readme

README.md

@@ -7,11 +7,11 @@ library_name: generic
 ---
 
 # Coreference Resolution for Long Documents
-Modified coreference resolution model from [BERT for Coreference Resolution: Baselines and Analysis](https://aclanthology.org/D19-1588/) for handling long documents (~40K words) efficiently (500K words/s on a NVIDIA Tesla V100). This modified model was used in [DAPR: A Benchmark on Document-Aware Passage Retrieval](https://arxiv.org/abs/2305.13915).
+Modified coreference resolution model from [BERT for Coreference Resolution: Baselines and Analysis](https://aclanthology.org/D19-1588/) for handling long documents (~40K words) efficiently (500K words/s on a NVIDIA Tesla V100). The checkpoint is based on AllenNLP's coref-spanbert-large-2021.03.10. This modified model was used in [DAPR: A Benchmark on Document-Aware Passage Retrieval](https://arxiv.org/abs/2305.13915).
 
 ## Usage
 ### API call
-One can call the Hugging's Inference Endpoints API directly: (need your access token from https://huggingface.co/settings/tokens)
+One can call the Hugging's Inference Endpoints API directly: (need your access token from https://huggingface.co/settings/tokens and the loading takes around 6 minutes)
 ```python
 import requests
 import time
@@ -65,6 +65,9 @@ pip install -r requirements.txt
 python local_run.py
 ```
 
+## Evalution
+The evaluation results are
+
 ## Citation
 If you use the repo, feel free to cite our publication [DAPR: A Benchmark on Document-Aware Passage Retrieval](https://arxiv.org/abs/2305.13915):
 ```bibtex