loic-dagnas-sinequa commited on
Commit
824b990
1 Parent(s): a3db8bd

Update README.md (#4)

Browse files

- Update README.md (b4b80975b40e7c34a8440a035f4401b90f1f577f)

Files changed (1) hide show
  1. README.md +8 -8
README.md CHANGED
@@ -35,7 +35,7 @@ The model was trained and tested in the following languages:
35
  - Dutch
36
  - Japanese
37
  - Portuguese
38
- - Chinese
39
 
40
  Besides these languages, basic support can be expected for additional 91 languages that were used during the pretraining
41
  of the base model (see Appendix A of XLM-R paper).
@@ -115,10 +115,10 @@ We evaluated the model on the datasets of the [MIRACL benchmark](https://github.
115
  multilingual capacities. Note that not all training languages are part of the benchmark, so we only report the metrics
116
  for the existing languages.
117
 
118
- | Language | Recall@100 |
119
- |:---------|-----------:|
120
- | French | 0.650 |
121
- | German | 0.528 |
122
- | Spanish | 0.602 |
123
- | Japanese | 0.614 |
124
- | Chinese | 0.680 |
 
35
  - Dutch
36
  - Japanese
37
  - Portuguese
38
+ - Chinese (simplified)
39
 
40
  Besides these languages, basic support can be expected for additional 91 languages that were used during the pretraining
41
  of the base model (see Appendix A of XLM-R paper).
 
115
  multilingual capacities. Note that not all training languages are part of the benchmark, so we only report the metrics
116
  for the existing languages.
117
 
118
+ | Language | Recall@100 |
119
+ |:----------------------|-----------:|
120
+ | French | 0.650 |
121
+ | German | 0.528 |
122
+ | Spanish | 0.602 |
123
+ | Japanese | 0.614 |
124
+ | Chinese (simplified) | 0.680 |