ArtifactAI
commited on
Commit
·
de7bd91
1
Parent(s):
b7d5e7f
Update README.md
Browse files
README.md
CHANGED
@@ -170,4 +170,31 @@ from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
|
|
170 |
tokenizer = AutoTokenizer.from_pretrained("Artifact-AI/led_base_16384_billsum_summarization")
|
171 |
|
172 |
model = AutoModelForSeq2SeqLM.from_pretrained("Artifact-AI/led_base_16384_billsum_summarization")
|
173 |
-
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
170 |
tokenizer = AutoTokenizer.from_pretrained("Artifact-AI/led_base_16384_billsum_summarization")
|
171 |
|
172 |
model = AutoModelForSeq2SeqLM.from_pretrained("Artifact-AI/led_base_16384_billsum_summarization")
|
173 |
+
```
|
174 |
+
|
175 |
+
### Results
|
176 |
+
|
177 |
+
| Model | Rouge-1 | Rouge-2 | Rouge-L | Rouge-Lsum |
|
178 |
+
| --- | --- | --- | --- | --- |
|
179 |
+
| LED Large | 47.843 | 26.342 | 34.230 | 41.689 |
|
180 |
+
| LED Base | 47.672 | 26.737 | 34.568 | 41.529 |
|
181 |
+
|
182 |
+
|
183 |
+
[![LED Large](figure/results.png)
|
184 |
+
|
185 |
+
|
186 |
+
The model is trained on the BillSum summarization dataset found [here](https://huggingface.co/datasets/billsum)
|
187 |
+
|
188 |
+
### Test The Model
|
189 |
+
|
190 |
+
Please find a notebook to test the model below:
|
191 |
+
|
192 |
+
[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1TX4IVyvwduDqsok6XuS6i9VIOs9pTXra?usp=sharing)
|
193 |
+
|
194 |
+
## Citing & Authors
|
195 |
+
|
196 |
+
@misc{led_base_16384_billsum_summarization,
|
197 |
+
title={led_base_16384_billsum_summarization},
|
198 |
+
author={Matthew Kenney},
|
199 |
+
year={2023}
|
200 |
+
}
|