Card: correct the start_token note — measured numbers do not carry over

README.md

@@ -144,5 +144,5 @@ import `.litertlm` directly from Hugging Face), download `model.litertlm`, impor
 
 The bundle's `LlmMetadata start_token` held the literal string `"None"`. This tokenizer has no BOS, and the LiteRT-LM engine resolved that string to a real vocabulary token — so every prompt began with the word `None`, which the model was never trained on. The start token has been removed.
 
-**Metadata-only change**: every tokenizer and TFLite section is byte-identical to the previous file (verified by sha256 per section), so quality and speed are unchanged and the measured numbers on this card still stand — only the file's own sha256 differs.
+**Metadata-only change**: every section of the bundle except the `LlmMetadata` block is byte-identical to the previous file (verified by sha256 per section), so the weights, the graph and the tokenizer are unchanged and the speed and memory numbers on this card still describe exactly this file — only the file's own sha256 differs. What changed is the input: the token stream the model reads for a given conversation can differ from the previous file's, and it now matches this model's own reference chat stream. Greedy decoding can turn on a single token, so an individual answer can differ from the previous file in either direction. Unless a row says otherwise, the accuracy figures on this card were measured on the previous file and have not been re-measured on this one. If you downloaded before 2026-08-28, re-download.