Adding Evaluation Results (#1)

- Adding Evaluation Results (a33b2afaec6471c44dd0ce75cefa98b1d4b379c0)


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

README.md

@@ -1,15 +1,110 @@
 ---
-base_model:
-- akjindal53244/Llama-3.1-Storm-8B
-- Sao10K/L3.1-8B-Niitama-v1.1
-- v000000/L3.1-Niitorm-8B-t0.0001
 library_name: transformers
 tags:
 - merge
 - llama
 - dpo
+base_model:
+- akjindal53244/Llama-3.1-Storm-8B
+- Sao10K/L3.1-8B-Niitama-v1.1
+- v000000/L3.1-Niitorm-8B-t0.0001
 datasets:
 - jondurbin/gutenberg-dpo-v0.1
+model-index:
+- name: L3.1-Niitorm-8B-DPO-t0.0001
+  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: 76.89
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=v000000/L3.1-Niitorm-8B-DPO-t0.0001
+      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: 30.51
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=v000000/L3.1-Niitorm-8B-DPO-t0.0001
+      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: 14.88
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=v000000/L3.1-Niitorm-8B-DPO-t0.0001
+      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: 5.93
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=v000000/L3.1-Niitorm-8B-DPO-t0.0001
+      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: 7.26
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=v000000/L3.1-Niitorm-8B-DPO-t0.0001
+      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: 31.85
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=v000000/L3.1-Niitorm-8B-DPO-t0.0001
+      name: Open LLM Leaderboard
 ---
 
 # Llama-3.1-Niitorm-8B-DPO
@@ -115,4 +210,17 @@ Credit to mlabonne.
 
 Credit to jondurbin.
 
-Credit to woofwolfy.
+Credit to woofwolfy.
+# [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-Niitorm-8B-DPO-t0.0001)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |27.89|
+|IFEval (0-Shot)    |76.89|
+|BBH (3-Shot)       |30.51|
+|MATH Lvl 5 (4-Shot)|14.88|
+|GPQA (0-shot)      | 5.93|
+|MuSR (0-shot)      | 7.26|
+|MMLU-PRO (5-shot)  |31.85|
+