Update app.py

app.py

@@ -1,10 +1,13 @@
 import gradio as gr
 
+import os
 import torch
+from dotenv import load_dotenv
 from datasets import load_dataset
 from peft import AutoPeftModelForCausalLM
 from transformers import AutoTokenizer, AutoModelForCausalLM
 
+load_dotenv()
 
 def format_instruction(report):
     return """### Instruction: 
@@ -30,12 +33,12 @@ def run_model(report):
 
     # load base LLM model, LoRA params and tokenizer
     model = AutoPeftModelForCausalLM.from_pretrained(
-        Model_Repo_ID,
+        os.getenv('Model_Repo_ID'),
         low_cpu_mem_usage=True,
         torch_dtype=torch.float16,
         load_in_4bit=True,
     )
-    tokenizer = AutoTokenizer.from_pretrained(Model_Repo_ID)
+    tokenizer = AutoTokenizer.from_pretrained(os.getenv('Model_Repo_ID'))
     input_ids = tokenizer(prompt, return_tensors="pt", truncation=True).input_ids.cpu()
     
     # inference