Adding Evaluation Results

README.md

@@ -1,8 +1,111 @@
 ---
-license: cc-by-sa-4.0
 language:
 - ko
 - en
+license: cc-by-sa-4.0
+model-index:
+- name: kiqu-70b
+  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: 72.1
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=maywell/kiqu-70b
+      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: 87.94
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=maywell/kiqu-70b
+      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: 74.93
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=maywell/kiqu-70b
+      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: 63.48
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=maywell/kiqu-70b
+      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: 84.85
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=maywell/kiqu-70b
+      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: 68.46
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=maywell/kiqu-70b
+      name: Open LLM Leaderboard
 ---
 
 # **kiqu-70b** [(Arena Leaderboard)](https://huggingface.co/spaces/instructkr/ko-chatbot-arena-leaderboard)
@@ -80,4 +183,17 @@ This model's training got sponsered by no one but support from people around Ear
 
 Contact Me on Discord - is.maywell
 
-Follow me on twitter - https://twitter.com/stablefluffy
+Follow me on twitter - https://twitter.com/stablefluffy
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_maywell__kiqu-70b)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |75.29|
+|AI2 Reasoning Challenge (25-Shot)|72.10|
+|HellaSwag (10-Shot)              |87.94|
+|MMLU (5-Shot)                    |74.93|
+|TruthfulQA (0-shot)              |63.48|
+|Winogrande (5-shot)              |84.85|
+|GSM8k (5-shot)                   |68.46|
+