Adding Evaluation Results

README.md

@@ -1,11 +1,5 @@
 ---
 license: artistic-2.0
-datasets:
-- Severian/Biomimicry
-- emrgnt-cmplxty/sciphi-textbooks-are-all-you-need
-- fmars/wiki_stem
-- fblgit/tree-of-knowledge
-- Severian/Bio-Design-Process
 tags:
 - chemistry
 - biology
@@ -17,9 +11,118 @@ tags:
 - biomimicry
 - fauna
 - flora
-pipeline_tag: text-generation
+datasets:
+- Severian/Biomimicry
+- emrgnt-cmplxty/sciphi-textbooks-are-all-you-need
+- fmars/wiki_stem
+- fblgit/tree-of-knowledge
+- Severian/Bio-Design-Process
 metrics:
 - accuracy
+pipeline_tag: text-generation
+model-index:
+- name: ANIMA-Phi-Neptune-Mistral-7B-v4
+  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: 55.46
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Severian/ANIMA-Phi-Neptune-Mistral-7B-v4
+      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: 77.63
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Severian/ANIMA-Phi-Neptune-Mistral-7B-v4
+      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: 53.12
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Severian/ANIMA-Phi-Neptune-Mistral-7B-v4
+      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: 59.01
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Severian/ANIMA-Phi-Neptune-Mistral-7B-v4
+      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: 73.48
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Severian/ANIMA-Phi-Neptune-Mistral-7B-v4
+      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: 14.94
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Severian/ANIMA-Phi-Neptune-Mistral-7B-v4
+      name: Open LLM Leaderboard
 ---
 # ANIMA-Phi-Neptune-Mistral-7B: Biomimicry Enhanced LLM
 
@@ -186,4 +289,17 @@ that help protect our environment from contamination.
 
 This project is licensed under Artistic-2.0
 
-**This model is for research purposes only and restricted from any commercial use**
+**This model is for research purposes only and restricted from any commercial use**
+# [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_Severian__ANIMA-Phi-Neptune-Mistral-7B-v4)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |55.61|
+|AI2 Reasoning Challenge (25-Shot)|55.46|
+|HellaSwag (10-Shot)              |77.63|
+|MMLU (5-Shot)                    |53.12|
+|TruthfulQA (0-shot)              |59.01|
+|Winogrande (5-shot)              |73.48|
+|GSM8k (5-shot)                   |14.94|
+