Update app.py

app.py

@@ -33,12 +33,12 @@ def run_model(report):
 
     # load base LLM model, LoRA params and tokenizer
     model = AutoPeftModelForCausalLM.from_pretrained(
-        "Krooz/placement-classification-mistral-7b-instruct-v1",
+        os.getenv("Model_Repo_ID"),
         low_cpu_mem_usage=True,
         torch_dtype=torch.float16,
-        load_in_4bit=True
+        #load_in_4bit=True
     )
-    tokenizer = AutoTokenizer.from_pretrained("Krooz/placement-classification-mistral-7b-instruct-v1")
+    tokenizer = AutoTokenizer.from_pretrained(os.getenv("Model_Repo_ID"))
     input_ids = tokenizer(prompt, return_tensors="pt", truncation=True).input_ids.cpu()
     
     # inference