Adding Evaluation Results

README.md

@@ -1,15 +1,118 @@
 ---
+language:
+- en
+license: apache-2.0
+tags:
+- not-for-all-audiences
 datasets:
 - Intel/orca_dpo_pairs
 - athirdpath/DPO_Pairs-Roleplay-Alpaca-NSFW
 - Open-Orca/SlimOrca
 - MinervaAI/Aesir-Preview
 - allenai/ultrafeedback_binarized_cleaned
-license: apache-2.0
-language:
-- en
-tags:
-- not-for-all-audiences
+model-index:
+- name: NEBULA-23B-v1.0
+  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=TeeZee/NEBULA-23B-v1.0
+      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: 86.98
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TeeZee/NEBULA-23B-v1.0
+      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: 65.4
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TeeZee/NEBULA-23B-v1.0
+      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: 57.6
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TeeZee/NEBULA-23B-v1.0
+      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: 82.95
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TeeZee/NEBULA-23B-v1.0
+      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: 0.0
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TeeZee/NEBULA-23B-v1.0
+      name: Open LLM Leaderboard
 ---
 ### TeeZee/NEBULA-23B-v1.0 ###
 
@@ -23,4 +126,17 @@ tags:
 - for evaluation of RP and ERP more tests are needed
 
 ### Prompt template
-- Alpaca
+- Alpaca
+# [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_TeeZee__NEBULA-23B-v1.0)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |59.94|
+|AI2 Reasoning Challenge (25-Shot)|66.72|
+|HellaSwag (10-Shot)              |86.98|
+|MMLU (5-Shot)                    |65.40|
+|TruthfulQA (0-shot)              |57.60|
+|Winogrande (5-shot)              |82.95|
+|GSM8k (5-shot)                   | 0.00|
+