Update README.md
Browse files
README.md
CHANGED
|
@@ -13,7 +13,7 @@ bert-chunker-3 is a text chunker based on BertForTokenClassification to predict
|
|
| 13 |
|
| 14 |
Different from [bc-2](https://huggingface.co/tim1900/bert-chunker-2) and [bc](https://huggingface.co/tim1900/bert-chunker), to overcome the data distribution shift, our training data were labeled by a LLM and trainng pipeline was improved, therefore it is **more stable**.
|
| 15 |
|
| 16 |
-
|
| 17 |
|
| 18 |
## Usage
|
| 19 |
Run the following:
|
|
|
|
| 13 |
|
| 14 |
Different from [bc-2](https://huggingface.co/tim1900/bert-chunker-2) and [bc](https://huggingface.co/tim1900/bert-chunker), to overcome the data distribution shift, our training data were labeled by a LLM and trainng pipeline was improved, therefore it is **more stable**.
|
| 15 |
|
| 16 |
+
Updates (2025.5.12): an experimental script that **supports specifying the maximum tokens per chunk** is [here](https://huggingface.co/tim1900/bert-chunker-3.1/blob/main/README.md)
|
| 17 |
|
| 18 |
## Usage
|
| 19 |
Run the following:
|