Adding Evaluation Results (#5)

- Adding Evaluation Results (18d92888dcd908814f9ffbc02d7f2d9efe17c5b2)


Co-authored-by: Open LLM Leaderboard PR Bot <[email protected]>

README.md

@@ -1,25 +1,120 @@
 ---
+language:
+- en
+- fr
+- de
+- es
+- it
+- pt
+- ru
+- zh
+- ja
 license: other
-license_name: tongyi-qianwen
-license_link: https://huggingface.co/anthracite-org/magnum-v2-72b/blob/main/LICENSE
+tags:
+- chat
 base_model: Qwen/Qwen2-72B-Instruct
 datasets:
-  - Doctor-Shotgun/C2-Stheno
-  - anthracite-org/kalo-opus-instruct-22k-no-refusal
-  - anthracite-org/nopm_claude_writing_fixed
-language:
-  - en
-  - fr
-  - de
-  - es
-  - it
-  - pt
-  - ru
-  - zh
-  - ja
+- Doctor-Shotgun/C2-Stheno
+- anthracite-org/kalo-opus-instruct-22k-no-refusal
+- anthracite-org/nopm_claude_writing_fixed
+license_name: tongyi-qianwen
+license_link: https://huggingface.co/anthracite-org/magnum-v2-72b/blob/main/LICENSE
 pipeline_tag: text-generation
-tags:
-- chat
+model-index:
+- name: magnum-v2-72b
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: IFEval (0-Shot)
+      type: HuggingFaceH4/ifeval
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: inst_level_strict_acc and prompt_level_strict_acc
+      value: 75.6
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=anthracite-org/magnum-v2-72b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: BBH (3-Shot)
+      type: BBH
+      args:
+        num_few_shot: 3
+    metrics:
+    - type: acc_norm
+      value: 57.85
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=anthracite-org/magnum-v2-72b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MATH Lvl 5 (4-Shot)
+      type: hendrycks/competition_math
+      args:
+        num_few_shot: 4
+    metrics:
+    - type: exact_match
+      value: 31.65
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=anthracite-org/magnum-v2-72b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GPQA (0-shot)
+      type: Idavidrein/gpqa
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 18.12
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=anthracite-org/magnum-v2-72b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MuSR (0-shot)
+      type: TAUR-Lab/MuSR
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 14.18
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=anthracite-org/magnum-v2-72b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU-PRO (5-shot)
+      type: TIGER-Lab/MMLU-Pro
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 49.51
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=anthracite-org/magnum-v2-72b
+      name: Open LLM Leaderboard
 ---
 
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6491e00e057b0928b3e07b75/u8B-5bEeroN549uxUIisV.png)
@@ -58,4 +153,17 @@ Sample Packing was done for 16k tokens rather than the 8k tokens used in our pre
 [<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
 
 ## Safety
-...
+...
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_anthracite-org__magnum-v2-72b)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |41.15|
+|IFEval (0-Shot)    |75.60|
+|BBH (3-Shot)       |57.85|
+|MATH Lvl 5 (4-Shot)|31.65|
+|GPQA (0-shot)      |18.12|
+|MuSR (0-shot)      |14.18|
+|MMLU-PRO (5-shot)  |49.51|
+