Adding Evaluation Results

README.md

@@ -1,9 +1,112 @@
 ---
 license: other
-license_name: yi-license
-license_link: LICENSE
 datasets:
 - garage-bAInd/Open-Platypus
+license_name: yi-license
+license_link: LICENSE
+model-index:
+- name: platypus-yi-34b
+  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: 68.43
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=bhenrym14/platypus-yi-34b
+      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: 85.21
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=bhenrym14/platypus-yi-34b
+      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: 78.13
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=bhenrym14/platypus-yi-34b
+      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: 54.48
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=bhenrym14/platypus-yi-34b
+      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: 84.06
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=bhenrym14/platypus-yi-34b
+      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: 59.82
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=bhenrym14/platypus-yi-34b
+      name: Open LLM Leaderboard
 ---
 
 # Instruction tune of Yi-34b with Open-Platypus (fp16)
@@ -24,3 +127,17 @@ Use as you would any llama-2 model.
 ## Prompting:
 
 Model was trained with legacy airoboros <2.0 system prompt. See [bhenrym14/airoboros-33b-gpt4-1.4.1-lxctx-PI-16384-fp16](https://huggingface.co/bhenrym14/airoboros-33b-gpt4-1.4.1-lxctx-PI-16384-fp16) model card for details.
+
+# [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_bhenrym14__platypus-yi-34b)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |71.69|
+|AI2 Reasoning Challenge (25-Shot)|68.43|
+|HellaSwag (10-Shot)              |85.21|
+|MMLU (5-Shot)                    |78.13|
+|TruthfulQA (0-shot)              |54.48|
+|Winogrande (5-shot)              |84.06|
+|GSM8k (5-shot)                   |59.82|
+