Adding Evaluation Results

This is an automated PR created with [this space](https://huggingface.co/spaces/T145/open-llm-leaderboard-results-to-modelcard)!

The purpose of this PR is to add evaluation results from the Open LLM Leaderboard to your model card.

Please report any issues here: https://huggingface.co/spaces/T145/open-llm-leaderboard-results-to-modelcard/discussions

README.md

@@ -1,11 +1,110 @@
 ---
 library_name: transformers
 base_model:
-  - nbeerbower/llama-3-bophades-v3-8B
+- nbeerbower/llama-3-bophades-v3-8B
 datasets:
 - jondurbin/gutenberg-dpo-v0.1
 license: other
 license_name: llama3
+model-index:
+- name: llama-3-gutenberg-8B
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: IFEval (0-Shot)
+      type: wis-k/instruction-following-eval
+      split: train
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: inst_level_strict_acc and prompt_level_strict_acc
+      value: 43.72
+      name: averaged accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=nbeerbower%2Fllama-3-gutenberg-8B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: BBH (3-Shot)
+      type: SaylorTwift/bbh
+      split: test
+      args:
+        num_few_shot: 3
+    metrics:
+    - type: acc_norm
+      value: 27.96
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=nbeerbower%2Fllama-3-gutenberg-8B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MATH Lvl 5 (4-Shot)
+      type: lighteval/MATH-Hard
+      split: test
+      args:
+        num_few_shot: 4
+    metrics:
+    - type: exact_match
+      value: 7.78
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=nbeerbower%2Fllama-3-gutenberg-8B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GPQA (0-shot)
+      type: Idavidrein/gpqa
+      split: train
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 6.82
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=nbeerbower%2Fllama-3-gutenberg-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: 10.05
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=nbeerbower%2Fllama-3-gutenberg-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: 31.45
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=nbeerbower%2Fllama-3-gutenberg-8B
+      name: Open LLM Leaderboard
 ---
 
 # llama-3-gutenberg-8B
@@ -117,4 +216,17 @@ dpo_trainer = DPOTrainer(
     max_length=1536,
     force_use_ref_model=True
 )
-```
+```# [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/nbeerbower__llama-3-gutenberg-8B-details)!
+Summarized results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/contents/viewer/default/train?q=nbeerbower%2Fllama-3-gutenberg-8B&sort[column]=Average%20%E2%AC%86%EF%B8%8F&sort[direction]=desc)!
+
+|      Metric       |Value (%)|
+|-------------------|--------:|
+|**Average**        |    21.30|
+|IFEval (0-Shot)    |    43.72|
+|BBH (3-Shot)       |    27.96|
+|MATH Lvl 5 (4-Shot)|     7.78|
+|GPQA (0-shot)      |     6.82|
+|MuSR (0-shot)      |    10.05|
+|MMLU-PRO (5-shot)  |    31.45|
+