Adding Evaluation Results

README.md

@@ -1,14 +1,117 @@
 ---
 language:
 - en
+license: other
 tags:
 - llama
-license: other
 metrics:
 - MMLU
-- ARC 
+- ARC
 - HellaSwag
 - TruthfulQA
+model-index:
+- name: Platypus-30B
+  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: 64.59
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=lilloukas/Platypus-30B
+      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: 84.24
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=lilloukas/Platypus-30B
+      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: 64.19
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=lilloukas/Platypus-30B
+      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: 45.35
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=lilloukas/Platypus-30B
+      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: 81.37
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=lilloukas/Platypus-30B
+      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: 14.4
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=lilloukas/Platypus-30B
+      name: Open LLM Leaderboard
 ---
 
 # 🥳 Platypus-30B has arrived! 
@@ -99,3 +202,17 @@ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-le
 | Winogrande (5-shot)   | 81.37   |
 | GSM8K (5-shot)        | 14.4        |
 | DROP (3-shot)         | 45.65         |
+
+# [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_lilloukas__Platypus-30B)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |59.03|
+|AI2 Reasoning Challenge (25-Shot)|64.59|
+|HellaSwag (10-Shot)              |84.24|
+|MMLU (5-Shot)                    |64.19|
+|TruthfulQA (0-shot)              |45.35|
+|Winogrande (5-shot)              |81.37|
+|GSM8k (5-shot)                   |14.40|
+