Adding Evaluation Results

README.md

@@ -1,9 +1,112 @@
 ---
-license: cc-by-sa-4.0
 language:
 - en
 - ko
+license: cc-by-sa-4.0
 pipeline_tag: text-generation
+model-index:
+- name: PiVoT-10.7B-Mistral-v0.2
+  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: 63.31
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=maywell/PiVoT-10.7B-Mistral-v0.2
+      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: 81.68
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=maywell/PiVoT-10.7B-Mistral-v0.2
+      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: 59.86
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=maywell/PiVoT-10.7B-Mistral-v0.2
+      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: 58.23
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=maywell/PiVoT-10.7B-Mistral-v0.2
+      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: 80.03
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=maywell/PiVoT-10.7B-Mistral-v0.2
+      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: 42.38
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=maywell/PiVoT-10.7B-Mistral-v0.2
+      name: Open LLM Leaderboard
 ---
 
 # PiVoT-10.7B-Mistral-v0.2
@@ -21,4 +124,17 @@ Follow me on twitter: https://twitter.com/stablefluffy
 
 Consider Support me making these model alone: https://www.buymeacoffee.com/mwell or with Runpod Credit Gift 💕
 
-Contact me on Telegram: https://t.me/AlzarTakkarsen
+Contact me on Telegram: https://t.me/AlzarTakkarsen
+# [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__PiVoT-10.7B-Mistral-v0.2)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |64.25|
+|AI2 Reasoning Challenge (25-Shot)|63.31|
+|HellaSwag (10-Shot)              |81.68|
+|MMLU (5-Shot)                    |59.86|
+|TruthfulQA (0-shot)              |58.23|
+|Winogrande (5-shot)              |80.03|
+|GSM8k (5-shot)                   |42.38|
+