Adding Evaluation Results

README.md

@@ -1,3 +1,104 @@
+---
+model-index:
+- name: FuseChat-Llama-3.1-8B-Instruct
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: IFEval (0-Shot)
+      type: wis-k/instruction-following-eval
+      split: train
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: inst_level_strict_acc and prompt_level_strict_acc
+      value: 72.05
+      name: averaged accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=FuseAI%2FFuseChat-Llama-3.1-8B-Instruct
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: BBH (3-Shot)
+      type: SaylorTwift/bbh
+      split: test
+      args:
+        num_few_shot: 3
+    metrics:
+    - type: acc_norm
+      value: 30.85
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=FuseAI%2FFuseChat-Llama-3.1-8B-Instruct
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MATH Lvl 5 (4-Shot)
+      type: lighteval/MATH-Hard
+      split: test
+      args:
+        num_few_shot: 4
+    metrics:
+    - type: exact_match
+      value: 7.02
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=FuseAI%2FFuseChat-Llama-3.1-8B-Instruct
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GPQA (0-shot)
+      type: Idavidrein/gpqa
+      split: train
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 7.38
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=FuseAI%2FFuseChat-Llama-3.1-8B-Instruct
+      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: 6.15
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=FuseAI%2FFuseChat-Llama-3.1-8B-Instruct
+      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: 30.37
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=FuseAI%2FFuseChat-Llama-3.1-8B-Instruct
+      name: Open LLM Leaderboard
+---
 <p align="center" width="100%">
 </p>
 
@@ -409,3 +510,18 @@ journal={arXiv preprint arXiv:2412.03187},
 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/FuseAI__FuseChat-Llama-3.1-8B-Instruct-details)!
+Summarized results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/contents/viewer/default/train?q=FuseAI%2FFuseChat-Llama-3.1-8B-Instruct&sort[column]=Average%20%E2%AC%86%EF%B8%8F&sort[direction]=desc)!
+
+|      Metric       |Value (%)|
+|-------------------|--------:|
+|**Average**        |    25.64|
+|IFEval (0-Shot)    |    72.05|
+|BBH (3-Shot)       |    30.85|
+|MATH Lvl 5 (4-Shot)|     7.02|
+|GPQA (0-shot)      |     7.38|
+|MuSR (0-shot)      |     6.15|
+|MMLU-PRO (5-shot)  |    30.37|
+