Adding Evaluation Results (#1)

- Adding Evaluation Results (b0153a977032b09e493de38007aa323df34b378a)


Co-authored-by: Open LLM Leaderboard PR Bot <leaderboard-pr-bot@users.noreply.huggingface.co>

README.md

@@ -1,7 +1,110 @@
 ---
-license: cc-by-nc-4.0
 language:
 - en
+license: cc-by-nc-4.0
+model-index:
+- name: Dionysus-Mistral-m3-v6
+  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: 63.14
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=decem/Dionysus-Mistral-m3-v6
+      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: 84.51
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=decem/Dionysus-Mistral-m3-v6
+      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: 62.82
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=decem/Dionysus-Mistral-m3-v6
+      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: 49.49
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=decem/Dionysus-Mistral-m3-v6
+      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: 78.45
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=decem/Dionysus-Mistral-m3-v6
+      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: 64.22
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=decem/Dionysus-Mistral-m3-v6
+      name: Open LLM Leaderboard
 ---
 # Dionysus-Mistral-m3-v6 - A Fine-tuned Language Model
 
@@ -36,4 +139,17 @@ stop_words: </s>
 ```
 
 ## Open LLM Leaderboard Evaluation Details
-[https://huggingface.co/datasets/open-llm-leaderboard/details_decem__Dionysus-Mistral-m3-v6](https://huggingface.co/datasets/open-llm-leaderboard/details_decem__Dionysus-Mistral-m3-v6)
+[https://huggingface.co/datasets/open-llm-leaderboard/details_decem__Dionysus-Mistral-m3-v6](https://huggingface.co/datasets/open-llm-leaderboard/details_decem__Dionysus-Mistral-m3-v6)
+# [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_decem__Dionysus-Mistral-m3-v6)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |67.10|
+|AI2 Reasoning Challenge (25-Shot)|63.14|
+|HellaSwag (10-Shot)              |84.51|
+|MMLU (5-Shot)                    |62.82|
+|TruthfulQA (0-shot)              |49.49|
+|Winogrande (5-shot)              |78.45|
+|GSM8k (5-shot)                   |64.22|
+