Update README.md

README.md

@@ -1,41 +1,47 @@
+---
+license: apache-2.0
+---
+# Pre-trained Language Model for England and Wales Court of Appeal (Criminal Division) Decisions
 
+## Introduction
 
-# mdeberta-wl-base-es
+The research for understanding the bias in criminal court decisions need the support of natural language processing tools. 
 
-This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on Bailii dataset. This dataset is not available publicly.
+The pre-trained language model has greatly improved the accuracy of text mining in general texts. At present, there is an urgent need for a pre-trained language model specifically for the automatic processing of court decision texts. 
 
-## Model description
+We used the text from the [Bailii website](https://www.bailii.org/ew/cases/EWCA/Crim/) as the training set. Based on the deep language model framework of RoBERTa, we constructed bailii-roberta  pre-training language model by [transformers/run_mlm.py](https://github.com/huggingface/transformers/blob/main/examples/pytorch/language-modeling/run_mlm.py) and [transformers/mlm_wwm](https://github.com/huggingface/transformers/tree/main/examples/research_projects/mlm_wwm). 
 
-More information needed
 
-## Intended uses & limitations
+##  How to use
 
-More information needed
+### Huggingface Transformers 
 
-## Training and evaluation data
+The `from_pretrained` method based on [Huggingface Transformers](https://github.com/huggingface/transformers) can directly obtain bailii-roberta model online. 
 
-More information needed
 
-## Training procedure
+```python
+from transformers import AutoTokenizer, AutoModel
 
-### Training hyperparameters
+tokenizer = AutoTokenizer.from_pretrained("tsantosh7/bailii-roberta")
 
-The following hyperparameters were used during training:
-- learning_rate: 5e-05
-- train_batch_size: 16
-- eval_batch_size: 16
-- seed: 42
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: linear
-- num_epochs: 3.0
+model = AutoModel.from_pretrained("tsantosh7/bailii-roberta")
+```
 
-### Training results
+### Download Models
 
+- The version of the model we provide is `PyTorch`. 
 
+### From Huggingface 
 
-### Framework versions
+- Download directly through Huggingface's official website. 
+- [tsantosh7/bailii-roberta](https://huggingface.co/tsantosh7/Bailii-Roberta/)
 
-- Transformers 4.21.0.dev0
-- Pytorch 1.11.0+cu113
-- Datasets 2.3.3.dev0
-- Tokenizers 0.12.1
+## Disclaimer
+
+- The experimental results presented in the report only show the performance under a specific data set and hyperparameter combination, and cannot represent the essence of each model. The experimental results may change due to the random number of seeds and computing equipment. 
+- **Users can use the model arbitrarily within the scope of the license, but we are not responsible for the direct or indirect losses caused by using the content of the project.** 
+
+
+##  Acknowledgment
+
+- bailii-roberta was trained based on [roberta-base](https://arxiv.org/abs/1907.11692)).