Update app.py

app.py

@@ -12,12 +12,12 @@ DEFAULT_MAX_NEW_TOKENS = 512
 MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "4096"))
 
 DESCRIPTION = """\
-# Chat with Patched Mixture of Experts (MoE) Model
+# Chat with Patched Coder
 """
 
 LICENSE = """\
 ---
-This space is powered by the patched-mix-4x7B model, which was created by [patched](https://patched.codes).
+This space is powered by the patched-coder-7b model, which was created by [patched](https://patched.codes).
 """
 
 if not torch.cuda.is_available():
@@ -25,7 +25,7 @@ if not torch.cuda.is_available():
 
 
 if torch.cuda.is_available():
-    model_id = "Qwen/CodeQwen1.5-7B-Chat"
+    model_id = "patched-codes/patched-coder-7b"
     model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", load_in_4bit=True)
     tokenizer = AutoTokenizer.from_pretrained(model_id)
     tokenizer.padding_side = 'right'