Update README.md

README.md

@@ -26,7 +26,7 @@ The general architecture and experimental results of BamiBERT can be found in ou
 
 **Please CITE** our paper when BamiBERT is used to help produce published results or is incorporated into other software.
 
-### Model Loading with `transformers` 
+## Model Loading with `transformers` 
 
 ```python
 # Using transformers<=5.5.0
@@ -35,12 +35,15 @@ tokenizer = AutoTokenizer.from_pretrained("Qualcomm-AI-Research/BamiBERT")
 bamibert = AutoModel.from_pretrained("Qualcomm-AI-Research/BamiBERT")
 ```
 
-### Model Fine-tuning
+## Model Fine-tuning
 
-Please find fine-tuning examples for a variety of downstream tasks using [transformers](https://github.com/huggingface/transformers/tree/main/examples/pytorch).
+Please find fine-tuning examples for various downstream tasks, such as token classification (e.g., NER), text classification and question answering, using [transformers](https://github.com/huggingface/transformers/tree/main/examples/pytorch).
 
 ## License/Terms of Use
 This model is released under the BSD 3-Clause Clear license and the Qualcomm responsible AI license: https://www.qualcomm.com/site/responsible-ai-license 
 
 ## Uses
-The model is intended for research purposes.
+The model is intended for research and educational purposes.
+
+## Limitations and Bias
+BamiBERT is not designed for fluent text generation like GPT-style models. It may also suffer from temporal concept drift: although its pre-training corpus (cutoff December 2022) is more recent than those of other general-domain models (pre-2021), it may not reflect current language use. BamiBERT may also be biased toward standard Northern Vietnamese and underperform on Central and Southern dialects.