Update app.py

app.py

@@ -13,20 +13,20 @@ total_count=0
 MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "4096"))
 
 DESCRIPTION = """\
-# DeepSeek-6.7B-Chat
+# DeepSeek-33B-Chat
 
-This Space demonstrates model [DeepSeek-Coder](https://huggingface.co/deepseek-ai/deepseek-coder-6.7b-instruct) by DeepSeek, a code model with 6.7B parameters fine-tuned for chat instructions.
+This Space demonstrates model [DeepSeek-Coder](https://huggingface.co/deepseek-ai/deepseek-coder-33b-instruct) by DeepSeek, a code model with 33B parameters fine-tuned for chat instructions.
 """
 
-# if not torch.cuda.is_available():
-#     DESCRIPTION += "\n<p>Running on CPU 🥶 This demo does not work on CPU.</p>"
+if not torch.cuda.is_available():
+    DESCRIPTION += "\n<p>Running on CPU 🥶 This demo does not work on CPU.</p>"
 
 
-# if torch.cuda.is_available():
-#     model_id = "deepseek-ai/deepseek-coder-33b-instruct"
-#     model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")
-#     tokenizer = AutoTokenizer.from_pretrained(model_id)
-#     tokenizer.use_default_system_prompt = False
+if torch.cuda.is_available():
+    model_id = "deepseek-ai/deepseek-coder-33b-instruct"
+    model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")
+    tokenizer = AutoTokenizer.from_pretrained(model_id)
+    tokenizer.use_default_system_prompt = False