Update app.py

app.py

@@ -2,13 +2,12 @@ import os
 import gc
 import torch
 import gradio as gr
-from transformers import StoppingCriteria, StoppingCriteriaList
-from transformers import AutoTokenizer, AutoModelForCausalLM
+from transformers import LlamaTokenizer, LlamaForCausalLM, StoppingCriteria, StoppingCriteriaList
 
 # =============================
 # Configuration
 # =============================
-MODEL_PATH = r"Muhammadidrees/JayConverstionalModel"
+MODEL_PATH = r"C:\Users\JAY\Downloads\Chatdoc\ChatDoctor\pretrained"
 MAX_NEW_TOKENS = 200
 TEMPERATURE = 0.5
 TOP_K = 50
@@ -21,7 +20,7 @@ print(f"Loading model from {MODEL_PATH} on {device}...")
 # =============================
 # Load Tokenizer and Model
 # =============================
-tokenizer = AutoTokenizer.from_pretrained(MODEL_PATH, legacy=False)
+tokenizer = LlamaTokenizer.from_pretrained(MODEL_PATH)
 model = LlamaForCausalLM.from_pretrained(
     MODEL_PATH,
     device_map="auto",