huangzixian
commited on
Commit
·
77d70d5
1
Parent(s):
2039528
update readme
Browse files
README.md
CHANGED
|
@@ -12,6 +12,17 @@
|
|
| 12 |
|
| 13 |
🔥 LLaMAX2-7B-MetaMath demonstrates good multilingual math reasoning capability in all languages, improving the average accuracy by 6.2% across all languages in MGSM dataset.
|
| 14 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15 |
### Model Usage
|
| 16 |
|
| 17 |
Prompt template:
|
|
@@ -45,14 +56,6 @@ two weeks. To find out how many words are in each daily crossword puzzle, we nee
|
|
| 45 |
the total number of words (1050) by the number of days in two weeks (14). So, there are
|
| 46 |
1050/14 = 75 words in each daily crossword puzzle on average. #### The answer is: 75“
|
| 47 |
```
|
| 48 |
-
### Experiments
|
| 49 |
-
We evaluated LLaMAX2-7B-MetaMath on the MGSM dataset. Compared with MetaMath-7B, LLaMAX-7B-MetaMath achieves a leading on both high-resource languages (Hrl.) and low-resource languages (Lrl.).
|
| 50 |
-
|
| 51 |
-
| MGSM | Avg. | Lrl. | Hrl. | Bn | Th | Sw | Ja | Zh | De | Fr | Ru | Es | En |
|
| 52 |
-
|---------------------------|---------|------|--------|--------|------|----|----|------|----|----|------|------|--------|
|
| 53 |
-
| MetaMath-7B (official) | 38.32 | 6.9 | 51.8 | 6.8 | 7.2 |6.8| 36.4 | 38.4 | 55.2|54.4| 52.0 |57.2|68.8|
|
| 54 |
-
| MetaMath-7B (Reproduced) | 38.08 | 6.8 | 51.5 | 6.0 | 10.0 |4.4| 36.4 |42.8|52.8|56.0|48.8|58.8|64.8|
|
| 55 |
-
| LLaMAX2-7B-MetaMath | 44.28 | 25.6 | 52.3 | 26.8 | 24.0 |26.0| 35.6 |42.4|56.8|55.2|53.6|56.8|65.6|
|
| 56 |
|
| 57 |
### Citation
|
| 58 |
if our model helps your work, please cite this paper:
|
|
|
|
| 12 |
|
| 13 |
🔥 LLaMAX2-7B-MetaMath demonstrates good multilingual math reasoning capability in all languages, improving the average accuracy by 6.2% across all languages in MGSM dataset.
|
| 14 |
|
| 15 |
+
### Experiments
|
| 16 |
+
We evaluated LLaMAX2-7B-MetaMath on the MGSM dataset. Compared with MetaMath-7B, LLaMAX-7B-MetaMath achieves a leading on both high-resource languages (Hrl.) and low-resource languages (Lrl.).
|
| 17 |
+
|
| 18 |
+
| MGSM | Avg. | Lrl. | Hrl. | Bn | Th | Sw | Ja | Zh | De | Fr | Ru | Es | En |
|
| 19 |
+
|---------------------------|---------|------|--------|--------|------|----|----|------|----|----|------|------|--------|
|
| 20 |
+
| MetaMath-7B (official) | 38.32 | 6.9 | 51.8 | 6.8 | 7.2 |6.8| 36.4 | 38.4 | 55.2|54.4| 52.0 |57.2|68.8|
|
| 21 |
+
| MetaMath-7B (Reproduced) | 38.08 | 6.8 | 51.5 | 6.0 | 10.0 |4.4| 36.4 |42.8|52.8|56.0|48.8|58.8|64.8|
|
| 22 |
+
| LLaMAX2-7B-MetaMath | 44.28 | 25.6 | 52.3 | 26.8 | 24.0 |26.0| 35.6 |42.4|56.8|55.2|53.6|56.8|65.6|
|
| 23 |
+
|
| 24 |
+
|
| 25 |
+
|
| 26 |
### Model Usage
|
| 27 |
|
| 28 |
Prompt template:
|
|
|
|
| 56 |
the total number of words (1050) by the number of days in two weeks (14). So, there are
|
| 57 |
1050/14 = 75 words in each daily crossword puzzle on average. #### The answer is: 75“
|
| 58 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 59 |
|
| 60 |
### Citation
|
| 61 |
if our model helps your work, please cite this paper:
|