Adding Evaluation Results

README.md

@@ -1,16 +1,111 @@
 ---
-license: llama3
-datasets:
-- HuggingFaceH4/ultrafeedback_binarized
 language:
 - en
+license: llama3
 library_name: transformers
 tags:
 - tenyx-fine-tuning
 - dpo
 - tenyxchat
 - llama3
+datasets:
+- HuggingFaceH4/ultrafeedback_binarized
 pipeline_tag: text-generation
+model-index:
+- name: Llama3-TenyxChat-70B
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: IFEval (0-Shot)
+      type: HuggingFaceH4/ifeval
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: inst_level_strict_acc and prompt_level_strict_acc
+      value: 80.87
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=tenyx/Llama3-TenyxChat-70B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: BBH (3-Shot)
+      type: BBH
+      args:
+        num_few_shot: 3
+    metrics:
+    - type: acc_norm
+      value: 49.62
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=tenyx/Llama3-TenyxChat-70B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MATH Lvl 5 (4-Shot)
+      type: hendrycks/competition_math
+      args:
+        num_few_shot: 4
+    metrics:
+    - type: exact_match
+      value: 22.66
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=tenyx/Llama3-TenyxChat-70B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GPQA (0-shot)
+      type: Idavidrein/gpqa
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 6.82
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=tenyx/Llama3-TenyxChat-70B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MuSR (0-shot)
+      type: TAUR-Lab/MuSR
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 12.52
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=tenyx/Llama3-TenyxChat-70B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU-PRO (5-shot)
+      type: TIGER-Lab/MMLU-Pro
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 46.78
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=tenyx/Llama3-TenyxChat-70B
+      name: Open LLM Leaderboard
 ---
 # TenyxChat: Language Model Alignment using Tenyx Fine-tuning
 
@@ -138,4 +233,17 @@ If you use Llama3-TenyxChat-70B for your research, cite us as
       author={Tenyx},
       year={2024},
 }
-```
+```
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_tenyx__Llama3-TenyxChat-70B)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |36.54|
+|IFEval (0-Shot)    |80.87|
+|BBH (3-Shot)       |49.62|
+|MATH Lvl 5 (4-Shot)|22.66|
+|GPQA (0-shot)      | 6.82|
+|MuSR (0-shot)      |12.52|
+|MMLU-PRO (5-shot)  |46.78|
+