Adding Evaluation Results

README.md

@@ -1,19 +1,121 @@
 ---
 language:
 - en
-thumbnail: null
+license: llama2
 tags:
 - text generation
 - instruct
-pipeline_tag: text-generation
-inference: false
-license: llama2
 datasets:
 - PygmalionAI/PIPPA
 - Open-Orca/OpenOrca
 - Norquinal/claude_multiround_chat_30k
 - jondurbin/airoboros-gpt4-1.4.1
 - databricks/databricks-dolly-15k
+pipeline_tag: text-generation
+inference: false
+model-index:
+- name: pygmalion-2-13b
+  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: 60.32
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=PygmalionAI/pygmalion-2-13b
+      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: 82.37
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=PygmalionAI/pygmalion-2-13b
+      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: 56.02
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=PygmalionAI/pygmalion-2-13b
+      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: 42.22
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=PygmalionAI/pygmalion-2-13b
+      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: 78.06
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=PygmalionAI/pygmalion-2-13b
+      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: 11.75
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=PygmalionAI/pygmalion-2-13b
+      name: Open LLM Leaderboard
 ---
 <h1 style="text-align: center">Pygmalion-2 13B</h1>
 <h2 style="text-align: center">An instruction-tuned Llama-2 biased towards fiction writing and conversation.</h2>
@@ -66,3 +168,17 @@ As such, it was **not** fine-tuned to be safe and harmless: the base model _and_
 We would like to thank [SpicyChat](https://spicychat.ai/) for sponsoring the training for this model.
 
 [<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)
+
+# [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_PygmalionAI__pygmalion-2-13b)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |55.12|
+|AI2 Reasoning Challenge (25-Shot)|60.32|
+|HellaSwag (10-Shot)              |82.37|
+|MMLU (5-Shot)                    |56.02|
+|TruthfulQA (0-shot)              |42.22|
+|Winogrande (5-shot)              |78.06|
+|GSM8k (5-shot)                   |11.75|
+