Update app.py

app.py

@@ -7,8 +7,8 @@ import spaces
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
 
-MAX_MAX_NEW_TOKENS = 4096
-DEFAULT_MAX_NEW_TOKENS = 2048
+MAX_MAX_NEW_TOKENS = 8000
+DEFAULT_MAX_NEW_TOKENS = 4000
 MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "4096"))
 
 DESCRIPTION = """\
@@ -32,7 +32,7 @@ if not torch.cuda.is_available():
 
 
 if torch.cuda.is_available():
-    model_id = "ruggsea/Llama3-stanford-encyclopedia-philosophy-QA"
+    model_id = "ruggsea/Llama3.1-Chat-stanford-encyclopedia-philosophy"
     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