Adding Evaluation Results

README.md

@@ -1,12 +1,107 @@
 ---
-license: apache-2.0
 language:
 - en
-pipeline_tag: text-generation
+license: apache-2.0
 library_name: transformers
 tags:
 - nlp
 - llm
+pipeline_tag: text-generation
+model-index:
+- name: K2
+  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: 22.52
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=LLM360/K2
+      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: 28.22
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=LLM360/K2
+      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: 2.04
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=LLM360/K2
+      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: 3.58
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=LLM360/K2
+      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: 8.55
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=LLM360/K2
+      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: 22.27
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=LLM360/K2
+      name: Open LLM Leaderboard
 ---
 # K2: a fully-reproducible large language model outperforming Llama 2 70B using 35% less compute
 
@@ -144,4 +239,17 @@ We believe in a future where artificial general intelligence (AGI) is created by
       year={2024},
 }
 
-```
+```
+# [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_LLM360__K2)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |14.53|
+|IFEval (0-Shot)    |22.52|
+|BBH (3-Shot)       |28.22|
+|MATH Lvl 5 (4-Shot)| 2.04|
+|GPQA (0-shot)      | 3.58|
+|MuSR (0-shot)      | 8.55|
+|MMLU-PRO (5-shot)  |22.27|
+