limited to 256 token

app.py

@@ -166,7 +166,7 @@ def evaluate(
     top_k: int = 0
     prompt = generate_prompt(instruction, input)
     inputs = tokenizer(prompt, return_tensors="pt")
-    input_ids = inputs["input_ids"].to(device)
+    input_ids = inputs["input_ids"][:256].to(device)
     generation_config = GenerationConfig(
         temperature=temperature,
         top_p=top_p,
@@ -235,7 +235,7 @@ with gr.Blocks(
         with gr.Row():
             with gr.Column():
                 instruction = gr.Textbox(
-                    lines=3, label="Instruction", placeholder="こんにちは"
+                    lines=3, label="Instruction (Pre-Prompt + Instruction + Input is limitted to 256 tokens)", placeholder="こんにちは"
                 )
                 inputs = gr.Textbox(lines=1, label="Input", placeholder="none")
                 with gr.Row():