Update app.py

app.py

@@ -12,9 +12,9 @@ DEFAULT_MAX_NEW_TOKENS = 1024
 MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "4096"))
 
 DESCRIPTION = """\
-# Merlinite-7b Chat
+# Hermes-2 Pro 7b Chat
 
-This Space demonstrates model [Merlinite-7b](https://huggingface.co/ibm/merlinite-7b) by IBM, a finetuned Mistral model with 7B parameters for chat instructions.
+This Space demonstrates [Hermes-2 Pro 7b](https://huggingface.co/NousResearch/Hermes-2-Pro-Mistral-7B) by Nous, a finetuned Mistral model with 7B parameters for chat instructions.
 
 """
 
@@ -24,7 +24,7 @@ if not torch.cuda.is_available():
 
 
 if torch.cuda.is_available():
-    model_id = "ibm/merlinite-7b"
+    model_id = "NousResearch/Hermes-2-Pro-Mistral-7B"
     model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", load_in_4bit=True)
     tokenizer = AutoTokenizer.from_pretrained(model_id)
     tokenizer.use_default_system_prompt = False