Adding Evaluation Results

README.md

@@ -5,6 +5,101 @@ base_model:
 - SanjiWatsuki/Kunoichi-7B
 - uukuguy/speechless-instruct-mistral-7b-v0.2
 base_model_relation: merge
+model-index:
+- name: Inf-Silent-Kunoichi-v0.2-2x7B
+  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: 36.36
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Jacoby746/Inf-Silent-Kunoichi-v0.2-2x7B
+      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: 32.26
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Jacoby746/Inf-Silent-Kunoichi-v0.2-2x7B
+      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: 5.66
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Jacoby746/Inf-Silent-Kunoichi-v0.2-2x7B
+      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: 6.71
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Jacoby746/Inf-Silent-Kunoichi-v0.2-2x7B
+      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: 13.26
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Jacoby746/Inf-Silent-Kunoichi-v0.2-2x7B
+      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: 25.25
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Jacoby746/Inf-Silent-Kunoichi-v0.2-2x7B
+      name: Open LLM Leaderboard
 ---
 
 Test merge of 7b models for learning purposees. v0.2 is mostly the same, with minor promting changes and consolidating shards from 1B to 4B to reduce number of files.
@@ -20,4 +115,17 @@ Alpaca: Below is an instruction that describes a task. Write a response that app
 Instruction:
 {prompt}
 
-Response:
+Response:
+# [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_Jacoby746__Inf-Silent-Kunoichi-v0.2-2x7B)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |19.92|
+|IFEval (0-Shot)    |36.36|
+|BBH (3-Shot)       |32.26|
+|MATH Lvl 5 (4-Shot)| 5.66|
+|GPQA (0-shot)      | 6.71|
+|MuSR (0-shot)      |13.26|
+|MMLU-PRO (5-shot)  |25.25|
+