Update app.py

app.py

@@ -8,11 +8,10 @@ import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
 
 DESCRIPTION = """\
-# Llama 3.2 3B Instruct
+# Plutus 8B instruct
 
-Llama 3.2 3B is Meta's latest iteration of open LLMs.
-This is a demo of [`meta-llama/Llama-3.2-3B-Instruct`](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct), fine-tuned for instruction following.
-For more details, please check [our post](https://huggingface.co/blog/llama32).
+Plutus 8B is The Fin AI's latest iteration of open LLMs.
+This is a demo of [`TheFinAI/plutus-8B-instruct`](https://huggingface.co/TheFinAI/plutus-8B-instruct), fine-tuned for instruction following.
 """
 
 MAX_MAX_NEW_TOKENS = 2048
@@ -21,7 +20,7 @@ MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "4096"))
 
 device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
 
-model_id = "meta-llama/Llama-3.2-3B-Instruct"
+model_id = "TheFinAI/plutus-8B-instruct"
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 model = AutoModelForCausalLM.from_pretrained(
     model_id,