Update README.md
Browse files
README.md
CHANGED
@@ -36,6 +36,28 @@ model-index:
|
|
36 |
type: pass@1
|
37 |
value: 0.249
|
38 |
verified: false
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
39 |
---
|
40 |
|
41 |
|
|
|
36 |
type: pass@1
|
37 |
value: 0.249
|
38 |
verified: false
|
39 |
+
- task:
|
40 |
+
name: Math Reasoning
|
41 |
+
type: reasoning
|
42 |
+
dataset:
|
43 |
+
name: "GSM8K"
|
44 |
+
type: gsm8k
|
45 |
+
metrics:
|
46 |
+
- name: pass@1
|
47 |
+
type: pass@1
|
48 |
+
value: 0.174
|
49 |
+
verified: false
|
50 |
+
- task:
|
51 |
+
name: Knowledge
|
52 |
+
type: knowledge
|
53 |
+
dataset:
|
54 |
+
name: "MMLU"
|
55 |
+
type: mmlu
|
56 |
+
metrics:
|
57 |
+
- name: accuracy
|
58 |
+
type: accuracy
|
59 |
+
value: 0.399
|
60 |
+
verified: false
|
61 |
---
|
62 |
|
63 |
|