Update README.md
Browse files
README.md
CHANGED
|
@@ -26,7 +26,8 @@ model-index:
|
|
| 26 |
value: 52.35
|
| 27 |
name: strict accuracy
|
| 28 |
source:
|
| 29 |
-
url:
|
|
|
|
| 30 |
name: Open LLM Leaderboard
|
| 31 |
- task:
|
| 32 |
type: text-generation
|
|
@@ -41,7 +42,8 @@ model-index:
|
|
| 41 |
value: 50.64
|
| 42 |
name: normalized accuracy
|
| 43 |
source:
|
| 44 |
-
url:
|
|
|
|
| 45 |
name: Open LLM Leaderboard
|
| 46 |
- task:
|
| 47 |
type: text-generation
|
|
@@ -56,7 +58,8 @@ model-index:
|
|
| 56 |
value: 30.06
|
| 57 |
name: exact match
|
| 58 |
source:
|
| 59 |
-
url:
|
|
|
|
| 60 |
name: Open LLM Leaderboard
|
| 61 |
- task:
|
| 62 |
type: text-generation
|
|
@@ -71,7 +74,8 @@ model-index:
|
|
| 71 |
value: 19.13
|
| 72 |
name: acc_norm
|
| 73 |
source:
|
| 74 |
-
url:
|
|
|
|
| 75 |
name: Open LLM Leaderboard
|
| 76 |
- task:
|
| 77 |
type: text-generation
|
|
@@ -86,7 +90,8 @@ model-index:
|
|
| 86 |
value: 18.25
|
| 87 |
name: acc_norm
|
| 88 |
source:
|
| 89 |
-
url:
|
|
|
|
| 90 |
name: Open LLM Leaderboard
|
| 91 |
- task:
|
| 92 |
type: text-generation
|
|
@@ -103,8 +108,15 @@ model-index:
|
|
| 103 |
value: 49.15
|
| 104 |
name: accuracy
|
| 105 |
source:
|
| 106 |
-
url:
|
|
|
|
| 107 |
name: Open LLM Leaderboard
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 108 |
---
|
| 109 |
# merge
|
| 110 |
|
|
@@ -151,5 +163,4 @@ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-le
|
|
| 151 |
|MATH Lvl 5 (4-Shot)|30.06|
|
| 152 |
|GPQA (0-shot) |19.13|
|
| 153 |
|MuSR (0-shot) |18.25|
|
| 154 |
-
|MMLU-PRO (5-shot) |49.15|
|
| 155 |
-
|
|
|
|
| 26 |
value: 52.35
|
| 27 |
name: strict accuracy
|
| 28 |
source:
|
| 29 |
+
url: >-
|
| 30 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=CultriX/Qwen2.5-14B-Wernicke
|
| 31 |
name: Open LLM Leaderboard
|
| 32 |
- task:
|
| 33 |
type: text-generation
|
|
|
|
| 42 |
value: 50.64
|
| 43 |
name: normalized accuracy
|
| 44 |
source:
|
| 45 |
+
url: >-
|
| 46 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=CultriX/Qwen2.5-14B-Wernicke
|
| 47 |
name: Open LLM Leaderboard
|
| 48 |
- task:
|
| 49 |
type: text-generation
|
|
|
|
| 58 |
value: 30.06
|
| 59 |
name: exact match
|
| 60 |
source:
|
| 61 |
+
url: >-
|
| 62 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=CultriX/Qwen2.5-14B-Wernicke
|
| 63 |
name: Open LLM Leaderboard
|
| 64 |
- task:
|
| 65 |
type: text-generation
|
|
|
|
| 74 |
value: 19.13
|
| 75 |
name: acc_norm
|
| 76 |
source:
|
| 77 |
+
url: >-
|
| 78 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=CultriX/Qwen2.5-14B-Wernicke
|
| 79 |
name: Open LLM Leaderboard
|
| 80 |
- task:
|
| 81 |
type: text-generation
|
|
|
|
| 90 |
value: 18.25
|
| 91 |
name: acc_norm
|
| 92 |
source:
|
| 93 |
+
url: >-
|
| 94 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=CultriX/Qwen2.5-14B-Wernicke
|
| 95 |
name: Open LLM Leaderboard
|
| 96 |
- task:
|
| 97 |
type: text-generation
|
|
|
|
| 108 |
value: 49.15
|
| 109 |
name: accuracy
|
| 110 |
source:
|
| 111 |
+
url: >-
|
| 112 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=CultriX/Qwen2.5-14B-Wernicke
|
| 113 |
name: Open LLM Leaderboard
|
| 114 |
+
license: apache-2.0
|
| 115 |
+
language:
|
| 116 |
+
- en
|
| 117 |
+
metrics:
|
| 118 |
+
- accuracy
|
| 119 |
+
pipeline_tag: text-generation
|
| 120 |
---
|
| 121 |
# merge
|
| 122 |
|
|
|
|
| 163 |
|MATH Lvl 5 (4-Shot)|30.06|
|
| 164 |
|GPQA (0-shot) |19.13|
|
| 165 |
|MuSR (0-shot) |18.25|
|
| 166 |
+
|MMLU-PRO (5-shot) |49.15|
|
|
|