lhbonifacio commited on
Commit
79b17d7
1 Parent(s): 4e69123

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -5
README.md CHANGED
@@ -14,9 +14,9 @@ widget:
14
  - text: "Texto de exemplo em português"
15
  inference: false
16
  ---
17
- # mt5-base-multi-msmarco Reranker finetuned on Multi MS MARCO
18
  ## Introduction
19
- mT5-base is a mT5-based model finetuned on a multilingual translated version of MS MARCO passage dataset. This dataset, named Multi MS MARCO, is formed by 12 complete MS MARCO passages collection in 12 different languages.
20
  Further information about the dataset or the translation method can be found on our paper [**mMARCO: A Multilingual Version of MS MARCO Passage Ranking Dataset**](https://arxiv.org/abs/2108.13897) and [mMARCO](https://github.com/unicamp-dl/mMARCO) repository.
21
 
22
  ## Usage
@@ -24,17 +24,17 @@ Further information about the dataset or the translation method can be found on
24
 
25
  from transformers import T5Tokenizer, MT5ForConditionalGeneration
26
 
27
- model_name = 'unicamp-dl/mt5-base-multi-msmarco'
28
  tokenizer = T5Tokenizer.from_pretrained(model_name)
29
  model = MT5ForConditionalGeneration.from_pretrained(model_name)
30
 
31
  ```
32
  # Citation
33
- If you use ptt5-base-msmarco-pt-100k, please cite:
34
 
35
  @misc{bonifacio2021mmarco,
36
  title={mMARCO: A Multilingual Version of MS MARCO Passage Ranking Dataset},
37
- author={Luiz Henrique Bonifacio and Israel Campiotti and Roberto Lotufo and Rodrigo Nogueira},
38
  year={2021},
39
  eprint={2108.13897},
40
  archivePrefix={arXiv},
 
14
  - text: "Texto de exemplo em português"
15
  inference: false
16
  ---
17
+ # mt5-base-mmarco-v1 Reranker finetuned on Multi MS MARCO
18
  ## Introduction
19
+ mt5-base-mmarco-v1 is a mT5-based model fine-tuned on a multilingual translated version of MS MARCO passage dataset. This dataset, named Multi MS MARCO, is formed by 9 complete MS MARCO passages collection in 9 different languages. In the version v1, the datasets were translated using [Helsinki](https://huggingface.co/Helsinki-NLP) NMT models.
20
  Further information about the dataset or the translation method can be found on our paper [**mMARCO: A Multilingual Version of MS MARCO Passage Ranking Dataset**](https://arxiv.org/abs/2108.13897) and [mMARCO](https://github.com/unicamp-dl/mMARCO) repository.
21
 
22
  ## Usage
 
24
 
25
  from transformers import T5Tokenizer, MT5ForConditionalGeneration
26
 
27
+ model_name = 'unicamp-dl/mt5-base-mmarco-v1'
28
  tokenizer = T5Tokenizer.from_pretrained(model_name)
29
  model = MT5ForConditionalGeneration.from_pretrained(model_name)
30
 
31
  ```
32
  # Citation
33
+ If you use mt5-base-mmarco-v1, please cite:
34
 
35
  @misc{bonifacio2021mmarco,
36
  title={mMARCO: A Multilingual Version of MS MARCO Passage Ranking Dataset},
37
+ author={Luiz Henrique Bonifacio and Vitor Jeronymo and Hugo Queiroz Abonizio and Israel Campiotti and Marzieh Fadaee and and Roberto Lotufo and Rodrigo Nogueira},
38
  year={2021},
39
  eprint={2108.13897},
40
  archivePrefix={arXiv},