_utils import run_generation, estimate_latency, reset_textbox, get_special_token_id
-from config import SUPPORTED_LLM_MODELS
 import gradio as gr
 from threading import Thread
 from time import perf_counter
@@ -11,9 +9,14 @@ from transformers import TextIteratorStreamer
 import numpy as np
 
 # Model configuration and loading
-model_dir = "phi-2/INT8_compressed_weights"
+model_dir = "C:/Users/KIIT/OneDrive/Desktop/INTEL/phi-2/INT8_compressed_weights"
 model_name = "susnato/phi-2"
-model_configuration = SUPPORTED_LLM_MODELS["phi-2"]
+model_configuration = {
+    "prompt_template": "{instruction}",
+    "toeknizer_kwargs": {},
+    "response_key": "### Response",
+    "end_key": "### End"
+}
 ov_config = {"PERFORMANCE_HINT": "LATENCY", "NUM_STREAMS": "1", "CACHE_DIR": ""}
 
 tokenizer = AutoTokenizer.from_pretrained(model_name)
@@ -199,4 +202,3 @@ def main():
 
 if __name__ == "__main__":
     main()
-