Update app.py

app.py

@@ -7,15 +7,8 @@ import spaces
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
 
-DESCRIPTION = """\
-# Gemma 2 2B IT
+DESCRIPTION = """""""
 
-Gemma 2 is Google's latest iteration of open LLMs.
-This is a demo of [`google/gemma-2-2b-it`](https://huggingface.co/google/gemma-2-2b-it), fine-tuned for instruction following.
-For more details, please check [our post](https://huggingface.co/blog/gemma2).
-
-👉 Looking for a larger and more powerful version? Try the 27B version in [HuggingChat](https://huggingface.co/chat/models/google/gemma-2-27b-it) and the 9B version in [this Space](https://huggingface.co/spaces/huggingface-projects/gemma-2-9b-it).
-"""
 
 MAX_MAX_NEW_TOKENS = 2048
 DEFAULT_MAX_NEW_TOKENS = 1024
@@ -23,7 +16,7 @@ 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 = "google/gemma-2-2b-it"
+model_id = "MCES10/code-gen-gemma-2-2b-it"
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 model = AutoModelForCausalLM.from_pretrained(
     model_id,