Commit
·
d3c3868
1
Parent(s):
e02c7b7
Update README.md
Browse files
README.md
CHANGED
|
@@ -20,38 +20,39 @@ model-index:
|
|
| 20 |
- task:
|
| 21 |
type: text-generation
|
| 22 |
dataset:
|
| 23 |
-
type:
|
| 24 |
-
name: HumanEval (Python)
|
| 25 |
metrics:
|
| 26 |
- name: pass@1
|
| 27 |
type: pass@1
|
| 28 |
-
value: 0.
|
| 29 |
verified: false
|
| 30 |
- name: pass@10
|
| 31 |
type: pass@10
|
| 32 |
-
value: 0.
|
| 33 |
verified: false
|
| 34 |
- name: pass@100
|
| 35 |
type: pass@100
|
| 36 |
-
value: 0.
|
| 37 |
verified: false
|
| 38 |
- task:
|
| 39 |
type: text-generation
|
| 40 |
dataset:
|
| 41 |
type: nuprl/MultiPL-E
|
| 42 |
-
name: MultiPL
|
| 43 |
metrics:
|
| 44 |
- name: pass@1
|
| 45 |
type: pass@1
|
| 46 |
-
value: 0.
|
| 47 |
verified: false
|
| 48 |
- name: pass@10
|
| 49 |
type: pass@10
|
| 50 |
-
value: 0.
|
| 51 |
verified: false
|
| 52 |
- name: pass@100
|
| 53 |
type: pass@100
|
| 54 |
-
value: 0.
|
|
|
|
| 55 |
- task:
|
| 56 |
type: text-generation
|
| 57 |
dataset:
|
|
@@ -60,67 +61,70 @@ model-index:
|
|
| 60 |
metrics:
|
| 61 |
- name: pass@1
|
| 62 |
type: pass@1
|
| 63 |
-
value: 0.
|
| 64 |
verified: false
|
| 65 |
- name: pass@10
|
| 66 |
type: pass@10
|
| 67 |
-
value: 0.
|
| 68 |
verified: false
|
| 69 |
- name: pass@100
|
| 70 |
type: pass@100
|
| 71 |
value: 0.47
|
|
|
|
| 72 |
- task:
|
| 73 |
type: text-generation
|
| 74 |
dataset:
|
| 75 |
-
type:
|
| 76 |
-
name: MBPP (
|
| 77 |
metrics:
|
| 78 |
- name: pass@1
|
| 79 |
type: pass@1
|
| 80 |
-
value: 0.
|
| 81 |
verified: false
|
| 82 |
- name: pass@10
|
| 83 |
type: pass@10
|
| 84 |
-
value: 0.
|
| 85 |
verified: false
|
| 86 |
- name: pass@100
|
| 87 |
type: pass@100
|
| 88 |
-
value: 0.
|
| 89 |
verified: false
|
| 90 |
- task:
|
| 91 |
type: text-generation
|
| 92 |
dataset:
|
| 93 |
type: nuprl/MultiPL-E
|
| 94 |
-
name: MultiPL
|
| 95 |
metrics:
|
| 96 |
- name: pass@1
|
| 97 |
type: pass@1
|
| 98 |
-
value: 0.
|
| 99 |
verified: false
|
| 100 |
- name: pass@10
|
| 101 |
type: pass@10
|
| 102 |
-
value: 0.
|
| 103 |
verified: false
|
| 104 |
- name: pass@100
|
| 105 |
type: pass@100
|
| 106 |
-
value: 0.
|
|
|
|
| 107 |
- task:
|
| 108 |
type: text-generation
|
| 109 |
dataset:
|
| 110 |
type: nuprl/MultiPL-E
|
| 111 |
-
name: MultiPL MBPP (
|
| 112 |
metrics:
|
| 113 |
- name: pass@1
|
| 114 |
type: pass@1
|
| 115 |
-
value: 0.
|
| 116 |
verified: false
|
| 117 |
- name: pass@10
|
| 118 |
type: pass@10
|
| 119 |
-
value: 0.
|
| 120 |
verified: false
|
| 121 |
- name: pass@100
|
| 122 |
type: pass@100
|
| 123 |
-
value: 0.
