Upload app.py

app.py

@@ -12,7 +12,7 @@ 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 = "Qwen/Qwen2.5-0.5B-Instruct"
+model_id = "meta-llama/Meta-Llama-3-8B-Instruct"
 model = AutoModelForCausalLM.from_pretrained(
     model_id,
     torch_dtype=torch.float16,
@@ -32,7 +32,7 @@ def generate(
     system_prompt: str,
     max_new_tokens: int = 1024,
     temperature: float = 0.01,
-    top_p: float = 0.01,
+    top_p: float = 1.00,
 ) -> Iterator[str]:
     conversation = []
     if system_prompt:
@@ -98,10 +98,10 @@ chat_interface = gr.Interface(
             minimum=0.05,
             maximum=1.0,
             step=0.01,
-            value=0.01,
+            value=1.0,
         ),          
     ],
-    title="Model testing - Qwen-0.5B-Instruct",
+    title="Model testing - Meta-Llama-3-8B-Instruct",
     description="Provide system settings and a prompt to interact with the model.",
 )