Adding Evaluation Results

README.md

@@ -1,16 +1,111 @@
 ---
-library_name: transformers
 language:
 - en
+license: apache-2.0
+library_name: transformers
 base_model:
 - EleutherAI/gpt-neo-1.3B
-license: apache-2.0
 datasets:
 - legacy-datasets/wikipedia
 metrics:
 - perplexity
 - accuracy
 new_version: Kimargin/GPT-NEO-1.3B-wiki
+model-index:
+- name: GPT-NEO-1.3B-wiki
+  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: 19.21
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Kimargin/GPT-NEO-1.3B-wiki
+      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: 3.42
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Kimargin/GPT-NEO-1.3B-wiki
+      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: 0.83
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Kimargin/GPT-NEO-1.3B-wiki
+      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: 0.0
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Kimargin/GPT-NEO-1.3B-wiki
+      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: 6.93
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Kimargin/GPT-NEO-1.3B-wiki
+      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: 1.1
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Kimargin/GPT-NEO-1.3B-wiki
+      name: Open LLM Leaderboard
 ---
 
 # Model Card for GPT-NEO-1.3B-wiki
@@ -120,4 +215,17 @@ If you use this model, please cite the original GPT-Neo model as follows:
   title = {GPT-Neo: Large Scale Autoregressive Language Model},
   year = {2021},
   url = {https://github.com/EleutherAI/gpt-neo}
-}
+}
+# [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_Kimargin__GPT-NEO-1.3B-wiki)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               | 5.25|
+|IFEval (0-Shot)    |19.21|
+|BBH (3-Shot)       | 3.42|
+|MATH Lvl 5 (4-Shot)| 0.83|
+|GPQA (0-shot)      | 0.00|
+|MuSR (0-shot)      | 6.93|
+|MMLU-PRO (5-shot)  | 1.10|
+