Adding Evaluation Results

README.md

@@ -1,8 +1,111 @@
 ---
+license: apache-2.0
 datasets:
 - openagi-project/OpenAGI-set-dpo-v0.1
 base_model: freecs/ThetaWave-7B-v0.1
-license: apache-2.0
+model-index:
+- name: OpenAGI-7B-v0.1
+  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: 66.72
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=openagi-project/OpenAGI-7B-v0.1
+      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: 86.13
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=openagi-project/OpenAGI-7B-v0.1
+      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: 63.53
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=openagi-project/OpenAGI-7B-v0.1
+      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: 69.55
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=openagi-project/OpenAGI-7B-v0.1
+      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: 79.48
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=openagi-project/OpenAGI-7B-v0.1
+      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: 56.63
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=openagi-project/OpenAGI-7B-v0.1
+      name: Open LLM Leaderboard
 ---
 
 # OpenAGI-7B-v0.1
@@ -36,4 +139,17 @@ print(decoded[0])
  |- [GR](https://twitter.com/gr_username)
 
 
-If you'd like to support this project, kindly consider making a [donation](https://freecs.org/donate).
+If you'd like to support this project, kindly consider making a [donation](https://freecs.org/donate).
+# [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_openagi-project__OpenAGI-7B-v0.1)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |70.34|
+|AI2 Reasoning Challenge (25-Shot)|66.72|
+|HellaSwag (10-Shot)              |86.13|
+|MMLU (5-Shot)                    |63.53|
+|TruthfulQA (0-shot)              |69.55|
+|Winogrande (5-shot)              |79.48|
+|GSM8k (5-shot)                   |56.63|
+