Adding Evaluation Results (#1)

- Adding Evaluation Results (b0b165356fe9d2935bac0d21f7b607a286c570d0)

README.md

@@ -1,12 +1,107 @@
 ---
-base_model:
-- Qwen/Qwen2.5-7B-Instruct-1M
-- huihui-ai/Qwen2.5-7B-Instruct-1M-abliterated
+license: apache-2.0
 library_name: transformers
 tags:
 - mergekit
 - merge
-license: apache-2.0
+base_model:
+- Qwen/Qwen2.5-7B-Instruct-1M
+- huihui-ai/Qwen2.5-7B-Instruct-1M-abliterated
+model-index:
+- name: Q2.5-Instruct-1M_Harmony
+  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: 60.38
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Q2.5-Instruct-1M_Harmony
+      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: 33.63
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Q2.5-Instruct-1M_Harmony
+      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: 32.1
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Q2.5-Instruct-1M_Harmony
+      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: 9.73
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Q2.5-Instruct-1M_Harmony
+      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: 18.1
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Q2.5-Instruct-1M_Harmony
+      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: 37.4
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Q2.5-Instruct-1M_Harmony
+      name: Open LLM Leaderboard
 ---
 # merge
 
@@ -36,4 +131,17 @@ dtype: bfloat16
 parameters:
   t: [0, 0.5, 1, 0.5, 0]
 
-```
+```
+# [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/Triangle104__Q2.5-Instruct-1M_Harmony-details)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |31.89|
+|IFEval (0-Shot)    |60.38|
+|BBH (3-Shot)       |33.63|
+|MATH Lvl 5 (4-Shot)|32.10|
+|GPQA (0-shot)      | 9.73|
+|MuSR (0-shot)      |18.10|
+|MMLU-PRO (5-shot)  |37.40|
+