Generate README

README.md

@@ -1,47 +1,67 @@
 ---
+datasets:
+- ctkfacts
+- squad2
+languages:
+- cs
+license: cc-by-sa-4.0
 tags:
-- generated_from_keras_callback
-model-index:
-- name: xlm-roberta-large-squad2-ctkfacts
-  results: []
----
-
-<!-- This model card has been generated automatically according to the information Keras had access to. You should
-probably proofread and complete it, then remove this comment. -->
-
-# xlm-roberta-large-squad2-ctkfacts
-
-This model was trained from scratch on an unknown dataset.
-It achieves the following results on the evaluation set:
-
-
-## Model description
-
-More information needed
-
-## Intended uses & limitations
-
-More information needed
-
-## Training and evaluation data
-
-More information needed
-
-## Training procedure
-
-### Training hyperparameters
-
-The following hyperparameters were used during training:
-- optimizer: None
-- training_precision: float32
-
-### Training results
-
+- natural-language-inference
 
+---
 
-### Framework versions
+# 🦾 xlm-roberta-large-squad2-ctkfacts
+
+## 🧰 Usage
+
+### 🤗 Using Huggingface `transformers`
+```python
+from transformers import AutoModelForSequenceClassification, AutoTokenizer
+model = AutoModelForSequenceClassification.from_pretrained("ctu-aic/xlm-roberta-large-squad2-ctkfacts")
+tokenizer = AutoTokenizer.from_pretrained("ctu-aic/xlm-roberta-large-squad2-ctkfacts")
+```
+
+### 👾 Using UKPLab `sentence_transformers` `CrossEncoder`
+The model was trained using the `CrossEncoder` API and we recommend it for its usage.
+```python
+from sentence_transformers.cross_encoder import CrossEncoder
+model = CrossEncoder('ctu-aic/xlm-roberta-large-squad2-ctkfacts')
+scores = model.predict([["My first context.", "My first hypothesis."],  
+                        ["Second context.", "Hypothesis."]])
+```
+
+## 🌳 Contributing
+Pull requests are welcome. For major changes, please open an issue first to discuss what you would like to change.
+
+## 👬 Authors
+The model was trained and uploaded by **[ullriher](https://udb.fel.cvut.cz/?uid=ullriher&sn=&givenname=&_cmd=Hledat&_reqn=1&_type=user&setlang=en)** (e-mail: [[email protected]](mailto:[email protected]))
+
+The code was codeveloped by the NLP team at Artificial Intelligence Center of CTU in Prague ([AIC](https://www.aic.fel.cvut.cz/)).
+
+## 🔐 License
+[cc-by-sa-4.0](https://choosealicense.com/licenses/cc-by-sa-4.0)
+
+## 💬 Citation
+If you find this model helpful, feel free to cite our publication:
+```
+
+@article{DBLP:journals/corr/abs-2201-11115,
+  author    = {Jan Drchal and
+               Herbert Ullrich and
+               Martin R{'{y}}par and
+               Hana Vincourov{'{a}} and
+               V{'{a}}clav Moravec},
+  title     = {CsFEVER and CTKFacts: Czech Datasets for Fact Verification},
+  journal   = {CoRR},
+  volume    = {abs/2201.11115},
+  year      = {2022},
+  url       = {https://arxiv.org/abs/2201.11115},
+  eprinttype = {arXiv},
+  eprint    = {2201.11115},
+  timestamp = {Tue, 01 Feb 2022 14:59:01 +0100},
+  biburl    = {https://dblp.org/rec/journals/corr/abs-2201-11115.bib},
+  bibsource = {dblp computer science bibliography, https://dblp.org}
+}
+
+```
 
-- Transformers 4.21.0
-- TensorFlow 2.7.1
-- Datasets 2.4.0
-- Tokenizers 0.12.1