Adding Evaluation Results (#1)

- Adding Evaluation Results (6e230e284caf2a0758fe533334923aa004bff53f)


Co-authored-by: Open LLM Leaderboard PR Bot <[email protected]>

README.md

@@ -1,13 +1,116 @@
 ---
-base_model:
-- mlabonne/NeuralDaredevil-8B-abliterated
-- nbeerbower/llama-3-spicy-abliterated-stella-8B
-- flammenai/Mahou-1.2-llama3-8B
+license: llama3
 library_name: transformers
 tags:
 - mergekit
 - merge
-license: llama3
+base_model:
+- mlabonne/NeuralDaredevil-8B-abliterated
+- nbeerbower/llama-3-spicy-abliterated-stella-8B
+- flammenai/Mahou-1.2-llama3-8B
+model-index:
+- name: llama-3-NeuralMahou
+  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: 67.41
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=lemon07r/llama-3-NeuralMahou
+      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: 83.45
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=lemon07r/llama-3-NeuralMahou
+      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: 68.63
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=lemon07r/llama-3-NeuralMahou
+      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: 58.21
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=lemon07r/llama-3-NeuralMahou
+      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: 77.74
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=lemon07r/llama-3-NeuralMahou
+      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: 72.55
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=lemon07r/llama-3-NeuralMahou
+      name: Open LLM Leaderboard
 ---
 # NeuralMahou
 
@@ -40,4 +143,17 @@ slices:
     model: nbeerbower/llama-3-spicy-abliterated-stella-8B
   - layer_range: [0, 32]
     model: mlabonne/NeuralDaredevil-8B-abliterated
-```
+```
+# [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_lemon07r__llama-3-NeuralMahou)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |71.33|
+|AI2 Reasoning Challenge (25-Shot)|67.41|
+|HellaSwag (10-Shot)              |83.45|
+|MMLU (5-Shot)                    |68.63|
+|TruthfulQA (0-shot)              |58.21|
+|Winogrande (5-shot)              |77.74|
+|GSM8k (5-shot)                   |72.55|
+