updated README

README.md

@@ -1,3 +1,63 @@
 ---
 license: apache-2.0
 ---
+
+# rrivera1849/LUAR-CRUD
+
+Author Style Representations using [LUAR](https://aclanthology.org/2021.emnlp-main.70.pdf).
+
+This particular model was trained on a subsample of the [Pushshift](https://arxiv.org/abs/2001.08435) dataset for comments published between January 2015 and October 2019 by authors publishing at least 100 comments during that period.
+
+## Usage
+
+```python
+from transformers import AutoModel, AutoTokenizer
+
+tokenizer = AutoTokenizer.from_pretrained("rrivera1849/LUAR-CRUD")
+model = AutoModel.from_pretrained("rrivera1849/LUAR-CRUD")
+
+# we embed `episodes`, a colletion of documents presumed to come from an author
+# NOTE: make sure that `episode_length` consistent across `episode`
+batch_size = 3
+episode_length = 16
+text = [
+    ["Foo"] * episode_length,
+    ["Bar"] * episode_length,
+    ["Zoo"] * episode_length,
+]
+text = [j for i in text for j in i]
+tokenized_text = tokenizer(
+    text, 
+    max_length=32,
+    padding="max_length", 
+    truncation=True,
+    return_tensors="pt"
+)
+# inputs size: (batch_size, episode_length, max_token_length)
+tokenized_text["input_ids"] = tokenized_text["input_ids"].reshape(batch_size, episode_length, -1)
+tokenized_text["attention_mask"] = tokenized_text["attention_mask"].reshape(batch_size, episode_length, -1)
+print(tokenized_text["input_ids"].size())       # torch.Size([3, 16, 32])
+print(tokenized_text["attention_mask"].size())  # torch.Size([3, 16, 32])
+
+out = model(**tokenized_text)
+print(out.size())   # torch.Size([3, 512])
+```
+
+## Citing & Authors
+
+If you find this model helpful, feel free to cite our [publication](https://aclanthology.org/2021.emnlp-main.70.pdf).
+
+```
+@inproceedings{uar-emnlp2021,
+  author    = {Rafael A. Rivera Soto and Olivia Miano and Juanita Ordonez and Barry Chen and Aleem Khan and Marcus Bishop and Nicholas Andrews},
+  title     = {Learning Universal Authorship Representations},
+  booktitle = {EMNLP},
+  year      = {2021},
+}
+```
+
+## License
+
+LUAR is distributed under the terms of the Apache License (Version 2.0).
+
+All new contributions must be made under the Apache-2.0 licenses.