Adding Evaluation Results

README.md

@@ -1,8 +1,5 @@
 ---
 license: other
-license_name: helpingai
-license_link: LICENSE.md
-pipeline_tag: text-generation
 tags:
 - HelpingAI
 - Emotionally Intelligent
@@ -11,6 +8,104 @@ datasets:
 - OEvortex/SentimentSynth
 - OEvortex/EmotionalIntelligence-75k
 - Abhaykoul/Emotion
+license_name: helpingai
+license_link: LICENSE.md
+pipeline_tag: text-generation
+model-index:
+- name: HelpingAI-15B
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: IFEval (0-Shot)
+      type: HuggingFaceH4/ifeval
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: inst_level_strict_acc and prompt_level_strict_acc
+      value: 20.3
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=OEvortex/HelpingAI-15B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: BBH (3-Shot)
+      type: BBH
+      args:
+        num_few_shot: 3
+    metrics:
+    - type: acc_norm
+      value: 1.82
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=OEvortex/HelpingAI-15B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MATH Lvl 5 (4-Shot)
+      type: hendrycks/competition_math
+      args:
+        num_few_shot: 4
+    metrics:
+    - type: exact_match
+      value: 0.0
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=OEvortex/HelpingAI-15B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GPQA (0-shot)
+      type: Idavidrein/gpqa
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 1.01
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=OEvortex/HelpingAI-15B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MuSR (0-shot)
+      type: TAUR-Lab/MuSR
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 2.73
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=OEvortex/HelpingAI-15B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU-PRO (5-shot)
+      type: TIGER-Lab/MMLU-Pro
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 1.24
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=OEvortex/HelpingAI-15B
+      name: Open LLM Leaderboard
 ---
 
 # HelpingAI-15B: Emotionally Intelligent Conversational AI
@@ -166,4 +261,17 @@ Remember, it's important to choose devices that fit your specific needs and budg
 
 Also, make sure to test and maintain these devices regularly to ensure they're in working order. 🔧
 
-If you have any specific questions about any of these devices, feel free to ask! I'm here to help you stay safe and secure! 🌈
+If you have any specific questions about any of these devices, feel free to ask! I'm here to help you stay safe and secure! 🌈
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_OEvortex__HelpingAI-15B)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               | 4.52|
+|IFEval (0-Shot)    |20.30|
+|BBH (3-Shot)       | 1.82|
+|MATH Lvl 5 (4-Shot)| 0.00|
+|GPQA (0-shot)      | 1.01|
+|MuSR (0-shot)      | 2.73|
+|MMLU-PRO (5-shot)  | 1.24|
+