kevinpro commited on
Commit
4cb2807
1 Parent(s): c5c52b7

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +18 -6
README.md CHANGED
@@ -1,14 +1,26 @@
1
  ---
2
  license: apache-2.0
 
 
 
 
 
3
  ---
4
  ## MAPO: Advancing Multilingual Reasoning through Multilingual Alignment-as-Preference Optimization
5
- see our paper in https://arxiv.org/abs/2401.06838
6
 
 
 
 
 
 
7
 
8
- View the Github Project:
9
  https://github.com/NJUNLP/MAPO
10
 
11
- Multilingual Reasoning Benchmark: https://huggingface.co/spaces/kevinpro/Open-Multilingual-Reasoning-Leaderboard
 
 
 
 
12
 
13
  ## Benchmarks
14
  | System | [MSVAMP](https://huggingface.co/datasets/Mathoctopus/MSVAMP) | [MGSM](https://huggingface.co/datasets/juletxara/mgsm) | [MNumGLUESub](https://huggingface.co/datasets/Mathoctopus/MSVAMP) |
@@ -22,8 +34,8 @@ Multilingual Reasoning Benchmark: https://huggingface.co/spaces/kevinpro/Open-Mu
22
  | **[+ MAPO-DPO(ours)🔥](https://huggingface.co/kevinpro/MathOctopus-MAPO-DPO-7B)** | **57.4** | **41.6** | **50.4** |
23
  | [MetaMathOctopus 7B](https://huggingface.co/kevinpro/MetaMathOctopus-7B) | 53.0 | 45.5 | 39.2 |
24
  | **[+ MAPO-DPO(ours) 👑](https://huggingface.co/kevinpro/MetaMathOctopus-MAPO-DPO-7B)** | **64.7** | **51.6** | **52.9** |
25
- | MistralMathOctopus 7B | 59.0 | 58.0 | 56.8 |
26
- | **+ MAPO-DPO(ours) 👑** | **74.6** | **67.3** | **70.0** |
27
 
28
  | System | [MSVAMP](https://huggingface.co/datasets/Mathoctopus/MSVAMP) | [MGSM](https://huggingface.co/datasets/juletxara/mgsm) | [MNumGLUESub](https://huggingface.co/datasets/Mathoctopus/MSVAMP) |
29
  | ------ | :-------------------------------------------------------------: | :------------------------------------------------------: | :-------------------------------------------------------------: |
@@ -50,4 +62,4 @@ If you find this model helpful, feel free to cite our paper:
50
  archivePrefix={arXiv},
51
  primaryClass={cs.CL}
52
  }
53
- ```
 
1
  ---
2
  license: apache-2.0
3
+ metrics:
4
+ - accuracy
5
+ pipeline_tag: text-generation
6
+ tags:
7
+ - multilingual
8
  ---
9
  ## MAPO: Advancing Multilingual Reasoning through Multilingual Alignment-as-Preference Optimization
 
10
 
11
+ **🔥Our paper**
12
+
13
+ https://arxiv.org/abs/2401.06838
14
+
15
+ **🔥Github Project**
16
 
 
17
  https://github.com/NJUNLP/MAPO
18
 
19
+ **🔥Open Multilingual Reasoning Leaderboard**
20
+
21
+ https://huggingface.co/spaces/kevinpro/Open-Multilingual-Reasoning-Leaderboard
22
+
23
+
24
 
25
  ## Benchmarks
26
  | System | [MSVAMP](https://huggingface.co/datasets/Mathoctopus/MSVAMP) | [MGSM](https://huggingface.co/datasets/juletxara/mgsm) | [MNumGLUESub](https://huggingface.co/datasets/Mathoctopus/MSVAMP) |
 
34
  | **[+ MAPO-DPO(ours)🔥](https://huggingface.co/kevinpro/MathOctopus-MAPO-DPO-7B)** | **57.4** | **41.6** | **50.4** |
35
  | [MetaMathOctopus 7B](https://huggingface.co/kevinpro/MetaMathOctopus-7B) | 53.0 | 45.5 | 39.2 |
36
  | **[+ MAPO-DPO(ours) 👑](https://huggingface.co/kevinpro/MetaMathOctopus-MAPO-DPO-7B)** | **64.7** | **51.6** | **52.9** |
37
+ | [MistralMathOctopus 7B](https://huggingface.co/kevinpro/MistralMathOctopus-7B) | 59.0 | 58.0 | 56.8 |
38
+ | **[+ MAPO-DPO(ours) 👑](https://huggingface.co/kevinpro/MistralMathOctopus-MAPO-DPO-7B)** | **74.6** | **67.3** | **70.0** |
39
 
40
  | System | [MSVAMP](https://huggingface.co/datasets/Mathoctopus/MSVAMP) | [MGSM](https://huggingface.co/datasets/juletxara/mgsm) | [MNumGLUESub](https://huggingface.co/datasets/Mathoctopus/MSVAMP) |
41
  | ------ | :-------------------------------------------------------------: | :------------------------------------------------------: | :-------------------------------------------------------------: |
 
62
  archivePrefix={arXiv},
63
  primaryClass={cs.CL}
64
  }
65
+ ```