Transformers
Inference Endpoints
DKYoon commited on
Commit
ee61686
·
verified ·
1 Parent(s): 827659f

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +153 -0
README.md ADDED
@@ -0,0 +1,153 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ language:
4
+ - multilingual
5
+ - af
6
+ - am
7
+ - ar
8
+ - az
9
+ - be
10
+ - bg
11
+ - bn
12
+ - ca
13
+ - ceb
14
+ - co
15
+ - cs
16
+ - cy
17
+ - da
18
+ - de
19
+ - el
20
+ - en
21
+ - eo
22
+ - es
23
+ - et
24
+ - eu
25
+ - fa
26
+ - fi
27
+ - fil
28
+ - fr
29
+ - fy
30
+ - ga
31
+ - gd
32
+ - gl
33
+ - gu
34
+ - ha
35
+ - haw
36
+ - hi
37
+ - hmn
38
+ - ht
39
+ - hu
40
+ - hy
41
+ - ig
42
+ - is
43
+ - it
44
+ - iw
45
+ - ja
46
+ - jv
47
+ - ka
48
+ - kk
49
+ - km
50
+ - kn
51
+ - ko
52
+ - ku
53
+ - ky
54
+ - la
55
+ - lb
56
+ - lo
57
+ - lt
58
+ - lv
59
+ - mg
60
+ - mi
61
+ - mk
62
+ - ml
63
+ - mn
64
+ - mr
65
+ - ms
66
+ - mt
67
+ - my
68
+ - ne
69
+ - nl
70
+ - no
71
+ - ny
72
+ - pa
73
+ - pl
74
+ - ps
75
+ - pt
76
+ - ro
77
+ - ru
78
+ - sd
79
+ - si
80
+ - sk
81
+ - sl
82
+ - sm
83
+ - sn
84
+ - so
85
+ - sq
86
+ - sr
87
+ - st
88
+ - su
89
+ - sv
90
+ - sw
91
+ - ta
92
+ - te
93
+ - tg
94
+ - th
95
+ - tr
96
+ - uk
97
+ - und
98
+ - ur
99
+ - uz
100
+ - vi
101
+ - xh
102
+ - yi
103
+ - yo
104
+ - zh
105
+ - zu
106
+ library_name: transformers
107
+ ---
108
+ ## Links for Reference
109
+ - **Repository: https://github.com/kaistAI/LangBridge**
110
+ - **Paper: [LangBridge: Multilingual Reasoning Without Multilingual Supervision](https://arxiv.org/pdf/2401.10695.pdf)**
111
+ - **Point of Contact: dkyoon@kaist.ac.kr**
112
+ # TL;DR
113
+ 🤔LMs good at reasoning are mostly English-centric (MetaMath, Orca 2, etc).
114
+
115
+ 😃Let’s adapt them to solve multilingual tasks. BUT without using multilingual data!
116
+
117
+ LangBridge “bridges” mT5 encoder and the target LM together while utilizing only English data. In test time, LangBridge models can solve multilingual reasoning tasks effectively.
118
+ ![image/png](./figure2.png)
119
+
120
+ # Usage
121
+
122
+ This is the tokenizer used for the encoder models of LinguaBridge. LinguaBridge models require two tokenizers, one for the encoder model and one for the language model. To the best of our knowledge there is no way of uploading two tokenizers for a model. So this seperate repository was created.
123
+
124
+
125
+ Please refer to the [Github repository](https://github.com/kaistAI/LangBridge) for detailed usage examples.
126
+
127
+
128
+ # Related Models
129
+ [Check out other LangBridge models.](https://huggingface.co/collections/kaist-ai/langbridge-65afbbdae50627e40ca58f9a)
130
+
131
+ We have:
132
+ - Llama 2
133
+ - Llemma
134
+ - MetaMath
135
+ - Code Llama
136
+ - Orca 2
137
+
138
+ # Citation
139
+
140
+ If you find the following model helpful, please consider citing our paper!
141
+
142
+ **BibTeX:**
143
+
144
+ ```bibtex
145
+ @misc{yoon2024langbridge,
146
+ title={LangBridge: Multilingual Reasoning Without Multilingual Supervision},
147
+ author={Dongkeun Yoon and Joel Jang and Sungdong Kim and Seungone Kim and Sheikh Shafayat and Minjoon Seo},
148
+ year={2024},
149
+ eprint={2401.10695},
150
+ archivePrefix={arXiv},
151
+ primaryClass={cs.CL}
152
+ }
153
+ ```