Update README.md
Browse files
README.md
CHANGED
|
@@ -12,6 +12,9 @@ model-index:
|
|
| 12 |
- name: AI2 Reasoning Challenge (25-Shot)
|
| 13 |
type: AI2 Reasoning Challenge (25-Shot)
|
| 14 |
value: 54.3921
|
|
|
|
|
|
|
|
|
|
| 15 |
|
| 16 |
- task:
|
| 17 |
type: text-generation
|
|
@@ -22,6 +25,9 @@ model-index:
|
|
| 22 |
- name: HellaSwag (10-shot)
|
| 23 |
type: HellaSwag (10-shot)
|
| 24 |
value: 54.3921
|
|
|
|
|
|
|
|
|
|
| 25 |
|
| 26 |
- task:
|
| 27 |
type: text-generation
|
|
@@ -32,6 +38,9 @@ model-index:
|
|
| 32 |
- name: MMLU (5-Shot)
|
| 33 |
type: MMLU (5-Shot)
|
| 34 |
value: 54.3921
|
|
|
|
|
|
|
|
|
|
| 35 |
|
| 36 |
- task:
|
| 37 |
type: text-generation
|
|
@@ -42,6 +51,9 @@ model-index:
|
|
| 42 |
- name: TruthfulQA (0-shot)
|
| 43 |
type: TruthfulQA (0-shot)
|
| 44 |
value: 54.3921
|
|
|
|
|
|
|
|
|
|
| 45 |
|
| 46 |
- task:
|
| 47 |
type: text-generation
|
|
@@ -52,6 +64,9 @@ model-index:
|
|
| 52 |
- name: Winogrande (5-shot)
|
| 53 |
type: Winogrande (5-shot)
|
| 54 |
value: 49
|
|
|
|
|
|
|
|
|
|
| 55 |
|
| 56 |
- task:
|
| 57 |
type: text-generation
|
|
@@ -62,6 +77,9 @@ model-index:
|
|
| 62 |
- name: GSM8k (5-shot)
|
| 63 |
type: GSM8k (5-shot)
|
| 64 |
value: 5
|
|
|
|
|
|
|
|
|
|
| 65 |
|
| 66 |
- task:
|
| 67 |
type: text-generation
|
|
@@ -72,7 +90,9 @@ model-index:
|
|
| 72 |
- name: DROP (3-shot)
|
| 73 |
type: DROP (3-shot)
|
| 74 |
value: 9
|
| 75 |
-
|
|
|
|
|
|
|
| 76 |
|
| 77 |
|
| 78 |
---
|
|
|
|
| 12 |
- name: AI2 Reasoning Challenge (25-Shot)
|
| 13 |
type: AI2 Reasoning Challenge (25-Shot)
|
| 14 |
value: 54.3921
|
| 15 |
+
source:
|
| 16 |
+
name: Open LLM Leaderboard
|
| 17 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard
|
| 18 |
|
| 19 |
- task:
|
| 20 |
type: text-generation
|
|
|
|
| 25 |
- name: HellaSwag (10-shot)
|
| 26 |
type: HellaSwag (10-shot)
|
| 27 |
value: 54.3921
|
| 28 |
+
source:
|
| 29 |
+
name: Open LLM Leaderboard
|
| 30 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard
|
| 31 |
|
| 32 |
- task:
|
| 33 |
type: text-generation
|
|
|
|
| 38 |
- name: MMLU (5-Shot)
|
| 39 |
type: MMLU (5-Shot)
|
| 40 |
value: 54.3921
|
| 41 |
+
source:
|
| 42 |
+
name: Open LLM Leaderboard
|
| 43 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard
|
| 44 |
|
| 45 |
- task:
|
| 46 |
type: text-generation
|
|
|
|
| 51 |
- name: TruthfulQA (0-shot)
|
| 52 |
type: TruthfulQA (0-shot)
|
| 53 |
value: 54.3921
|
| 54 |
+
source:
|
| 55 |
+
name: Open LLM Leaderboard
|
| 56 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard
|
| 57 |
|
| 58 |
- task:
|
| 59 |
type: text-generation
|
|
|
|
| 64 |
- name: Winogrande (5-shot)
|
| 65 |
type: Winogrande (5-shot)
|
| 66 |
value: 49
|
| 67 |
+
source:
|
| 68 |
+
name: Open LLM Leaderboard
|
| 69 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard
|
| 70 |
|
| 71 |
- task:
|
| 72 |
type: text-generation
|
|
|
|
| 77 |
- name: GSM8k (5-shot)
|
| 78 |
type: GSM8k (5-shot)
|
| 79 |
value: 5
|
| 80 |
+
source:
|
| 81 |
+
name: Open LLM Leaderboard
|
| 82 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard
|
| 83 |
|
| 84 |
- task:
|
| 85 |
type: text-generation
|
|
|
|
| 90 |
- name: DROP (3-shot)
|
| 91 |
type: DROP (3-shot)
|
| 92 |
value: 9
|
| 93 |
+
source:
|
| 94 |
+
name: Open LLM Leaderboard
|
| 95 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard
|
| 96 |
|
| 97 |
|
| 98 |
---
|