Ripple advertises a 1M context window, but `tokenizer_config.json` declares 131,072 tokens while `config.json` declares 2,097,152. Tokenizer-based clients can consequently validate or truncate inputs at 128Ki.
Set both declared limits to 1,048,576 tokens and state the exact 1Mi limit in the model card.
Validation: both JSON files parse, their context limits agree at 1,048,576, and the diff is limited to those two metadata values and the model-card wording.
