Update README.md
Browse files
README.md
CHANGED
|
@@ -12,6 +12,7 @@ tags:
|
|
| 12 |
- math
|
| 13 |
- trl
|
| 14 |
- reasoning
|
|
|
|
| 15 |
model-index:
|
| 16 |
- name: Magellanic-Opus-14B-Exp
|
| 17 |
results:
|
|
@@ -29,7 +30,8 @@ model-index:
|
|
| 29 |
value: 68.66
|
| 30 |
name: averaged accuracy
|
| 31 |
source:
|
| 32 |
-
url:
|
|
|
|
| 33 |
name: Open LLM Leaderboard
|
| 34 |
- task:
|
| 35 |
type: text-generation
|
|
@@ -42,10 +44,11 @@ model-index:
|
|
| 42 |
num_few_shot: 3
|
| 43 |
metrics:
|
| 44 |
- type: acc_norm
|
| 45 |
-
value: 48
|
| 46 |
name: normalized accuracy
|
| 47 |
source:
|
| 48 |
-
url:
|
|
|
|
| 49 |
name: Open LLM Leaderboard
|
| 50 |
- task:
|
| 51 |
type: text-generation
|
|
@@ -61,7 +64,8 @@ model-index:
|
|
| 61 |
value: 37.99
|
| 62 |
name: exact match
|
| 63 |
source:
|
| 64 |
-
url:
|
|
|
|
| 65 |
name: Open LLM Leaderboard
|
| 66 |
- task:
|
| 67 |
type: text-generation
|
|
@@ -77,7 +81,8 @@ model-index:
|
|
| 77 |
value: 16.55
|
| 78 |
name: acc_norm
|
| 79 |
source:
|
| 80 |
-
url:
|
|
|
|
| 81 |
name: Open LLM Leaderboard
|
| 82 |
- task:
|
| 83 |
type: text-generation
|
|
@@ -92,7 +97,8 @@ model-index:
|
|
| 92 |
value: 21.64
|
| 93 |
name: acc_norm
|
| 94 |
source:
|
| 95 |
-
url:
|
|
|
|
| 96 |
name: Open LLM Leaderboard
|
| 97 |
- task:
|
| 98 |
type: text-generation
|
|
@@ -109,7 +115,8 @@ model-index:
|
|
| 109 |
value: 47.47
|
| 110 |
name: accuracy
|
| 111 |
source:
|
| 112 |
-
url:
|
|
|
|
| 113 |
name: Open LLM Leaderboard
|
| 114 |
---
|
| 115 |
|
|
@@ -214,5 +221,4 @@ Summarized results can be found [here](https://huggingface.co/datasets/open-llm-
|
|
| 214 |
|MATH Lvl 5 (4-Shot)| 37.99|
|
| 215 |
|GPQA (0-shot) | 16.55|
|
| 216 |
|MuSR (0-shot) | 21.64|
|
| 217 |
-
|MMLU-PRO (5-shot) | 47.47|
|
| 218 |
-
|
|
|
|
| 12 |
- math
|
| 13 |
- trl
|
| 14 |
- reasoning
|
| 15 |
+
- QwQ
|
| 16 |
model-index:
|
| 17 |
- name: Magellanic-Opus-14B-Exp
|
| 18 |
results:
|
|
|
|
| 30 |
value: 68.66
|
| 31 |
name: averaged accuracy
|
| 32 |
source:
|
| 33 |
+
url: >-
|
| 34 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=prithivMLmods%2FMagellanic-Opus-14B-Exp
|
| 35 |
name: Open LLM Leaderboard
|
| 36 |
- task:
|
| 37 |
type: text-generation
|
|
|
|
| 44 |
num_few_shot: 3
|
| 45 |
metrics:
|
| 46 |
- type: acc_norm
|
| 47 |
+
value: 48
|
| 48 |
name: normalized accuracy
|
| 49 |
source:
|
| 50 |
+
url: >-
|
| 51 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=prithivMLmods%2FMagellanic-Opus-14B-Exp
|
| 52 |
name: Open LLM Leaderboard
|
| 53 |
- task:
|
| 54 |
type: text-generation
|
|
|
|
| 64 |
value: 37.99
|
| 65 |
name: exact match
|
| 66 |
source:
|
| 67 |
+
url: >-
|
| 68 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=prithivMLmods%2FMagellanic-Opus-14B-Exp
|
| 69 |
name: Open LLM Leaderboard
|
| 70 |
- task:
|
| 71 |
type: text-generation
|
|
|
|
| 81 |
value: 16.55
|
| 82 |
name: acc_norm
|
| 83 |
source:
|
| 84 |
+
url: >-
|
| 85 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=prithivMLmods%2FMagellanic-Opus-14B-Exp
|
| 86 |
name: Open LLM Leaderboard
|
| 87 |
- task:
|
| 88 |
type: text-generation
|
|
|
|
| 97 |
value: 21.64
|
| 98 |
name: acc_norm
|
| 99 |
source:
|
| 100 |
+
url: >-
|
| 101 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=prithivMLmods%2FMagellanic-Opus-14B-Exp
|
| 102 |
name: Open LLM Leaderboard
|
| 103 |
- task:
|
| 104 |
type: text-generation
|
|
|
|
| 115 |
value: 47.47
|
| 116 |
name: accuracy
|
| 117 |
source:
|
| 118 |
+
url: >-
|
| 119 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=prithivMLmods%2FMagellanic-Opus-14B-Exp
|
| 120 |
name: Open LLM Leaderboard
|
| 121 |
---
|
| 122 |
|
|
|
|
| 221 |
|MATH Lvl 5 (4-Shot)| 37.99|
|
| 222 |
|GPQA (0-shot) | 16.55|
|
| 223 |
|MuSR (0-shot) | 21.64|
|
| 224 |
+
|MMLU-PRO (5-shot) | 47.47|
|
|
|