Adding Evaluation Results

README.md

@@ -1,5 +1,8 @@
 ---
 license: cc-by-nc-4.0
+tags:
+- merge
+- mergekit
 datasets:
 - pankajmathur/orca_mini_v1_dataset
 - openai/summarize_from_feedback
@@ -9,9 +12,109 @@ datasets:
 - PKU-Alignment/PKU-SafeRLHF
 - Intel/orca_dpo_pairs
 - allenai/ultrafeedback_binarized_cleaned
-tags:
-- merge
-- mergekit
+model-index:
+- name: piano-medley-7b
+  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: 67.58
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=chargoddard/piano-medley-7b
+      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: 85.36
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=chargoddard/piano-medley-7b
+      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: 64.49
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=chargoddard/piano-medley-7b
+      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: 61.42
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=chargoddard/piano-medley-7b
+      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: 79.16
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=chargoddard/piano-medley-7b
+      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: 56.56
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=chargoddard/piano-medley-7b
+      name: Open LLM Leaderboard
 ---
 
 Another experiment in the line of [loyal-piano-m7](https://huggingface.co/chargoddard/loyal-piano-m7).
@@ -55,4 +158,17 @@ parameters:
   density: 0.4
   normalize: true
   int8_mask: true
-```
+```
+# [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__piano-medley-7b)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |69.10|
+|AI2 Reasoning Challenge (25-Shot)|67.58|
+|HellaSwag (10-Shot)              |85.36|
+|MMLU (5-Shot)                    |64.49|
+|TruthfulQA (0-shot)              |61.42|
+|Winogrande (5-shot)              |79.16|
+|GSM8k (5-shot)                   |56.56|
+