Update README.md
Browse filesbenchmark scores added
README.md
CHANGED
@@ -1,3 +1,92 @@
|
|
1 |
-
---
|
2 |
-
license: llama3
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: llama3
|
3 |
+
language:
|
4 |
+
- tr
|
5 |
+
- en
|
6 |
+
model-index:
|
7 |
+
- name: Kocdigital-LLM-8b-v0.1
|
8 |
+
results:
|
9 |
+
- task:
|
10 |
+
type: text-generation
|
11 |
+
name: Text Generation
|
12 |
+
dataset:
|
13 |
+
name: AI2 Reasoning Challenge TR
|
14 |
+
type: ai2_arc
|
15 |
+
config: ARC-Challenge
|
16 |
+
split: test
|
17 |
+
args:
|
18 |
+
num_few_shot: 25
|
19 |
+
metrics:
|
20 |
+
- type: acc
|
21 |
+
value: 44.03
|
22 |
+
name: accuracy
|
23 |
+
- task:
|
24 |
+
type: text-generation
|
25 |
+
name: Text Generation
|
26 |
+
dataset:
|
27 |
+
name: HellaSwag TR
|
28 |
+
type: hellaswag
|
29 |
+
split: validation
|
30 |
+
args:
|
31 |
+
num_few_shot: 10
|
32 |
+
metrics:
|
33 |
+
- type: acc
|
34 |
+
value: 46.73
|
35 |
+
name: accuracy
|
36 |
+
- task:
|
37 |
+
type: text-generation
|
38 |
+
name: Text Generation
|
39 |
+
dataset:
|
40 |
+
name: MMLU TR
|
41 |
+
type: cais/mmlu
|
42 |
+
config: all
|
43 |
+
split: test
|
44 |
+
args:
|
45 |
+
num_few_shot: 5
|
46 |
+
metrics:
|
47 |
+
- type: acc
|
48 |
+
value: 49.11
|
49 |
+
name: accuracy
|
50 |
+
- task:
|
51 |
+
type: text-generation
|
52 |
+
name: Text Generation
|
53 |
+
dataset:
|
54 |
+
name: TruthfulQA TR
|
55 |
+
type: truthful_qa
|
56 |
+
config: multiple_choice
|
57 |
+
split: validation
|
58 |
+
args:
|
59 |
+
num_few_shot: 0
|
60 |
+
metrics:
|
61 |
+
- type: acc
|
62 |
+
name: accuracy
|
63 |
+
value: 48.21
|
64 |
+
- task:
|
65 |
+
type: text-generation
|
66 |
+
name: Text Generation
|
67 |
+
dataset:
|
68 |
+
name: Winogrande TR
|
69 |
+
type: winogrande
|
70 |
+
config: winogrande_xl
|
71 |
+
split: validation
|
72 |
+
args:
|
73 |
+
num_few_shot: 10
|
74 |
+
metrics:
|
75 |
+
- type: acc
|
76 |
+
value: 54.98
|
77 |
+
name: accuracy
|
78 |
+
- task:
|
79 |
+
type: text-generation
|
80 |
+
name: Text Generation
|
81 |
+
dataset:
|
82 |
+
name: GSM8k TR
|
83 |
+
type: gsm8k
|
84 |
+
config: main
|
85 |
+
split: test
|
86 |
+
args:
|
87 |
+
num_few_shot: 5
|
88 |
+
metrics:
|
89 |
+
- type: acc
|
90 |
+
value: 51.78
|
91 |
+
name: accuracy
|
92 |
+
---
|