Update README.md

README.md

@@ -3,7 +3,7 @@ license: cc-by-nc-sa-4.0
 pipeline_tag: fill-mask
 arxiv: 2210.05529
 language: en
-thumbnail: https://raw.githubusercontent.com/coastalcph/hierarchical-transformers/main/data/figures/hat_encoder.png
+thumbnail: https://github.com/coastalcph/hierarchical-transformers/raw/main/data/figures/hat_encoder.png
 tags:
 - long-documents
 datasets:
@@ -19,7 +19,7 @@ model-index:
 
 This is a Hierarchical Attention Transformer (HAT) model as presented in [An Exploration of Hierarchical Attention Transformers for Efficient Long Document Classification (Chalkidis et al., 2022)](https://arxiv.org/abs/2210.05529). 
 
-The model has been warm-started re-using the weights of RoBERTa [(Liu et al., 2019)](https://arxiv.org/abs/1907.11692), and continued pre-trained for MLM in long sequences following the paradigm of Longformer released by [Beltagy et al. (2020)](https://arxiv.org/abs/2004.05150). It supports sequences of length up to 4,096.
+The model has been warm-started re-using the weights of RoBERTa (Liu et al., 2019), and continued pre-trained for MLM in long sequences following the paradigm of Longformer released by Beltagy et al. (2020). It supports sequences of length up to 4,096.
 
 HAT uses hierarchical attention, which is a combination of segment-wise and cross-segment attention operations. You can think of segments as paragraphs or sentences.
 
@@ -40,7 +40,7 @@ tokenizer = AutoTokenizer.from_pretrained("kiddothe2b/hierarchical-transformer-b
 mlm_model = AutoModelforForMaskedLM("kiddothe2b/hierarchical-transformer-base-4096", trust_remote_code=True)
 ```
 
-You can also fine-tun it for SequenceClassification, SequentialSentenceClassification, and MultipleChoice down-stream tasks:
+You can also fine-tune it for SequenceClassification, SequentialSentenceClassification, and MultipleChoice down-stream tasks:
 
 ```python
 from transformers import AutoTokenizer, AutoModelforSequenceClassification
@@ -103,7 +103,7 @@ If you use HAT in your research, please cite [An Exploration of Hierarchical Att
 
 ```
 @misc{chalkidis-etal-2022-hat,
-  url = {https://arxiv.org/abs/xxx},
+  url = {https://arxiv.org/abs/2210.05529},
   author = {Chalkidis, Ilias and Dai, Xiang and Fergadiotis, Manos and Malakasiotis, Prodromos and Elliott, Desmond},
   title = {An Exploration of Hierarchical Attention Transformers for Efficient Long Document Classification},
   publisher = {arXiv},