Adding Evaluation Results (#1)

- Adding Evaluation Results (3d302ceb90ea99405072251829290204db9868f5)


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

README.md

@@ -1,4 +1,9 @@
 ---
+library_name: transformers
+tags:
+- mergekit
+- merge
+- llama
 base_model:
 - v000000/L3.1-8B-RP-Test-003-Task_Arithmetic
 - v000000/L3.1-Niitorm-8B-t0.0001
@@ -8,11 +13,101 @@ base_model:
 - arcee-ai/Llama-Spark
 - v000000/L3.1-8B-RP-Test-002-Task_Arithmetic
 - grimjim/Llama-3-Instruct-abliteration-LoRA-8B
-library_name: transformers
-tags:
-- mergekit
-- merge
-- llama
+model-index:
+- name: L3.1-Storniitova-8B
+  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: 78.17
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=v000000/L3.1-Storniitova-8B
+      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: 30.81
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=v000000/L3.1-Storniitova-8B
+      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: 13.29
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=v000000/L3.1-Storniitova-8B
+      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: 5.26
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=v000000/L3.1-Storniitova-8B
+      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: 9.96
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=v000000/L3.1-Storniitova-8B
+      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: 30.84
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=v000000/L3.1-Storniitova-8B
+      name: Open LLM Leaderboard
 ---
 
 # Llama-3.1-Storniitova-8B
@@ -121,3 +216,17 @@ dtype: float16
 
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64f74b6e6389380c77562762/GP2LMRvMkhVJwNDSEC4oU.png)
 
+
+# [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_v000000__L3.1-Storniitova-8B)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |28.06|
+|IFEval (0-Shot)    |78.17|
+|BBH (3-Shot)       |30.81|
+|MATH Lvl 5 (4-Shot)|13.29|
+|GPQA (0-shot)      | 5.26|
+|MuSR (0-shot)      | 9.96|
+|MMLU-PRO (5-shot)  |30.84|
+