Update README.md
Browse files
README.md
CHANGED
|
@@ -24,7 +24,8 @@ model-index:
|
|
| 24 |
value: 67.21
|
| 25 |
name: strict accuracy
|
| 26 |
source:
|
| 27 |
-
url:
|
|
|
|
| 28 |
name: Open LLM Leaderboard
|
| 29 |
- task:
|
| 30 |
type: text-generation
|
|
@@ -39,7 +40,8 @@ model-index:
|
|
| 39 |
value: 31.36
|
| 40 |
name: normalized accuracy
|
| 41 |
source:
|
| 42 |
-
url:
|
|
|
|
| 43 |
name: Open LLM Leaderboard
|
| 44 |
- task:
|
| 45 |
type: text-generation
|
|
@@ -54,7 +56,8 @@ model-index:
|
|
| 54 |
value: 12.08
|
| 55 |
name: exact match
|
| 56 |
source:
|
| 57 |
-
url:
|
|
|
|
| 58 |
name: Open LLM Leaderboard
|
| 59 |
- task:
|
| 60 |
type: text-generation
|
|
@@ -69,7 +72,8 @@ model-index:
|
|
| 69 |
value: 8.84
|
| 70 |
name: acc_norm
|
| 71 |
source:
|
| 72 |
-
url:
|
|
|
|
| 73 |
name: Open LLM Leaderboard
|
| 74 |
- task:
|
| 75 |
type: text-generation
|
|
@@ -84,7 +88,8 @@ model-index:
|
|
| 84 |
value: 14.34
|
| 85 |
name: acc_norm
|
| 86 |
source:
|
| 87 |
-
url:
|
|
|
|
| 88 |
name: Open LLM Leaderboard
|
| 89 |
- task:
|
| 90 |
type: text-generation
|
|
@@ -101,8 +106,14 @@ model-index:
|
|
| 101 |
value: 29.76
|
| 102 |
name: accuracy
|
| 103 |
source:
|
| 104 |
-
url:
|
|
|
|
| 105 |
name: Open LLM Leaderboard
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 106 |
---
|
| 107 |
# merge
|
| 108 |
|
|
@@ -300,5 +311,4 @@ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-le
|
|
| 300 |
|MATH Lvl 5 (4-Shot)|12.08|
|
| 301 |
|GPQA (0-shot) | 8.84|
|
| 302 |
|MuSR (0-shot) |14.34|
|
| 303 |
-
|MMLU-PRO (5-shot) |29.76|
|
| 304 |
-
|
|
|
|
| 24 |
value: 67.21
|
| 25 |
name: strict accuracy
|
| 26 |
source:
|
| 27 |
+
url: >-
|
| 28 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bamec66557/Mistral-Nemo-VICIOUS_MESH-12B-2407
|
| 29 |
name: Open LLM Leaderboard
|
| 30 |
- task:
|
| 31 |
type: text-generation
|
|
|
|
| 40 |
value: 31.36
|
| 41 |
name: normalized accuracy
|
| 42 |
source:
|
| 43 |
+
url: >-
|
| 44 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bamec66557/Mistral-Nemo-VICIOUS_MESH-12B-2407
|
| 45 |
name: Open LLM Leaderboard
|
| 46 |
- task:
|
| 47 |
type: text-generation
|
|
|
|
| 56 |
value: 12.08
|
| 57 |
name: exact match
|
| 58 |
source:
|
| 59 |
+
url: >-
|
| 60 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bamec66557/Mistral-Nemo-VICIOUS_MESH-12B-2407
|
| 61 |
name: Open LLM Leaderboard
|
| 62 |
- task:
|
| 63 |
type: text-generation
|
|
|
|
| 72 |
value: 8.84
|
| 73 |
name: acc_norm
|
| 74 |
source:
|
| 75 |
+
url: >-
|
| 76 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bamec66557/Mistral-Nemo-VICIOUS_MESH-12B-2407
|
| 77 |
name: Open LLM Leaderboard
|
| 78 |
- task:
|
| 79 |
type: text-generation
|
|
|
|
| 88 |
value: 14.34
|
| 89 |
name: acc_norm
|
| 90 |
source:
|
| 91 |
+
url: >-
|
| 92 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bamec66557/Mistral-Nemo-VICIOUS_MESH-12B-2407
|
| 93 |
name: Open LLM Leaderboard
|
| 94 |
- task:
|
| 95 |
type: text-generation
|
|
|
|
| 106 |
value: 29.76
|
| 107 |
name: accuracy
|
| 108 |
source:
|
| 109 |
+
url: >-
|
| 110 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bamec66557/Mistral-Nemo-VICIOUS_MESH-12B-2407
|
| 111 |
name: Open LLM Leaderboard
|
| 112 |
+
datasets:
|
| 113 |
+
- open-llm-leaderboard/bamec66557__Mistral-Nemo-VICIOUS_MESH-12B-2407-details
|
| 114 |
+
- open-llm-leaderboard/bamec66557__VICIOUS_MESH-12B-BETA-details
|
| 115 |
+
- open-llm-leaderboard/bamec66557__VICIOUS_MESH-12B-OMEGA-details
|
| 116 |
+
- open-llm-leaderboard/bamec66557__VICIOUS_MESH-12B-ALPHA-details
|
| 117 |
---
|
| 118 |
# merge
|
| 119 |
|
|
|
|
| 311 |
|MATH Lvl 5 (4-Shot)|12.08|
|
| 312 |
|GPQA (0-shot) | 8.84|
|
| 313 |
|MuSR (0-shot) |14.34|
|
| 314 |
+
|MMLU-PRO (5-shot) |29.76|
|
|
|