Adding Evaluation Results (#1)

- Adding Evaluation Results (1e156ef06b2bb83dd98cc5c52ab745fb6bfc2ced)


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

README.md

@@ -1,4 +1,11 @@
 ---
+language:
+- en
+license: other
+library_name: transformers
+tags:
+- mergekit
+- merge
 base_model:
 - unsloth/Mistral-Small-Instruct-2409
 - Gryphe/Pantheon-RP-Pure-1.6.2-22b-Small
@@ -10,13 +17,101 @@ base_model:
 - InferenceIllusionist/SorcererLM-22B
 - allura-org/MS-Meadowlark-22B
 - crestf411/MS-sunfall-v0.7.0
-library_name: transformers
-tags:
-- mergekit
-- merge
-license: other
-language:
-- en
+model-index:
+- name: MS-Schisandra-22B-v0.2
+  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: 63.83
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Nohobby/MS-Schisandra-22B-v0.2
+      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: 40.61
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Nohobby/MS-Schisandra-22B-v0.2
+      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: 19.94
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Nohobby/MS-Schisandra-22B-v0.2
+      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: 11.41
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Nohobby/MS-Schisandra-22B-v0.2
+      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: 10.67
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Nohobby/MS-Schisandra-22B-v0.2
+      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: 34.85
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Nohobby/MS-Schisandra-22B-v0.2
+      name: Open LLM Leaderboard
 ---
 ***
 ## Schisandra
@@ -181,4 +276,17 @@ models:
         - filter: down_proj
           value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
         - value: 1
-```
+```
+# [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_Nohobby__MS-Schisandra-22B-v0.2)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |30.22|
+|IFEval (0-Shot)    |63.83|
+|BBH (3-Shot)       |40.61|
+|MATH Lvl 5 (4-Shot)|19.94|
+|GPQA (0-shot)      |11.41|
+|MuSR (0-shot)      |10.67|
+|MMLU-PRO (5-shot)  |34.85|
+