Adding Evaluation Results (#4)

- Adding Evaluation Results (7d39d6df03673e0b1e3b0d0c2f509e11353fbd0f)


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

README.md

@@ -1,8 +1,8 @@
 ---
 language:
 - en
-library_name: transformers
 license: llama2
+library_name: transformers
 datasets:
 - garage-bAInd/Open-Platypus
 - tatsu-lab/alpaca
@@ -13,6 +13,109 @@ datasets:
 - psmathur/WizardLM_Orca
 - psmathur/alpaca_orca
 - psmathur/dolly-v2_orca
+model-index:
+- name: model_007_v2
+  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: 71.42
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=psmathur/model_007_v2
+      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: 87.31
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=psmathur/model_007_v2
+      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: 68.58
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=psmathur/model_007_v2
+      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: 62.65
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=psmathur/model_007_v2
+      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: 84.14
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=psmathur/model_007_v2
+      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: 28.66
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=psmathur/model_007_v2
+      name: Open LLM Leaderboard
 ---
 
 It's a preview version of psmathur/model_007, Sorry for the naming confusion. 
@@ -209,3 +312,17 @@ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-le
 | Winogrande (5-shot)   | 84.14   |
 | GSM8K (5-shot)        | 28.66        |
 | DROP (3-shot)         | 31.38         |
+
+# [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_psmathur__model_007_v2)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |67.13|
+|AI2 Reasoning Challenge (25-Shot)|71.42|
+|HellaSwag (10-Shot)              |87.31|
+|MMLU (5-Shot)                    |68.58|
+|TruthfulQA (0-shot)              |62.65|
+|Winogrande (5-shot)              |84.14|
+|GSM8k (5-shot)                   |28.66|
+