Update app.py

app.py

@@ -1,19 +1,14 @@
-import os
 import gradio as gr
-from transformers import AutoModelForCausalLM, AutoTokenizer
+from transformers import AutoTokenizer, AutoModelForCausalLM
+from peft import PeftModel
 import torch
 
-model_name = "jimy26/Chatbot"
+base_model_name = "unsloth/mistral-7b-instruct-v0.3-bnb-4bit"  
+adapter_model = "jimy26/Chatbot"
 
-hf_token = os.getenv("HF_TOKEN")
-tokenizer = AutoTokenizer.from_pretrained(model_name, use_auth_token=hf_token)
-
-model = AutoModelForCausalLM.from_pretrained(
-    model_name,
-    device_map="auto",
-    torch_dtype=torch.float16,
-    use_auth_token=hf_token
-)
+tokenizer = AutoTokenizer.from_pretrained(base_model_name)
+base_model = AutoModelForCausalLM.from_pretrained(base_model_name, device_map="auto", torch_dtype=torch.float16)
+model = PeftModel.from_pretrained(base_model, adapter_model)
 
 def chat(prompt):
     inputs = tokenizer(prompt, return_tensors="pt").to(model.device)