Commit
•
e412f30
1
Parent(s):
8033195
Update README.md (#3)
Browse files- Update README.md (332267404693c7d034502da0e6280c0d154d2de9)
Co-authored-by: DV <[email protected]>
README.md
CHANGED
|
@@ -23,7 +23,8 @@ model-index:
|
|
| 23 |
value: 56.29
|
| 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: 35.55
|
| 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: 17.6
|
| 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: 10.4
|
| 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: 13.43
|
| 84 |
name: acc_norm
|
| 85 |
source:
|
| 86 |
-
url:
|
|
|
|
| 87 |
name: Open LLM Leaderboard
|
| 88 |
- task:
|
| 89 |
type: text-generation
|
|
@@ -100,8 +105,16 @@ model-index:
|
|
| 100 |
value: 31.44
|
| 101 |
name: accuracy
|
| 102 |
source:
|
| 103 |
-
url:
|
|
|
|
| 104 |
name: Open LLM Leaderboard
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 105 |
---
|
| 106 |
|
| 107 |
|
|
@@ -271,5 +284,4 @@ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-le
|
|
| 271 |
|MATH Lvl 5 (4-Shot)|17.60|
|
| 272 |
|GPQA (0-shot) |10.40|
|
| 273 |
|MuSR (0-shot) |13.43|
|
| 274 |
-
|MMLU-PRO (5-shot) |31.44|
|
| 275 |
-
|
|
|
|
| 23 |
value: 56.29
|
| 24 |
name: strict accuracy
|
| 25 |
source:
|
| 26 |
+
url: >-
|
| 27 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=anthracite-org/magnum-v4-22b
|
| 28 |
name: Open LLM Leaderboard
|
| 29 |
- task:
|
| 30 |
type: text-generation
|
|
|
|
| 39 |
value: 35.55
|
| 40 |
name: normalized accuracy
|
| 41 |
source:
|
| 42 |
+
url: >-
|
| 43 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=anthracite-org/magnum-v4-22b
|
| 44 |
name: Open LLM Leaderboard
|
| 45 |
- task:
|
| 46 |
type: text-generation
|
|
|
|
| 55 |
value: 17.6
|
| 56 |
name: exact match
|
| 57 |
source:
|
| 58 |
+
url: >-
|
| 59 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=anthracite-org/magnum-v4-22b
|
| 60 |
name: Open LLM Leaderboard
|
| 61 |
- task:
|
| 62 |
type: text-generation
|
|
|
|
| 71 |
value: 10.4
|
| 72 |
name: acc_norm
|
| 73 |
source:
|
| 74 |
+
url: >-
|
| 75 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=anthracite-org/magnum-v4-22b
|
| 76 |
name: Open LLM Leaderboard
|
| 77 |
- task:
|
| 78 |
type: text-generation
|
|
|
|
| 87 |
value: 13.43
|
| 88 |
name: acc_norm
|
| 89 |
source:
|
| 90 |
+
url: >-
|
| 91 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=anthracite-org/magnum-v4-22b
|
| 92 |
name: Open LLM Leaderboard
|
| 93 |
- task:
|
| 94 |
type: text-generation
|
|
|
|
| 105 |
value: 31.44
|
| 106 |
name: accuracy
|
| 107 |
source:
|
| 108 |
+
url: >-
|
| 109 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=anthracite-org/magnum-v4-22b
|
| 110 |
name: Open LLM Leaderboard
|
| 111 |
+
datasets:
|
| 112 |
+
- anthracite-org/c2_logs_32k_mistral-v3_v1.2_no_system
|
| 113 |
+
- anthracite-org/kalo-opus-instruct-22k-no-refusal-no-system
|
| 114 |
+
- anthracite-org/kalo-opus-instruct-3k-filtered-no-system
|
| 115 |
+
- anthracite-org/nopm_claude_writing_fixed
|
| 116 |
+
- anthracite-org/kalo_opus_misc_240827_no_system
|
| 117 |
+
- anthracite-org/kalo_misc_part2_no_system
|
| 118 |
---
|
| 119 |
|
| 120 |
|
|
|
|
| 284 |
|MATH Lvl 5 (4-Shot)|17.60|
|
| 285 |
|GPQA (0-shot) |10.40|
|
| 286 |
|MuSR (0-shot) |13.43|
|
| 287 |
+
|MMLU-PRO (5-shot) |31.44|
|
|
|