Create README.md

README.md

@@ -0,0 +1,81 @@
+---
+# For reference on model card metadata, see the spec: https://github.com/huggingface/hub-docs/blob/main/modelcard.md?plain=1
+# Doc / guide: https://huggingface.co/docs/hub/model-cards
+{}
+---
+
+<!-- # Model Card for Model ID -->
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+<!-- This modelcard aims to be a base template for new models. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/modelcard_template.md?plain=1). -->
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+The Longformer-Encoder-Decoder (LED) model is designed to address the challenge of summarizing lengthy English texts, particularly legal documents. Utilizing a local-global attention mechanism, LED is capable of handling longer input sequences efficiently, making it highly suitable for legal document summarization tasks.
+
+- **Developed by:** Duc Dinh Chu
+- **Model type:** LED
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** MIT
+- **Finetuned from model [optional]:** allenai/led-base-16384
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+The model can be directly used for summarizing lengthy legal documents, extracting key information while reducing the overall length of the text.
+
+## How to Get Started with the Model
+
+```python
+from transformers import LongformerForSequenceClassification, LongformerTokenizer
+
+tokenizer = LongformerTokenizer.from_pretrained('')
+model = LongformerForSequenceClassification.from_pretrained('')
+
+inputs = tokenizer("Document text to summarize", return_tensors="pt")
+outputs = model(**inputs)
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+The model is trained on the BillSum dataset, which includes structured and domain-specific legal texts from the US Congress and California state bills.
+
+### Training Procedure
+
+#### Preprocessing [optional]
+
+The texts are preprocessed to extract relevant sections and ensure consistency in formatting before being fed into the model.
+
+#### Training Hyperparameters
+
+Training regime: fp32
+Learning rate: 5e-5
+Epochs: 5
+Batch size: [More Information Needed]
+
+## Citation
+
+**BibTeX:**
+
+@misc{duc2023led,
+  author = {Chu Đình Đức},
+  title = {Longformer-Encoder-Decoder for Legal Document Summarization},
+  year = {2023},
+  publisher = {Hugging Face},
+  howpublished = {\url{https://huggingface.co/models/duc2023led}}
+}