Update app.py

app.py

@@ -9,12 +9,13 @@ llm = Llama.from_pretrained(
     repo_id="prithivMLmods/SmolLM2-135M-Instruct-GGUF",
 	filename="SmolLM2-135M-Instruct.Q5_K_M.gguf",
     verbose=False,
+    n_ctx=7000
 )
 
 def generate(
     user_prompt: str,
     system_prompt: str = "You are a helpful assistant.",
-    max_tokens: int = 4000,
+    max_tokens: int = 8192-7000,
     temperature: float = 0.2,
     top_p: float = 0.95,
     top_k: int = 40,
@@ -44,7 +45,7 @@ with gr.Blocks() as demo:
 
     with gr.Accordion("kwargs"):
         with gr.Row(variant="panel"):
-            max_tokens = gr.Number(label="Max tokens", value=512)
+            max_tokens = gr.Number(label="Max tokens", value=1100)
             temperature = gr.Number(label="Temperature", value=0.2)
             top_p = gr.Number(label="Top p", value=0.95)
             top_k = gr.Number(label="Top k", value=40)