Update README.md

README.md

@@ -22,6 +22,110 @@ extra_gated_fields:
       - label: Other
         value: other
   You agree to not use the model to conduct experiments that cause harm to human subjects or use it to obtain illeagal knowladge and I also agree to use this model for non-commercial use ONLY: checkbox
+
+model-index:
+- name: Monah-8b
+  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: 58.87
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=hooking-dev/Monah-8b
+      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: 80.7
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=hooking-dev/Monah-8b
+      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: 64.69
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=hooking-dev/Monah-8b
+      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: 43.2
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=hooking-dev/Monah-8b
+      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: 76.64
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=hooking-dev/Monah-8b
+      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: 42.61
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=hooking-dev/Monah-8b
+      name: Open LLM Leaderboard
 ---
 
 [<img src="https://ai.hooking.co.il/upload/images/logo/0qUf-dashboard-hookingai-logo.png"/>](https://software.hooking.ltd/)
@@ -128,3 +232,16 @@ The model is available under the Apache-2.0 license.
   year={2024},
   publisher={Hooking}
 }
+
+# [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_hooking-dev__Monah-8b)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |61.12|
+|AI2 Reasoning Challenge (25-Shot)|58.87|
+|HellaSwag (10-Shot)              |80.70|
+|MMLU (5-Shot)                    |64.69|
+|TruthfulQA (0-shot)              |43.20|
+|Winogrande (5-shot)              |76.64|
+|GSM8k (5-shot)                   |42.61|