Adding Evaluation Results

README.md

@@ -1,15 +1,118 @@
 ---
+language:
+- en
 license: cc-by-nc-4.0
+tags:
+- mistral
 datasets:
 - pankajmathur/orca_mini_v1_dataset
 - openai/summarize_from_feedback
 - PygmalionAI/PIPPA
 - chargoddard/rpguild
 - lemonilia/LimaRP
-language:
-- en
-tags:
-- mistral
+model-index:
+- name: loyal-piano-m7
+  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: 66.72
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=chargoddard/loyal-piano-m7
+      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: 85.03
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=chargoddard/loyal-piano-m7
+      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: 64.43
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=chargoddard/loyal-piano-m7
+      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: 60.03
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=chargoddard/loyal-piano-m7
+      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: 79.08
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=chargoddard/loyal-piano-m7
+      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: 56.71
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=chargoddard/loyal-piano-m7
+      name: Open LLM Leaderboard
 ---
 
 [<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
@@ -34,4 +137,17 @@ Dataset composition:
 | summarize_from_feedback | 9k | 26% |
 | orca_mini_v1_dataset | 5.6k | 17% |
 | rpguild | 2.86k | 8% |
-| LimaRP | 2k | 6% |
+| LimaRP | 2k | 6% |
+# [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_chargoddard__loyal-piano-m7)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |68.67|
+|AI2 Reasoning Challenge (25-Shot)|66.72|
+|HellaSwag (10-Shot)              |85.03|
+|MMLU (5-Shot)                    |64.43|
+|TruthfulQA (0-shot)              |60.03|
+|Winogrande (5-shot)              |79.08|
+|GSM8k (5-shot)                   |56.71|
+