Adding Evaluation Results (#1)

- Adding Evaluation Results (129ecc8d7c0ccef07c3c791c72513e3dee883d73)


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

README.md

@@ -6,6 +6,109 @@ tags:
 - lazymergekit
 - dvilasuero/DistilabelBeagle14-7B
 - teknium/OpenHermes-2.5-Mistral-7B
+model-index:
+- name: DistilabelCerberus-7B-slerp
+  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: 68.17
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Stopwolf/DistilabelCerberus-7B-slerp
+      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: 86.78
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Stopwolf/DistilabelCerberus-7B-slerp
+      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: 64.2
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Stopwolf/DistilabelCerberus-7B-slerp
+      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: 60.93
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Stopwolf/DistilabelCerberus-7B-slerp
+      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: 79.48
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Stopwolf/DistilabelCerberus-7B-slerp
+      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: 69.83
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Stopwolf/DistilabelCerberus-7B-slerp
+      name: Open LLM Leaderboard
 ---
 
 # DistilabelCerberus-7B-slerp
@@ -41,4 +144,17 @@ dtype: bfloat16
 |-----------------------------|-------|-----------|-------------|------------|-------|---|---|
 | OpenHermes-2.5-Mistral-7B   | 61.26 | 65.22     | 52.24       | 78.06      | 26.08 |   |   |
 | DistilabelBeagle14-7B       | ?     | ?         | 71.66       | ?          | ?     |   |   |
-| DistilabelCerberus-7B-slerp | 65.44 | 69.29     | 60.93       | 79.48      | 69.82 |   |   |
+| DistilabelCerberus-7B-slerp | 65.44 | 69.29     | 60.93       | 79.48      | 69.82 |   |   |
+# [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_Stopwolf__DistilabelCerberus-7B-slerp)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |71.56|
+|AI2 Reasoning Challenge (25-Shot)|68.17|
+|HellaSwag (10-Shot)              |86.78|
+|MMLU (5-Shot)                    |64.20|
+|TruthfulQA (0-shot)              |60.93|
+|Winogrande (5-shot)              |79.48|
+|GSM8k (5-shot)                   |69.83|
+