Update app.py

app.py

@@ -12,12 +12,12 @@ DEFAULT_MAX_NEW_TOKENS = 1024
 MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "4096"))
 ACCESS_TOKEN = os.getenv("HF_TOKEN", "")
 
-model_id = "bartowski/Mistral-Nemo-Instruct-2407-GGUF"
-filename = "Mistral-Nemo-Instruct-2407-Q6_K_L.gguf"
+model_id = "nvidia/Mistral-NeMo-Minitron-8B-Instruct"
+#filename = "Mistral-Nemo-Instruct-2407-Q6_K_L.gguf"
 
 model = AutoModelForCausalLM.from_pretrained(
     model_id,
-    gguf_file=filename,
+    #gguf_file=filename,
     torch_dtype=torch.float16,
     device_map="auto",
     trust_remote_code=False,
@@ -25,7 +25,7 @@ model = AutoModelForCausalLM.from_pretrained(
 
 tokenizer = AutoTokenizer.from_pretrained(
     model_id,
-    gguf_file=filename,
+    #gguf_file=filename,
     trust_remote_code=False,
     token=ACCESS_TOKEN)
 
@@ -109,7 +109,7 @@ chat_interface = gr.Interface(
             value=0.7,
         ),          
     ],
-    title="Model testing - mistralai/Mistral-Nemo-Instruct-2407",
+    title="Model testing - Mistral-NeMo-Minitron-8B-Instruct",
     description="Provide system settings and a prompt to interact with the model.",
 )