Text Generation
Transformers
PyTorch
llama
text-generation-inference
Inference Endpoints
compasszzn commited on
Commit
39633d0
β€’
1 Parent(s): 1724e02

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +12 -3
README.md CHANGED
@@ -14,6 +14,7 @@ language:
14
  - fr
15
  - bn
16
  ---
 
17
  ### Introduction
18
 
19
  We introduce πŸ™ MathOctopus, a series of open-source large language models (LLMs) specifically tailored for multilingual math problem-solving. The MathOctopus models are trained on πŸ€— MGSM8KInstruct Dataset, encompassing ten distinct languages.
@@ -49,9 +50,9 @@ Our dataset and models are all available at Huggingface.
49
  |----|---------------------------------------------------------------|---------------------------------------------------------------------------|
50
  | 7B-LLaMA 2 | πŸ™ [MathOctopus-Parallel-7B](https://huggingface.co/Mathoctopus/Parallel_7B) | πŸ™ [MathOctopus-Cross-7B](https://huggingface.co/Mathoctopus/Cross_7B) |
51
  || πŸ™[MathOctopus-Parallel-xRFT-7B](https://huggingface.co/Mathoctopus/Parallel_xRFT_7B)|πŸ™[MathOctopus-Cross-xRFT-7B](https://huggingface.co/Mathoctopus/Cross_xRFT_7B)|
52
- | 13B-LLaMA 2 | πŸ™ [MathOctopus-Parallel-13B] | πŸ™ [MathOctopus-Cross-13B] |
53
- || πŸ™[MathOctopus-Parallel-xRFT-13B](https://huggingface.co/Mathoctopus/Parallel_xRFT_13B/tree/main)|πŸ™[MathOctopus-Cross-xRFT-13B]|
54
- | 33B-LLaMA 1 | πŸ™ [MathOctopus-Parallel-33B] | πŸ™ [MathOctopus-Cross-33B] |
55
  | 70B-LLaMA 2 | Coming soon! | Coming Soon! |
56
 
57
  *-Parallel refers to our model trained with the parallel-training strategy.
@@ -59,7 +60,9 @@ Our dataset and models are all available at Huggingface.
59
  *-Cross refers to our model trained with cross-training strategy.
60
 
61
  *-xRFT means we train the model with multilingual rejection sampling.
 
62
  ### **Overall Results on MGSM**
 
63
  | 7B Model | En | Sw | Zh | Bn | De | Es | Fr | Ja | Ru | Th | Overall |
64
  |:--------------------------------|:--------|:--------|:--------|:--------|:--------|:--------|:--------|:--------|:--------|:--------|:--------|
65
  | MathOctopus<sup>C</sup> | 52.0 | 23.6 | 31.6 | 18.8 | 38.0 | 39.2 | 36.4 | 27.2 | 33.6 | 21.6 | 32.2 |
@@ -83,7 +86,10 @@ Our dataset and models are all available at Huggingface.
83
  | **xRFT**-MathOctopus<sup>C</sup>| 53.6 | 27.6 | 34.4 | 19.2 | 47.2 | 47.6 | 44.8 | 30.8 | 38.8 | 22.8 | 36.7 |
84
  | MathOctopus<sup>P</sup> | 56.4 | 46.8 | 52.0 | 35.2 | 47.2 | 53.2 | 48.0 | 39.2 | 45.6 | 41.2 | 46.5 |
85
  | **xRFT**-MathOctopus<sup>P</sup>| 51.6 | 47.2 | 52.4 | 37.6 | 51.2 | 52.8 | 44.4 | 41.6 | 50.0 | 47.6 | 47.6 |
 
 
86
  ### **Overall Results on MSVAMP**
 
87
  | 7B Model | En | Sw | Zh | Bn | De | Es | Fr | Ja | Ru | Th | Overall |
88
  |:--------------------------------|:--------|:--------|:--------|:--------|:--------|:--------|:--------|:--------|:--------|:--------|:--------|
89
  | MathOctopus<sup>C</sup> | 49.2 | 36.6 | 43.6 | 30.2 | 48.6 | 46.8 | 46.4 | 42.5 | 46.7 | 34.0 | 42.5 |
@@ -107,7 +113,10 @@ Our dataset and models are all available at Huggingface.
107
  | **xRFT**-MathOctopus<sup>C</sup>| 48.1 | 42.8 | 43.6 | 23.3 | 48.7 | 50.0 | 48.9 | 43.4 | 44.6 | 35.5 | 42.9 |
108
  | MathOctopus<sup>P</sup> | 56.4 | 46.8 | 52.0 | 35.2 | 47.2 | 53.2 | 48.0 | 39.2 | 45.6 | 41.2 | 46.5 |
109
  | **xRFT**-MathOctopus<sup>P</sup>| 48.0 | 42.3 | 46.1 | 36.2 | 47.5 | 48.5 | 48.3 | 45.8 | 47.2 | 41.2 | 45.1 |
 
 
110
  ### **MathOctopus in English**
 
111
  | Models | GSM8K | SVAMP |
112
  |:--------------------------------|:--------|:--------|
113
  | LLaMA 2-7B | 42.4 | 38.3 |
 
14
  - fr
15
  - bn
16
  ---
17
+
18
  ### Introduction
19
 
20
  We introduce πŸ™ MathOctopus, a series of open-source large language models (LLMs) specifically tailored for multilingual math problem-solving. The MathOctopus models are trained on πŸ€— MGSM8KInstruct Dataset, encompassing ten distinct languages.
 
