Update README.md

README.md

@@ -138,8 +138,8 @@ Pre-trained on a sampled mixture of publicly available text corpora. The full da
 ## Limitations
 
 - English only (training corpus is predominantly English).
-- HRM-Text-1B was not trained on code datasets, so the raw checkpoint is expected to be weak at coding tasks. Early third-party code SFT experiments on roughly 1B tokens of code data improved coding benchmark scores from low single digits to around 40–50, suggesting promising adaptation potential, but those results are not part of this checkpoint.
-- Outputs may be inaccurate, biased, or unsafe.
+- HRM-Text-1B was not trained on code datasets, therefore its rather weak performance on coding tasks was expected. Early third-party code SFT experiments on roughly 1B tokens of code data improved coding benchmark scores from low single digits to around 40–50, suggesting promising adaptation potential, but those results are not part of this checkpoint.
+- Outputs may vary under different environments, and may contain inaccuracies, biases, or unsafe contents. 
 
 ## License