Update README.md
Browse files
README.md
CHANGED
|
@@ -1,5 +1,90 @@
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
| 4 |
|
| 5 |
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
+
model-index:
|
| 4 |
+
- name: OpenHermes-2.5-neural-chat-v3-3-Slerp
|
| 5 |
+
results:
|
| 6 |
+
- task:
|
| 7 |
+
type: text-generation
|
| 8 |
+
name: Text Generation
|
| 9 |
+
dataset:
|
| 10 |
+
name: AI2 Reasoning Challenge (25-Shot)
|
| 11 |
+
type: ai2_arc
|
| 12 |
+
config: ARC-Challenge
|
| 13 |
+
split: test
|
| 14 |
+
args:
|
| 15 |
+
num_few_shot: 25
|
| 16 |
+
metrics:
|
| 17 |
+
- type: acc_norm
|
| 18 |
+
value: 68.09
|
| 19 |
+
name: normalized accuracy
|
| 20 |
+
- task:
|
| 21 |
+
type: text-generation
|
| 22 |
+
name: Text Generation
|
| 23 |
+
dataset:
|
| 24 |
+
name: HellaSwag (10-Shot)
|
| 25 |
+
type: hellaswag
|
| 26 |
+
split: validation
|
| 27 |
+
args:
|
| 28 |
+
num_few_shot: 10
|
| 29 |
+
metrics:
|
| 30 |
+
- type: acc_norm
|
| 31 |
+
value: 86.2
|
| 32 |
+
name: normalized accuracy
|
| 33 |
+
- task:
|
| 34 |
+
type: text-generation
|
| 35 |
+
name: Text Generation
|
| 36 |
+
dataset:
|
| 37 |
+
name: MMLU (5-Shot)
|
| 38 |
+
type: cais/mmlu
|
| 39 |
+
config: all
|
| 40 |
+
split: test
|
| 41 |
+
args:
|
| 42 |
+
num_few_shot: 5
|
| 43 |
+
metrics:
|
| 44 |
+
- type: acc
|
| 45 |
+
value: 64.26
|
| 46 |
+
name: accuracy
|
| 47 |
+
- task:
|
| 48 |
+
type: text-generation
|
| 49 |
+
name: Text Generation
|
| 50 |
+
dataset:
|
| 51 |
+
name: TruthfulQA (0-shot)
|
| 52 |
+
type: truthful_qa
|
| 53 |
+
config: multiple_choice
|
| 54 |
+
split: validation
|
| 55 |
+
args:
|
| 56 |
+
num_few_shot: 0
|
| 57 |
+
metrics:
|
| 58 |
+
- type: mc2
|
| 59 |
+
value: 62.78
|
| 60 |
+
- task:
|
| 61 |
+
type: text-generation
|
| 62 |
+
name: Text Generation
|
| 63 |
+
dataset:
|
| 64 |
+
name: Winogrande (5-shot)
|
| 65 |
+
type: winogrande
|
| 66 |
+
config: winogrande_xl
|
| 67 |
+
split: validation
|
| 68 |
+
args:
|
| 69 |
+
num_few_shot: 5
|
| 70 |
+
metrics:
|
| 71 |
+
- type: acc
|
| 72 |
+
value: 79.16
|
| 73 |
+
name: accuracy
|
| 74 |
+
- task:
|
| 75 |
+
type: text-generation
|
| 76 |
+
name: Text Generation
|
| 77 |
+
dataset:
|
| 78 |
+
name: GSM8k (5-shot)
|
| 79 |
+
type: gsm8k
|
| 80 |
+
config: main
|
| 81 |
+
split: test
|
| 82 |
+
args:
|
| 83 |
+
num_few_shot: 5
|
| 84 |
+
metrics:
|
| 85 |
+
- type: acc
|
| 86 |
+
value: 67.78
|
| 87 |
+
name: accuracy
|
| 88 |
---
|
| 89 |
|
| 90 |
|