Adding Evaluation Results (#1)

- Adding Evaluation Results (d1a151bc63d4319c5c7f22f230ee919cbf2d96f2)


Co-authored-by: Open LLM Leaderboard PR Bot <leaderboard-pr-bot@users.noreply.huggingface.co>

README.md

@@ -1,12 +1,107 @@
 ---
-base_model:
-- dnhkng/RYS-Phi-3-medium-4k-instruct
-- failspy/Phi-3-medium-4k-instruct-abliterated-v3
+license: apache-2.0
 library_name: transformers
 tags:
 - mergekit
 - merge
-license: apache-2.0
+base_model:
+- dnhkng/RYS-Phi-3-medium-4k-instruct
+- failspy/Phi-3-medium-4k-instruct-abliterated-v3
+model-index:
+- name: Ph3merge3-14B
+  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: 16.45
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=allknowingroger/Ph3merge3-14B
+      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: 10.39
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=allknowingroger/Ph3merge3-14B
+      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: 0.0
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=allknowingroger/Ph3merge3-14B
+      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: 4.7
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=allknowingroger/Ph3merge3-14B
+      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: 8.86
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=allknowingroger/Ph3merge3-14B
+      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: 7.19
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=allknowingroger/Ph3merge3-14B
+      name: Open LLM Leaderboard
 ---
 # merge
 
@@ -44,4 +139,17 @@ parameters:
       value: [1, 0.5, 0.7, 0.3, 0]
     - value: 0.5
 dtype: bfloat16
-```
+```
+# [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_allknowingroger__Ph3merge3-14B)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               | 7.93|
+|IFEval (0-Shot)    |16.45|
+|BBH (3-Shot)       |10.39|
+|MATH Lvl 5 (4-Shot)| 0.00|
+|GPQA (0-shot)      | 4.70|
+|MuSR (0-shot)      | 8.86|
+|MMLU-PRO (5-shot)  | 7.19|
+