50
  |----|---------------------------------------------------------------|---------------------------------------------------------------------------|
51
  | 7B-LLaMA 2 | πŸ™ [MathOctopus-Parallel-7B](https://huggingface.co/Mathoctopus/Parallel_7B) | πŸ™ [MathOctopus-Cross-7B](https://huggingface.co/Mathoctopus/Cross_7B) |
52
  || πŸ™[MathOctopus-Parallel-xRFT-7B](https://huggingface.co/Mathoctopus/Parallel_xRFT_7B)|πŸ™[MathOctopus-Cross-xRFT-7B](https://huggingface.co/Mathoctopus/Cross_xRFT_7B)|
53
+ | 13B-LLaMA 2 | πŸ™ [MathOctopus-Parallel-13B](https://huggingface.co/Mathoctopus/Parallel_13B) | πŸ™ [MathOctopus-Cross-13B](https://huggingface.co/Mathoctopus/Cross_13B) |
54
+ || πŸ™[MathOctopus-Parallel-xRFT-13B](https://huggingface.co/Mathoctopus/Parallel_xRFT_13B)|πŸ™[MathOctopus-Cross-xRFT-13B]|
55
+ | 33B-LLaMA 1 | πŸ™ [MathOctopus-Parallel-33B](https://huggingface.co/Mathoctopus/Parallel_33B) | πŸ™ [MathOctopus-Cross-33B] |
56
  | 70B-LLaMA 2 | Coming soon! | Coming Soon! |
57
 
58
  *-Parallel refers to our model trained with the parallel-training strategy.
 
60
  *-Cross refers to our model trained with cross-training strategy.
61
 
62
  *-xRFT means we train the model with multilingual rejection sampling.
63
+
64
  ### **Overall Results on MGSM**
65
+
66
  | 7B Model | En | Sw | Zh | Bn | De | Es | Fr | Ja | Ru | Th | Overall |
67
  |:--------------------------------|:--------|:--------|:--------|:--------|:--------|:--------|:--------|:--------|:--------|:--------|:--------|
68
  | MathOctopus<sup>C</sup> | 52.0 | 23.6 | 31.6 | 18.8 | 38.0 | 39.2 | 36.4 | 27.2 | 33.6 | 21.6 | 32.2 |
 
86
  | **xRFT**-MathOctopus<sup>C</sup>| 53.6 | 27.6 | 34.4 | 19.2 | 47.2 | 47.6 | 44.8 | 30.8 | 38.8 | 22.8 | 36.7 |
87
  | MathOctopus<sup>P</sup> | 56.4 | 46.8 | 52.0 | 35.2 | 47.2 | 53.2 | 48.0 | 39.2 | 45.6 | 41.2 | 46.5 |
88
  | **xRFT**-MathOctopus<sup>P</sup>| 51.6 | 47.2 | 52.4 | 37.6 | 51.2 | 52.8 | 44.4 | 41.6 | 50.0 | 47.6 | 47.6 |
89
+
90
+
91
  ### **Overall Results on MSVAMP**
92
+
93
  | 7B Model | En | Sw | Zh | Bn | De | Es | Fr | Ja | Ru | Th | Overall |
94
  |:--------------------------------|:--------|:--------|:--------|:--------|:--------|:--------|:--------|:--------|:--------|:--------|:--------|
95
  | MathOctopus<sup>C</sup> | 49.2 | 36.6 | 43.6 | 30.2 | 48.6 | 46.8 | 46.4 | 42.5 | 46.7 | 34.0 | 42.5 |
 
113
  | **xRFT**-MathOctopus<sup>C</sup>| 48.1 | 42.8 | 43.6 | 23.3 | 48.7 | 50.0 | 48.9 | 43.4 | 44.6 | 35.5 | 42.9 |
114
  | MathOctopus<sup>P</sup> | 56.4 | 46.8 | 52.0 | 35.2 | 47.2 | 53.2 | 48.0 | 39.2 | 45.6 | 41.2 | 46.5 |
115
  | **xRFT**-MathOctopus<sup>P</sup>| 48.0 | 42.3 | 46.1 | 36.2 | 47.5 | 48.5 | 48.3 | 45.8 | 47.2 | 41.2 | 45.1 |
116
+
117
+
118
  ### **MathOctopus in English**
119
+
120
  | Models | GSM8K | SVAMP |
121
  |:--------------------------------|:--------|:--------|
122
  | LLaMA 2-7B | 42.4 | 38.3 |