Adding Evaluation Results

README.md

@@ -1,5 +1,10 @@
 ---
+language:
+- en
 license: mit
+tags:
+- merge
+- slerp
 datasets:
 - Open-Orca/OpenOrca
 - conceptofmind/cot_submix_original
@@ -7,15 +12,113 @@ datasets:
 - conceptofmind/niv2_submix_original
 - conceptofmind/flan2021_submix_original
 - ehartford/dolphin
-language:
-- en
-tags:
-- merge
-- slerp
-inference: false
 metrics:
 - accuracy
 - bleu
+inference: false
+model-index:
+- name: Dorflan
+  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: 54.44
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=formulae/Dorflan
+      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: 75.78
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=formulae/Dorflan
+      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: 51.36
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=formulae/Dorflan
+      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: 51.17
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=formulae/Dorflan
+      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: 72.61
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=formulae/Dorflan
+      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: 0.38
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=formulae/Dorflan
+      name: Open LLM Leaderboard
 ---
 <h1 style="text-align: center">Dorflan</h1>
 <h2 style="text-align: center">An experimental model</h2>
@@ -80,3 +183,17 @@ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-le
 | Winogrande (5-shot)   | 72.61   |
 | GSM8K (5-shot)        | 0.38        |
 | DROP (3-shot)         | 26.37         |
+
+# [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_formulae__Dorflan)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |50.96|
+|AI2 Reasoning Challenge (25-Shot)|54.44|
+|HellaSwag (10-Shot)              |75.78|
+|MMLU (5-Shot)                    |51.36|
+|TruthfulQA (0-shot)              |51.17|
+|Winogrande (5-shot)              |72.61|
+|GSM8k (5-shot)                   | 0.38|
+