Update README.md
Browse files
README.md
CHANGED
|
@@ -21,7 +21,8 @@ model-index:
|
|
| 21 |
value: 66.02
|
| 22 |
name: strict accuracy
|
| 23 |
source:
|
| 24 |
-
url:
|
|
|
|
| 25 |
name: Open LLM Leaderboard
|
| 26 |
- task:
|
| 27 |
type: text-generation
|
|
@@ -36,7 +37,8 @@ model-index:
|
|
| 36 |
value: 31.36
|
| 37 |
name: normalized accuracy
|
| 38 |
source:
|
| 39 |
-
url:
|
|
|
|
| 40 |
name: Open LLM Leaderboard
|
| 41 |
- task:
|
| 42 |
type: text-generation
|
|
@@ -51,7 +53,8 @@ model-index:
|
|
| 51 |
value: 11.1
|
| 52 |
name: exact match
|
| 53 |
source:
|
| 54 |
-
url:
|
|
|
|
| 55 |
name: Open LLM Leaderboard
|
| 56 |
- task:
|
| 57 |
type: text-generation
|
|
@@ -66,7 +69,8 @@ model-index:
|
|
| 66 |
value: 8.61
|
| 67 |
name: acc_norm
|
| 68 |
source:
|
| 69 |
-
url:
|
|
|
|
| 70 |
name: Open LLM Leaderboard
|
| 71 |
- task:
|
| 72 |
type: text-generation
|
|
@@ -81,7 +85,8 @@ model-index:
|
|
| 81 |
value: 14.7
|
| 82 |
name: acc_norm
|
| 83 |
source:
|
| 84 |
-
url:
|
|
|
|
| 85 |
name: Open LLM Leaderboard
|
| 86 |
- task:
|
| 87 |
type: text-generation
|
|
@@ -98,8 +103,11 @@ model-index:
|
|
| 98 |
value: 29.83
|
| 99 |
name: accuracy
|
| 100 |
source:
|
| 101 |
-
url:
|
|
|
|
| 102 |
name: Open LLM Leaderboard
|
|
|
|
|
|
|
| 103 |
---
|
| 104 |
# Z-2-A.TEST-TEMP-MODEL
|
| 105 |
|
|
@@ -170,5 +178,4 @@ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-le
|
|
| 170 |
|MATH Lvl 5 (4-Shot)|11.10|
|
| 171 |
|GPQA (0-shot) | 8.61|
|
| 172 |
|MuSR (0-shot) |14.70|
|
| 173 |
-
|MMLU-PRO (5-shot) |29.83|
|
| 174 |
-
|
|
|
|
| 21 |
value: 66.02
|
| 22 |
name: strict accuracy
|
| 23 |
source:
|
| 24 |
+
url: >-
|
| 25 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bamec66557/NameLess-12B-prob
|
| 26 |
name: Open LLM Leaderboard
|
| 27 |
- task:
|
| 28 |
type: text-generation
|
|
|
|
| 37 |
value: 31.36
|
| 38 |
name: normalized accuracy
|
| 39 |
source:
|
| 40 |
+
url: >-
|
| 41 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bamec66557/NameLess-12B-prob
|
| 42 |
name: Open LLM Leaderboard
|
| 43 |
- task:
|
| 44 |
type: text-generation
|
|
|
|
| 53 |
value: 11.1
|
| 54 |
name: exact match
|
| 55 |
source:
|
| 56 |
+
url: >-
|
| 57 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bamec66557/NameLess-12B-prob
|
| 58 |
name: Open LLM Leaderboard
|
| 59 |
- task:
|
| 60 |
type: text-generation
|
|
|
|
| 69 |
value: 8.61
|
| 70 |
name: acc_norm
|
| 71 |
source:
|
| 72 |
+
url: >-
|
| 73 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bamec66557/NameLess-12B-prob
|
| 74 |
name: Open LLM Leaderboard
|
| 75 |
- task:
|
| 76 |
type: text-generation
|
|
|
|
| 85 |
value: 14.7
|
| 86 |
name: acc_norm
|
| 87 |
source:
|
| 88 |
+
url: >-
|
| 89 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bamec66557/NameLess-12B-prob
|
| 90 |
name: Open LLM Leaderboard
|
| 91 |
- task:
|
| 92 |
type: text-generation
|
|
|
|
| 103 |
value: 29.83
|
| 104 |
name: accuracy
|
| 105 |
source:
|
| 106 |
+
url: >-
|
| 107 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bamec66557/NameLess-12B-prob
|
| 108 |
name: Open LLM Leaderboard
|
| 109 |
+
datasets:
|
| 110 |
+
- open-llm-leaderboard/bamec66557__NameLess-12B-prob-details
|
| 111 |
---
|
| 112 |
# Z-2-A.TEST-TEMP-MODEL
|
| 113 |
|
|
|
|
| 178 |
|MATH Lvl 5 (4-Shot)|11.10|
|
| 179 |
|GPQA (0-shot) | 8.61|
|
| 180 |
|MuSR (0-shot) |14.70|
|
| 181 |
+
|MMLU-PRO (5-shot) |29.83|
|
|
|