Update README.md
Browse files
README.md
CHANGED
@@ -20,17 +20,17 @@ This is a merge of pre-trained language models created using [mergekit](https://
|
|
20 |
|------------------------------------|-----------------------------------|--------------------------------|
|
21 |
| arc_challenge 0 shot | 47.95 | **51.62** |
|
22 |
| arc_easy 0 shot | 73.44 | **75.25** |
|
23 |
-
| hellaswag 0 shot | 68.27 | **68.52**
|
24 |
| openbookqa 0 shot | **41.6** | 41.4 |
|
25 |
| boolq 0 shot | **79.39** | 79.33 |
|
26 |
| piqa 0 shot | **77.86** | 77.53 |
|
27 |
| winogrande 0 shot | 70.64 | **72.06** |
|
28 |
-
| ifeval 0 shot |
|
29 |
| triviaqa 0 shot | 11.95 | **15.06** |
|
30 |
-
| triviaqa 5 shot EM |
|
31 |
| truthfulqa_mc2 10 shot | 45.89 | **46.52** |
|
32 |
| gsm8k 4 shot EM | **62.4** | 59.67 |
|
33 |
-
| mmlu 5 shot acc |
|
34 |
| commonsense_qa 10 shot acc | **71.17** | 70.76 |
|
35 |
|
36 |
|
|
|
20 |
|------------------------------------|-----------------------------------|--------------------------------|
|
21 |
| arc_challenge 0 shot | 47.95 | **51.62** |
|
22 |
| arc_easy 0 shot | 73.44 | **75.25** |
|
23 |
+
| hellaswag 0 shot | 68.27 | **68.52** |
|
24 |
| openbookqa 0 shot | **41.6** | 41.4 |
|
25 |
| boolq 0 shot | **79.39** | 79.33 |
|
26 |
| piqa 0 shot | **77.86** | 77.53 |
|
27 |
| winogrande 0 shot | 70.64 | **72.06** |
|
28 |
+
| ifeval 0 shot | 41.85 | **44.12** |
|
29 |
| triviaqa 0 shot | 11.95 | **15.06** |
|
30 |
+
| triviaqa 5 shot EM | 33.51 | 33.51 |
|
31 |
| truthfulqa_mc2 10 shot | 45.89 | **46.52** |
|
32 |
| gsm8k 4 shot EM | **62.4** | 59.67 |
|
33 |
+
| mmlu 5 shot acc | 52.96 | **53.39** |
|
34 |
| commonsense_qa 10 shot acc | **71.17** | 70.76 |
|
35 |
|
36 |
|