Update README.md

README.md

@@ -1,8 +1,111 @@
 ---
 language:
-- ko
 - en
 license: mit
+library_name: transformers
+model-index:
+- name: free-evo-qwen72b-v0.8-re
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: AI2 Reasoning Challenge (25-Shot)
+      type: ai2_arc
+      config: ARC-Challenge
+      split: test
+      args:
+        num_few_shot: 25
+    metrics:
+    - type: acc_norm
+      value: 79.86
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=freewheelin/free-evo-qwen72b-v0.8-re
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: HellaSwag (10-Shot)
+      type: hellaswag
+      split: validation
+      args:
+        num_few_shot: 10
+    metrics:
+    - type: acc_norm
+      value: 91.34
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=freewheelin/free-evo-qwen72b-v0.8-re
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU (5-Shot)
+      type: cais/mmlu
+      config: all
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 78.00
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=freewheelin/free-evo-qwen72b-v0.8-re
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: TruthfulQA (0-shot)
+      type: truthful_qa
+      config: multiple_choice
+      split: validation
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: mc2
+      value: 74.85
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=freewheelin/free-evo-qwen72b-v0.8-re
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: Winogrande (5-shot)
+      type: winogrande
+      config: winogrande_xl
+      split: validation
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 87.77
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=freewheelin/free-evo-qwen72b-v0.8-re
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GSM8k (5-shot)
+      type: gsm8k
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 75.89
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=freewheelin/free-evo-qwen72b-v0.8-re
+      name: Open LLM Leaderboard
 ---
 
 # Model Card for free-evo-qwen72b-v0.8
@@ -10,7 +113,17 @@ license: mit
 ## Developed by : [Freewheelin](https://freewheelin-recruit.oopy.io/) AI Technical Team
 
 ## 2024 4th May - avg. 81.28 [Open Llm Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)   
-oops~ model type? thank you ;)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_davidkim205__Rhea-72b-v0.5)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |81.28|
+|ARC (25-Shot)                    |79.86|
+|HellaSwag (10-Shot)              |91.32|
+|MMLU (5-Shot)                    |78.00|
+|TruthfulQA (0-shot)              |74.85|
+|Winogrande (5-shot)              |87.77|
+|GSM8k (5-shot)                   |75.89|
 
 ## Method
 - We were inspired by this [Sakana project](https://sakana.ai/evolutionary-model-merge/)