Adding Evaluation Results

README.md

@@ -1,22 +1,4 @@
 ---
-base_model:
-- LeroyDyer/LCARS_TOP_SCORE
-- LeroyDyer/Mixtral_AI_Cyber_Matrix_2_0
-- LeroyDyer/SpydazWeb_AI_CyberTron_Ultra_7b
-- LeroyDyer/LCARS_AI_StarTrek_Computer
-- LeroyDyer/_Spydaz_Web_AI_ActionQA_Project
-- LeroyDyer/_Spydaz_Web_AI_ChatML_512K_Project
-- LeroyDyer/_Spydaz_Web_AI_ChatQA_ReAct_Project_UltraFineTuned
-- LeroyDyer/SpyazWeb_AI_DeepMind_Project
-- LeroyDyer/SpydazWeb_AI_Swahili_Project
-- LeroyDyer/_Spydaz_Web_AI_ChatQA_ReAct_Project
-- LeroyDyer/_Spydaz_Web_AI_MistralStar_001_Project
-- LeroyDyer/QuietStar_Project
-- LeroyDyer/Mixtral_BioMedical_7b
-- LeroyDyer/Mixtral_AI_CyberTron_Coder
-- LeroyDyer/_Spydaz_Web_AI_BIBLE_002
-- LeroyDyer/_Spydaz_Web_AI_ChatQA_Reasoning101_Project
-- LeroyDyer/SpydazWeb_AI_Text_AudioVision_Project
 language:
 - en
 - sw
@@ -33,18 +15,6 @@ language:
 - bm
 - su
 license: apache-2.0
-datasets:
-- neoneye/base64-decode-v2
-- neoneye/base64-encode-v1
-- VuongQuoc/Chemistry_text_to_image
-- Kamizuru00/diagram_image_to_text
-- LeroyDyer/Chemistry_text_to_image_BASE64
-- LeroyDyer/AudioCaps-Spectrograms_to_Base64
-- LeroyDyer/winogroud_text_to_imaget_BASE64
-- LeroyDyer/chart_text_to_Base64
-- LeroyDyer/diagram_image_to_text_BASE64
-- mekaneeky/salt_m2e_15_3_instruction
-- mekaneeky/SALT-languages-bible
 tags:
 - mergekit
 - merge
@@ -88,6 +58,131 @@ tags:
 - Afro-Centric
 - African-Model
 - Ancient-One
+base_model:
+- LeroyDyer/LCARS_TOP_SCORE
+- LeroyDyer/Mixtral_AI_Cyber_Matrix_2_0
+- LeroyDyer/SpydazWeb_AI_CyberTron_Ultra_7b
+- LeroyDyer/LCARS_AI_StarTrek_Computer
+- LeroyDyer/_Spydaz_Web_AI_ActionQA_Project
+- LeroyDyer/_Spydaz_Web_AI_ChatML_512K_Project
+- LeroyDyer/_Spydaz_Web_AI_ChatQA_ReAct_Project_UltraFineTuned
+- LeroyDyer/SpyazWeb_AI_DeepMind_Project
+- LeroyDyer/SpydazWeb_AI_Swahili_Project
+- LeroyDyer/_Spydaz_Web_AI_ChatQA_ReAct_Project
+- LeroyDyer/_Spydaz_Web_AI_MistralStar_001_Project
+- LeroyDyer/QuietStar_Project
+- LeroyDyer/Mixtral_BioMedical_7b
+- LeroyDyer/Mixtral_AI_CyberTron_Coder
+- LeroyDyer/_Spydaz_Web_AI_BIBLE_002
+- LeroyDyer/_Spydaz_Web_AI_ChatQA_Reasoning101_Project
+- LeroyDyer/SpydazWeb_AI_Text_AudioVision_Project
+datasets:
+- neoneye/base64-decode-v2
+- neoneye/base64-encode-v1
+- VuongQuoc/Chemistry_text_to_image
+- Kamizuru00/diagram_image_to_text
+- LeroyDyer/Chemistry_text_to_image_BASE64
+- LeroyDyer/AudioCaps-Spectrograms_to_Base64
+- LeroyDyer/winogroud_text_to_imaget_BASE64
+- LeroyDyer/chart_text_to_Base64
+- LeroyDyer/diagram_image_to_text_BASE64
+- mekaneeky/salt_m2e_15_3_instruction
+- mekaneeky/SALT-languages-bible
+model-index:
+- name: SpydazWebAI_Human_AGI
+  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: 33.88
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=LeroyDyer/SpydazWebAI_Human_AGI
+      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: 7.45
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=LeroyDyer/SpydazWebAI_Human_AGI
+      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: 0.91
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=LeroyDyer/SpydazWebAI_Human_AGI
+      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: 4.36
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=LeroyDyer/SpydazWebAI_Human_AGI
+      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: 7.38
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=LeroyDyer/SpydazWebAI_Human_AGI
+      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: 5.32
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=LeroyDyer/SpydazWebAI_Human_AGI
+      name: Open LLM Leaderboard
 ---
 
 
@@ -823,3 +918,17 @@ LM_MODEL
 
 
 
+
+# [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_LeroyDyer__SpydazWebAI_Human_AGI)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               | 9.88|
+|IFEval (0-Shot)    |33.88|
+|BBH (3-Shot)       | 7.45|
+|MATH Lvl 5 (4-Shot)| 0.91|
+|GPQA (0-shot)      | 4.36|
+|MuSR (0-shot)      | 7.38|
+|MMLU-PRO (5-shot)  | 5.32|
+