Update README.md
Browse files
README.md
CHANGED
@@ -7,76 +7,77 @@ base_model: meta-llama/Meta-Llama-3-8B-Instruct
|
|
7 |
model-index:
|
8 |
- name: MARS
|
9 |
results:
|
10 |
-
|
11 |
-
|
12 |
-
|
13 |
-
|
14 |
-
|
15 |
-
|
16 |
-
|
17 |
-
|
18 |
-
|
19 |
-
|
20 |
-
|
21 |
-
|
22 |
-
|
23 |
-
|
24 |
-
|
25 |
-
|
26 |
-
|
27 |
-
|
28 |
-
|
29 |
-
|
30 |
-
|
31 |
-
|
32 |
-
|
33 |
-
|
34 |
-
|
35 |
-
|
36 |
-
|
37 |
-
|
38 |
-
|
39 |
-
|
40 |
-
|
41 |
-
|
42 |
-
|
43 |
-
|
44 |
-
|
45 |
-
|
46 |
-
|
47 |
-
|
48 |
-
|
49 |
-
|
50 |
-
|
51 |
-
|
52 |
-
|
53 |
-
|
54 |
-
|
55 |
-
|
56 |
-
|
57 |
-
|
58 |
-
|
59 |
-
|
60 |
-
|
61 |
-
|
62 |
-
|
63 |
-
|
64 |
-
|
65 |
-
|
66 |
-
|
67 |
-
|
68 |
-
|
69 |
-
|
70 |
-
|
71 |
-
|
72 |
-
|
73 |
-
|
74 |
-
|
75 |
-
|
76 |
-
|
77 |
-
|
78 |
-
|
79 |
-
|
|
|
80 |
---
|
81 |
|
82 |
|
|
|
7 |
model-index:
|
8 |
- name: MARS
|
9 |
results:
|
10 |
+
- task:
|
11 |
+
type: text-generation
|
12 |
+
name: Text Generation
|
13 |
+
dataset:
|
14 |
+
name: AI2 Reasoning Challenge TR
|
15 |
+
type: ai2_arc
|
16 |
+
config: ARC-Challenge
|
17 |
+
split: test
|
18 |
+
args:
|
19 |
+
num_few_shot: 25
|
20 |
+
metrics:
|
21 |
+
- type: acc
|
22 |
+
value: 46.08
|
23 |
+
name: accuracy
|
24 |
+
- task:
|
25 |
+
type: text-generation
|
26 |
+
name: Text Generation
|
27 |
+
dataset:
|
28 |
+
name: MMLU TR
|
29 |
+
type: cais/mmlu
|
30 |
+
config: all
|
31 |
+
split: test
|
32 |
+
args:
|
33 |
+
num_few_shot: 5
|
34 |
+
metrics:
|
35 |
+
- type: acc
|
36 |
+
value: 47.02
|
37 |
+
name: accuracy
|
38 |
+
- task:
|
39 |
+
type: text-generation
|
40 |
+
name: Text Generation
|
41 |
+
dataset:
|
42 |
+
name: TruthfulQA TR
|
43 |
+
type: truthful_qa
|
44 |
+
config: multiple_choice
|
45 |
+
split: validation
|
46 |
+
args:
|
47 |
+
num_few_shot: 0
|
48 |
+
metrics:
|
49 |
+
- type: acc
|
50 |
+
name: accuracy
|
51 |
+
value: 49.38
|
52 |
+
- task:
|
53 |
+
type: text-generation
|
54 |
+
name: Text Generation
|
55 |
+
dataset:
|
56 |
+
name: Winogrande TR
|
57 |
+
type: winogrande
|
58 |
+
config: winogrande_xl
|
59 |
+
split: validation
|
60 |
+
args:
|
61 |
+
num_few_shot: 5
|
62 |
+
metrics:
|
63 |
+
- type: acc
|
64 |
+
value: 53.71
|
65 |
+
name: accuracy
|
66 |
+
- task:
|
67 |
+
type: text-generation
|
68 |
+
name: Text Generation
|
69 |
+
dataset:
|
70 |
+
name: GSM8k TR
|
71 |
+
type: gsm8k
|
72 |
+
config: main
|
73 |
+
split: test
|
74 |
+
args:
|
75 |
+
num_few_shot: 5
|
76 |
+
metrics:
|
77 |
+
- type: acc
|
78 |
+
value: 53.08
|
79 |
+
name: accuracy
|
80 |
+
pipeline_tag: text-generation
|
81 |
---
|
82 |
|
83 |
|