Adding Evaluation Results

README.md

@@ -7,6 +7,109 @@ tags:
 - mlabonne/NeuralDaredevil-7B
 - Gille/StrangeMerges_21-7B-slerp
 - CultriX/NeuralTrix-7B-dpo
+model-index:
+- name: pikus-pikantny-7B-dare
+  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: 72.18
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=CorticalStack/pikus-pikantny-7B-dare
+      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: 88.56
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=CorticalStack/pikus-pikantny-7B-dare
+      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: 65.0
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=CorticalStack/pikus-pikantny-7B-dare
+      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: 73.29
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=CorticalStack/pikus-pikantny-7B-dare
+      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: 83.43
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=CorticalStack/pikus-pikantny-7B-dare
+      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: 70.89
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=CorticalStack/pikus-pikantny-7B-dare
+      name: Open LLM Leaderboard
 ---
 
 <img src="pikus-pikantny.png" alt="Pikus pikantny logo" width="800" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
@@ -43,4 +146,17 @@ base_model: bardsai/jaskier-7b-dpo-v5.6
 parameters:
   int8_mask: true
 dtype: bfloat16
-```
+```
+# [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_CorticalStack__pikus-pikantny-7B-dare)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |75.56|
+|AI2 Reasoning Challenge (25-Shot)|72.18|
+|HellaSwag (10-Shot)              |88.56|
+|MMLU (5-Shot)                    |65.00|
+|TruthfulQA (0-shot)              |73.29|
+|Winogrande (5-shot)              |83.43|
+|GSM8k (5-shot)                   |70.89|
+