Adding Evaluation Results (#1)

- Adding Evaluation Results (f2ec96ad8ce8e25997141b089ebf556787510e88)


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

README.md

@@ -4,6 +4,109 @@ datasets:
 - lodrick-the-lafted/Hermes-217K
 - garage-bAInd/Open-Platypus
 - jondurbin/airoboros-3.2
+model-index:
+- name: Grafted-Hermetic-Platypus-C-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: 58.96
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=lodrick-the-lafted/Grafted-Hermetic-Platypus-C-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: 82.77
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=lodrick-the-lafted/Grafted-Hermetic-Platypus-C-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: 62.08
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=lodrick-the-lafted/Grafted-Hermetic-Platypus-C-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: 60.87
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=lodrick-the-lafted/Grafted-Hermetic-Platypus-C-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: 77.74
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=lodrick-the-lafted/Grafted-Hermetic-Platypus-C-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: 43.9
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=lodrick-the-lafted/Grafted-Hermetic-Platypus-C-2x7B
+      name: Open LLM Leaderboard
 ---
 
 <img src=https://huggingface.co/lodrick-the-lafted/Grafted-Hermetic-Platypus-C-2x7B/resolve/main/ghp.png>
@@ -63,3 +166,17 @@ outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7,
 print(outputs[0]["generated_text"])
 ```
 
+
+# [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_lodrick-the-lafted__Grafted-Hermetic-Platypus-C-2x7B)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |64.39|
+|AI2 Reasoning Challenge (25-Shot)|58.96|
+|HellaSwag (10-Shot)              |82.77|
+|MMLU (5-Shot)                    |62.08|
+|TruthfulQA (0-shot)              |60.87|
+|Winogrande (5-shot)              |77.74|
+|GSM8k (5-shot)                   |43.90|
+