Adding Evaluation Results

README.md

@@ -1,12 +1,107 @@
 ---
 license: llama3
-base_model: meta-llama/Meta-Llama-3-8B
+library_name: transformers
 tags:
 - openchat
 - llama3
 - C-RLFT
-library_name: transformers
+base_model: meta-llama/Meta-Llama-3-8B
 pipeline_tag: text-generation
+model-index:
+- name: openchat-3.6-8b-20240522
+  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: 53.59
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=openchat/openchat-3.6-8b-20240522
+      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: 33.23
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=openchat/openchat-3.6-8b-20240522
+      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: 7.33
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=openchat/openchat-3.6-8b-20240522
+      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: 9.06
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=openchat/openchat-3.6-8b-20240522
+      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: 8.18
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=openchat/openchat-3.6-8b-20240522
+      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: 24.77
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=openchat/openchat-3.6-8b-20240522
+      name: Open LLM Leaderboard
 ---
 
 <div align="center">
@@ -171,4 +266,17 @@ We look forward to hearing from you and collaborating on this exciting project!
   journal={arXiv preprint arXiv:2309.11235},
   year={2023}
 }
-```
+```
+# [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_openchat__openchat-3.6-8b-20240522)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |23.06|
+|IFEval (0-Shot)    |53.59|
+|BBH (3-Shot)       |33.23|
+|MATH Lvl 5 (4-Shot)| 7.33|
+|GPQA (0-shot)      | 9.06|
+|MuSR (0-shot)      | 8.18|
+|MMLU-PRO (5-shot)  |24.77|
+