Update README.md (#6)
Browse files- Update README.md (07b8a167bb841f81a53f1ddda0e0177d03d673b3)
Co-authored-by: DV <[email protected]>
README.md
CHANGED
|
@@ -22,7 +22,8 @@ model-index:
|
|
| 22 |
value: 33.93
|
| 23 |
name: strict accuracy
|
| 24 |
source:
|
| 25 |
-
url:
|
|
|
|
| 26 |
name: Open LLM Leaderboard
|
| 27 |
- task:
|
| 28 |
type: text-generation
|
|
@@ -37,7 +38,8 @@ model-index:
|
|
| 37 |
value: 30.5
|
| 38 |
name: normalized accuracy
|
| 39 |
source:
|
| 40 |
-
url:
|
|
|
|
| 41 |
name: Open LLM Leaderboard
|
| 42 |
- task:
|
| 43 |
type: text-generation
|
|
@@ -52,7 +54,8 @@ model-index:
|
|
| 52 |
value: 9.82
|
| 53 |
name: exact match
|
| 54 |
source:
|
| 55 |
-
url:
|
|
|
|
| 56 |
name: Open LLM Leaderboard
|
| 57 |
- task:
|
| 58 |
type: text-generation
|
|
@@ -67,7 +70,8 @@ model-index:
|
|
| 67 |
value: 6.15
|
| 68 |
name: acc_norm
|
| 69 |
source:
|
| 70 |
-
url:
|
|
|
|
| 71 |
name: Open LLM Leaderboard
|
| 72 |
- task:
|
| 73 |
type: text-generation
|
|
@@ -82,7 +86,8 @@ model-index:
|
|
| 82 |
value: 10.36
|
| 83 |
name: acc_norm
|
| 84 |
source:
|
| 85 |
-
url:
|
|
|
|
| 86 |
name: Open LLM Leaderboard
|
| 87 |
- task:
|
| 88 |
type: text-generation
|
|
@@ -99,8 +104,16 @@ model-index:
|
|
| 99 |
value: 28.93
|
| 100 |
name: accuracy
|
| 101 |
source:
|
| 102 |
-
url:
|
|
|
|
| 103 |
name: Open LLM Leaderboard
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 104 |
---
|
| 105 |
|
| 106 |
|
|
@@ -270,5 +283,4 @@ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-le
|
|
| 270 |
|MATH Lvl 5 (4-Shot)| 9.82|
|
| 271 |
|GPQA (0-shot) | 6.15|
|
| 272 |
|MuSR (0-shot) |10.36|
|
| 273 |
-
|MMLU-PRO (5-shot) |28.93|
|
| 274 |
-
|
|
|
|
| 22 |
value: 33.93
|
| 23 |
name: strict accuracy
|
| 24 |
source:
|
| 25 |
+
url: >-
|
| 26 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=anthracite-org/magnum-v4-12b
|
| 27 |
name: Open LLM Leaderboard
|
| 28 |
- task:
|
| 29 |
type: text-generation
|
|
|
|
| 38 |
value: 30.5
|
| 39 |
name: normalized accuracy
|
| 40 |
source:
|
| 41 |
+
url: >-
|
| 42 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=anthracite-org/magnum-v4-12b
|
| 43 |
name: Open LLM Leaderboard
|
| 44 |
- task:
|
| 45 |
type: text-generation
|
|
|
|
| 54 |
value: 9.82
|
| 55 |
name: exact match
|
| 56 |
source:
|
| 57 |
+
url: >-
|
| 58 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=anthracite-org/magnum-v4-12b
|
| 59 |
name: Open LLM Leaderboard
|
| 60 |
- task:
|
| 61 |
type: text-generation
|
|
|
|
| 70 |
value: 6.15
|
| 71 |
name: acc_norm
|
| 72 |
source:
|
| 73 |
+
url: >-
|
| 74 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=anthracite-org/magnum-v4-12b
|
| 75 |
name: Open LLM Leaderboard
|
| 76 |
- task:
|
| 77 |
type: text-generation
|
|
|
|
| 86 |
value: 10.36
|
| 87 |
name: acc_norm
|
| 88 |
source:
|
| 89 |
+
url: >-
|
| 90 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=anthracite-org/magnum-v4-12b
|
| 91 |
name: Open LLM Leaderboard
|
| 92 |
- task:
|
| 93 |
type: text-generation
|
|
|
|
| 104 |
value: 28.93
|
| 105 |
name: accuracy
|
| 106 |
source:
|
| 107 |
+
url: >-
|
| 108 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=anthracite-org/magnum-v4-12b
|
| 109 |
name: Open LLM Leaderboard
|
| 110 |
+
datasets:
|
| 111 |
+
- anthracite-org/c2_logs_32k_llama3_qwen2_v1.2_no_system
|
| 112 |
+
- anthracite-org/kalo-opus-instruct-22k-no-refusal-no-system
|
| 113 |
+
- anthracite-org/kalo-opus-instruct-3k-filtered-no-system
|
| 114 |
+
- anthracite-org/nopm_claude_writing_fixed
|
| 115 |
+
- anthracite-org/kalo_opus_misc_240827_no_system
|
| 116 |
+
- anthracite-org/kalo_misc_part2_no_system
|
| 117 |
---
|
| 118 |
|
| 119 |
|
|
|
|
| 283 |
|MATH Lvl 5 (4-Shot)| 9.82|
|
| 284 |
|GPQA (0-shot) | 6.15|
|
| 285 |
|MuSR (0-shot) |10.36|
|
| 286 |
+
|MMLU-PRO (5-shot) |28.93|
|
|
|