Adding Evaluation Results

README.md

@@ -4,6 +4,109 @@ language:
 license: apache-2.0
 tags:
 - merge
+model-index:
+- name: NeuralHermes-MoE-2x7B
+  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: 62.12
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ibndias/NeuralHermes-MoE-2x7B
+      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: 84.21
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ibndias/NeuralHermes-MoE-2x7B
+      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: 64.56
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ibndias/NeuralHermes-MoE-2x7B
+      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: 43.61
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ibndias/NeuralHermes-MoE-2x7B
+      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: 78.14
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ibndias/NeuralHermes-MoE-2x7B
+      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: 51.86
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ibndias/NeuralHermes-MoE-2x7B
+      name: Open LLM Leaderboard
 ---
 
 # NeuralHermes-MoE-2x7B
@@ -49,4 +152,17 @@ Output:
 >done
 >```
 >Save the script with a.sh extension (e.g., scan_ports.sh) and make it executable by running `chmod +x scan_ports.sh`. Then, run the script by executing `./scan_ports.sh`.
->...
+>...
+# [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_ibndias__NeuralHermes-MoE-2x7B)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |64.08|
+|AI2 Reasoning Challenge (25-Shot)|62.12|
+|HellaSwag (10-Shot)              |84.21|
+|MMLU (5-Shot)                    |64.56|
+|TruthfulQA (0-shot)              |43.61|
+|Winogrande (5-shot)              |78.14|
+|GSM8k (5-shot)                   |51.86|
+