Adding Evaluation Results (#1)

- Adding Evaluation Results (d27be2754c759d47102486eee5d34e8f7a9ef660)


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

README.md

@@ -1,15 +1,110 @@
 ---
+license: llama3
+library_name: transformers
+tags:
+- mergekit
+- merge
 base_model:
 - nbeerbower/llama3.1-gutenberg-8B
 - akjindal53244/Llama-3.1-Storm-8B
 - NousResearch/Meta-Llama-3.1-8B
 - nbeerbower/llama3.1-airoboros3.2-QDT-8B
 - Sao10K/Llama-3.1-8B-Stheno-v3.4
-library_name: transformers
-tags:
-- mergekit
-- merge
-license: llama3
+model-index:
+- name: Llama-3.1-8B-Ultra-Instruct
+  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: 80.81
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Dampfinchen/Llama-3.1-8B-Ultra-Instruct
+      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: 32.49
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Dampfinchen/Llama-3.1-8B-Ultra-Instruct
+      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: 14.95
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Dampfinchen/Llama-3.1-8B-Ultra-Instruct
+      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: 5.59
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Dampfinchen/Llama-3.1-8B-Ultra-Instruct
+      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: 8.61
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Dampfinchen/Llama-3.1-8B-Ultra-Instruct
+      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: 31.4
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Dampfinchen/Llama-3.1-8B-Ultra-Instruct
+      name: Open LLM Leaderboard
 ---
 # merge
 
@@ -56,4 +151,17 @@ dtype: bfloat16
 name: Llama-3.1-8B-Ultra-Instruct
 ```
 
-Use Llama 3 Instruct prompt template. Use with caution, I'm not responsible for what you do with it. All credits and thanks go to the creators of the fine tunes I've merged.
+Use Llama 3 Instruct prompt template. Use with caution, I'm not responsible for what you do with it. All credits and thanks go to the creators of the fine tunes I've merged.
+# [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_Dampfinchen__Llama-3.1-8B-Ultra-Instruct)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |28.98|
+|IFEval (0-Shot)    |80.81|
+|BBH (3-Shot)       |32.49|
+|MATH Lvl 5 (4-Shot)|14.95|
+|GPQA (0-shot)      | 5.59|
+|MuSR (0-shot)      | 8.61|
+|MMLU-PRO (5-shot)  |31.40|
+