Adding Evaluation Results

README.md

@@ -1,10 +1,113 @@
 ---
-license: cc-by-nc-sa-4.0
 language:
 - en
+license: cc-by-nc-sa-4.0
 tags:
 - merge
 - slerp
+model-index:
+- name: CarbonVillain-en-10.7B-v2
+  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: 71.25
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jeonsworld/CarbonVillain-en-10.7B-v2
+      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: 88.4
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jeonsworld/CarbonVillain-en-10.7B-v2
+      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: 66.31
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jeonsworld/CarbonVillain-en-10.7B-v2
+      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: 71.94
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jeonsworld/CarbonVillain-en-10.7B-v2
+      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: 83.35
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jeonsworld/CarbonVillain-en-10.7B-v2
+      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: 65.28
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jeonsworld/CarbonVillain-en-10.7B-v2
+      name: Open LLM Leaderboard
 ---
 
 # CarbonVillain
@@ -38,4 +141,17 @@ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-le
 | MMLU (5-shot)         | 66.31   |
 | TruthfulQA (0-shot)   | 71.94   |
 | Winogrande (5-shot)   | 83.35   |
-| GSM8K (5-shot)        | 65.28   |
+| GSM8K (5-shot)        | 65.28   |
+# [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_jeonsworld__CarbonVillain-en-10.7B-v2)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |74.42|
+|AI2 Reasoning Challenge (25-Shot)|71.25|
+|HellaSwag (10-Shot)              |88.40|
+|MMLU (5-Shot)                    |66.31|
+|TruthfulQA (0-shot)              |71.94|
+|Winogrande (5-shot)              |83.35|
+|GSM8k (5-shot)                   |65.28|
+