Update README.md
Browse files
README.md
CHANGED
|
@@ -23,7 +23,8 @@ model-index:
|
|
| 23 |
value: 62.5
|
| 24 |
name: strict accuracy
|
| 25 |
source:
|
| 26 |
-
url:
|
|
|
|
| 27 |
name: Open LLM Leaderboard
|
| 28 |
- task:
|
| 29 |
type: text-generation
|
|
@@ -38,7 +39,8 @@ model-index:
|
|
| 38 |
value: 30.36
|
| 39 |
name: normalized accuracy
|
| 40 |
source:
|
| 41 |
-
url:
|
|
|
|
| 42 |
name: Open LLM Leaderboard
|
| 43 |
- task:
|
| 44 |
type: text-generation
|
|
@@ -53,7 +55,8 @@ model-index:
|
|
| 53 |
value: 11.63
|
| 54 |
name: exact match
|
| 55 |
source:
|
| 56 |
-
url:
|
|
|
|
| 57 |
name: Open LLM Leaderboard
|
| 58 |
- task:
|
| 59 |
type: text-generation
|
|
@@ -68,7 +71,8 @@ model-index:
|
|
| 68 |
value: 8.84
|
| 69 |
name: acc_norm
|
| 70 |
source:
|
| 71 |
-
url:
|
|
|
|
| 72 |
name: Open LLM Leaderboard
|
| 73 |
- task:
|
| 74 |
type: text-generation
|
|
@@ -83,7 +87,8 @@ model-index:
|
|
| 83 |
value: 11.64
|
| 84 |
name: acc_norm
|
| 85 |
source:
|
| 86 |
-
url:
|
|
|
|
| 87 |
name: Open LLM Leaderboard
|
| 88 |
- task:
|
| 89 |
type: text-generation
|
|
@@ -100,8 +105,11 @@ model-index:
|
|
| 100 |
value: 29.84
|
| 101 |
name: accuracy
|
| 102 |
source:
|
| 103 |
-
url:
|
|
|
|
| 104 |
name: Open LLM Leaderboard
|
|
|
|
|
|
|
| 105 |
---
|
| 106 |
# merge
|
| 107 |
|
|
@@ -270,5 +278,4 @@ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-le
|
|
| 270 |
|MATH Lvl 5 (4-Shot)|11.63|
|
| 271 |
|GPQA (0-shot) | 8.84|
|
| 272 |
|MuSR (0-shot) |11.64|
|
| 273 |
-
|MMLU-PRO (5-shot) |29.84|
|
| 274 |
-
|
|
|
|
| 23 |
value: 62.5
|
| 24 |
name: strict accuracy
|
| 25 |
source:
|
| 26 |
+
url: >-
|
| 27 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bamec66557/MISCHIEVOUS-12B-Mix_Neo
|
| 28 |
name: Open LLM Leaderboard
|
| 29 |
- task:
|
| 30 |
type: text-generation
|
|
|
|
| 39 |
value: 30.36
|
| 40 |
name: normalized accuracy
|
| 41 |
source:
|
| 42 |
+
url: >-
|
| 43 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bamec66557/MISCHIEVOUS-12B-Mix_Neo
|
| 44 |
name: Open LLM Leaderboard
|
| 45 |
- task:
|
| 46 |
type: text-generation
|
|
|
|
| 55 |
value: 11.63
|
| 56 |
name: exact match
|
| 57 |
source:
|
| 58 |
+
url: >-
|
| 59 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bamec66557/MISCHIEVOUS-12B-Mix_Neo
|
| 60 |
name: Open LLM Leaderboard
|
| 61 |
- task:
|
| 62 |
type: text-generation
|
|
|
|
| 71 |
value: 8.84
|
| 72 |
name: acc_norm
|
| 73 |
source:
|
| 74 |
+
url: >-
|
| 75 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bamec66557/MISCHIEVOUS-12B-Mix_Neo
|
| 76 |
name: Open LLM Leaderboard
|
| 77 |
- task:
|
| 78 |
type: text-generation
|
|
|
|
| 87 |
value: 11.64
|
| 88 |
name: acc_norm
|
| 89 |
source:
|
| 90 |
+
url: >-
|
| 91 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bamec66557/MISCHIEVOUS-12B-Mix_Neo
|
| 92 |
name: Open LLM Leaderboard
|
| 93 |
- task:
|
| 94 |
type: text-generation
|
|
|
|
| 105 |
value: 29.84
|
| 106 |
name: accuracy
|
| 107 |
source:
|
| 108 |
+
url: >-
|
| 109 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bamec66557/MISCHIEVOUS-12B-Mix_Neo
|
| 110 |
name: Open LLM Leaderboard
|
| 111 |
+
datasets:
|
| 112 |
+
- open-llm-leaderboard/bamec66557__MISCHIEVOUS-12B-Mix_Neo-details
|
| 113 |
---
|
| 114 |
# merge
|
| 115 |
|
|
|
|
| 278 |
|MATH Lvl 5 (4-Shot)|11.63|
|
| 279 |
|GPQA (0-shot) | 8.84|
|
| 280 |
|MuSR (0-shot) |11.64|
|
| 281 |
+
|MMLU-PRO (5-shot) |29.84|
|
|
|