|
|
|
|
| 124 |
- task:
|
| 125 |
type: text-generation
|
| 126 |
dataset:
|
|
|
|
| 20 |
- task:
|
| 21 |
type: text-generation
|
| 22 |
dataset:
|
| 23 |
+
type: nuprl/MultiPL-E
|
| 24 |
+
name: MultiPL HumanEval (Python)
|
| 25 |
metrics:
|
| 26 |
- name: pass@1
|
| 27 |
type: pass@1
|
| 28 |
+
value: 0.18
|
| 29 |
verified: false
|
| 30 |
- name: pass@10
|
| 31 |
type: pass@10
|
| 32 |
+
value: 0.29
|
| 33 |
verified: false
|
| 34 |
- name: pass@100
|
| 35 |
type: pass@100
|
| 36 |
+
value: 0.49
|
| 37 |
verified: false
|
| 38 |
- task:
|
| 39 |
type: text-generation
|
| 40 |
dataset:
|
| 41 |
type: nuprl/MultiPL-E
|
| 42 |
+
name: MultiPL MBPP (Python)
|
| 43 |
metrics:
|
| 44 |
- name: pass@1
|
| 45 |
type: pass@1
|
| 46 |
+
value: 0.35
|
| 47 |
verified: false
|
| 48 |
- name: pass@10
|
| 49 |
type: pass@10
|
| 50 |
+
value: 0.58
|
| 51 |
verified: false
|
| 52 |
- name: pass@100
|
| 53 |
type: pass@100
|
| 54 |
+
value: 0.77
|
| 55 |
+
verified: false
|
| 56 |
- task:
|
| 57 |
type: text-generation
|
| 58 |
dataset:
|
|
|
|
| 61 |
metrics:
|
| 62 |
- name: pass@1
|
| 63 |
type: pass@1
|
| 64 |
+
value: 0.16
|
| 65 |
verified: false
|
| 66 |
- name: pass@10
|
| 67 |
type: pass@10
|
| 68 |
+
value: 0.27
|
| 69 |
verified: false
|
| 70 |
- name: pass@100
|
| 71 |
type: pass@100
|
| 72 |
value: 0.47
|
| 73 |
+
verified: false
|
| 74 |
- task:
|
| 75 |
type: text-generation
|
| 76 |
dataset:
|
| 77 |
+
type: nuprl/MultiPL-E
|
| 78 |
+
name: MultiPL MBPP (Javascript)
|
| 79 |
metrics:
|
| 80 |
- name: pass@1
|
| 81 |
type: pass@1
|
| 82 |
+
value: 0.28
|
| 83 |
verified: false
|
| 84 |
- name: pass@10
|
| 85 |
type: pass@10
|
| 86 |
+
value: 0.51
|
| 87 |
verified: false
|
| 88 |
- name: pass@100
|
| 89 |
type: pass@100
|
| 90 |
+
value: 0.70
|
| 91 |
verified: false
|
| 92 |
- task:
|
| 93 |
type: text-generation
|
| 94 |
dataset:
|
| 95 |
type: nuprl/MultiPL-E
|
| 96 |
+
name: MultiPL HumanEval (Java)
|
| 97 |
metrics:
|
| 98 |
- name: pass@1
|
| 99 |
type: pass@1
|
| 100 |
+
value: 0.15
|
| 101 |
verified: false
|
| 102 |
- name: pass@10
|
| 103 |
type: pass@10
|
| 104 |
+
value: 0.26
|
| 105 |
verified: false
|
| 106 |
- name: pass@100
|
| 107 |
type: pass@100
|
| 108 |
+
value: 0.41
|
| 109 |
+
verified: false
|
| 110 |
- task:
|
| 111 |
type: text-generation
|
| 112 |
dataset:
|
| 113 |
type: nuprl/MultiPL-E
|
| 114 |
+
name: MultiPL MBPP (Java)
|
| 115 |
metrics:
|
| 116 |
- name: pass@1
|
| 117 |
type: pass@1
|
| 118 |
+
value: 0.28
|
| 119 |
verified: false
|
| 120 |
- name: pass@10
|
| 121 |
type: pass@10
|
| 122 |
+
value: 0.44
|
| 123 |
verified: false
|
| 124 |
- name: pass@100
|
| 125 |
type: pass@100
|
| 126 |
+
value: 0.59
|
| 127 |
+
verified: false
|
| 128 |
- task:
|
| 129 |
type: text-generation
|
| 130 |
dataset:
|