heruberuto commited on
Commit
47934e3
1 Parent(s): 6389a20

Generate README

Browse files
Files changed (1) hide show
  1. README.md +46 -31
README.md CHANGED
@@ -1,47 +1,62 @@
1
- ---
2
- tags:
3
- - generated_from_keras_callback
4
- model-index:
5
- - name: xlm-roberta-large-xnli-csfever
6
- results: []
7
- ---
8
 
9
- <!-- This model card has been generated automatically according to the information Keras had access to. You should
10
- probably proofread and complete it, then remove this comment. -->
11
 
12
- # xlm-roberta-large-xnli-csfever
13
 
14
- This model was trained from scratch on an unknown dataset.
15
- It achieves the following results on the evaluation set:
 
 
 
 
 
 
16
 
 
 
 
 
 
 
17
 
18
- ## Model description
19
 
20
- More information needed
21
 
22
- ## Intended uses & limitations
23
 
24
- More information needed
 
25
 
26
- ## Training and evaluation data
 
27
 
28
- More information needed
29
 
30
- ## Training procedure
 
31
 
32
- ### Training hyperparameters
33
 
34
- The following hyperparameters were used during training:
35
- - optimizer: None
36
- - training_precision: float32
37
 
38
- ### Training results
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
39
 
 
40
 
41
-
42
- ### Framework versions
43
-
44
- - Transformers 4.21.0
45
- - TensorFlow 2.7.1
46
- - Datasets 2.4.0
47
- - Tokenizers 0.12.1
 
1
+ ('---\ndatasets:\n- ctu-aic/csfever\nlanguages:\n- cs\nlicense: cc-by-sa-4.0\ntags:\n- natural-language-inference\n\n---',)
 
 
 
 
 
 
2
 
3
+ # 🦾 xlm-roberta-large-xnli-csfever
4
+ Transformer model for **Natural Language Inference** in ['cs'] languages finetuned on ['ctu-aic/csfever'] datasets.
5
 
6
+ ## 🧰 Usage
7
 
8
+ ### 👾 Using UKPLab `sentence_transformers` `CrossEncoder`
9
+ The model was trained using the `CrossEncoder` API and we recommend it for its usage.
10
+ ```python
11
+ from sentence_transformers.cross_encoder import CrossEncoder
12
+ model = CrossEncoder('ctu-aic/xlm-roberta-large-xnli-csfever')
13
+ scores = model.predict([["My first context.", "My first hypothesis."],
14
+ ["Second context.", "Hypothesis."]])
15
+ ```
16
 
17
+ ### 🤗 Using Huggingface `transformers`
18
+ ```python
19
+ from transformers import AutoModelForSequenceClassification, AutoTokenizer
20
+ model = AutoModelForSequenceClassification.from_pretrained("ctu-aic/xlm-roberta-large-xnli-csfever")
21
+ tokenizer = AutoTokenizer.from_pretrained("ctu-aic/xlm-roberta-large-xnli-csfever")
22
+ ```
23
 
 
24
 
 
25
 
 
26
 
27
+ ## 🌳 Contributing
28
+ Pull requests are welcome. For major changes, please open an issue first to discuss what you would like to change.
29
 
30
+ ## 👬 Authors
31
+ 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: [ullriher@fel.cvut.cz](mailto:ullriher@fel.cvut.cz))
32
 
33
+ The code was codeveloped by the NLP team at Artificial Intelligence Center of CTU in Prague ([AIC](https://www.aic.fel.cvut.cz/)).
34
 
35
+ ## 🔐 License
36
+ [cc-by-sa-4.0](https://choosealicense.com/licenses/cc-by-sa-4.0)
37
 
 
38
 
39
+ ## 💬 Citation
40
+ If you find this repository helpful, feel free to cite our publication:
41
+ ```
42
 
43
+ @article{DBLP:journals/corr/abs-2201-11115,
44
+ author = {Herbert Ullrich and
45
+ Jan Drchal and
46
+ Martin R{'{y}}par and
47
+ Hana Vincourov{'{a}} and
48
+ V{'{a}}clav Moravec},
49
+ title = {CsFEVER and CTKFacts: Acquiring Czech Data for Fact Verification},
50
+ journal = {CoRR},
51
+ volume = {abs/2201.11115},
52
+ year = {2022},
53
+ url = {https://arxiv.org/abs/2201.11115},
54
+ eprinttype = {arXiv},
55
+ eprint = {2201.11115},
56
+ timestamp = {Tue, 01 Feb 2022 14:59:01 +0100},
57
+ biburl = {https://dblp.org/rec/journals/corr/abs-2201-11115.bib},
58
+ bibsource = {dblp computer science bibliography, https://dblp.org}
59
+ }
60
 
61
+ ```
62