Adding Evaluation Results

README.md

@@ -1,15 +1,118 @@
 ---
-license: apache-2.0
 language:
 - en
-pipeline_tag: text-generation
+license: apache-2.0
+library_name: transformers
 tags:
 - mistral
 - mixtral
 - solar
 - model-fusion
 - fusechat
-library_name: transformers
+pipeline_tag: text-generation
+model-index:
+- name: FuseChat-7B-Slerp
+  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: 62.63
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=FuseAI/FuseChat-7B-Slerp
+      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: 84.17
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=FuseAI/FuseChat-7B-Slerp
+      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: 63.9
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=FuseAI/FuseChat-7B-Slerp
+      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: 45.62
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=FuseAI/FuseChat-7B-Slerp
+      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=FuseAI/FuseChat-7B-Slerp
+      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: 62.55
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=FuseAI/FuseChat-7B-Slerp
+      name: Open LLM Leaderboard
 ---
 <p align="center" width="100%">
 </p>
@@ -410,4 +513,17 @@ If you find this work is relevant with your research or applications, please fee
   journal={arXiv preprint arXiv:2402.16107},
   year={2024}
 }
-```
+```
+# [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_FuseAI__FuseChat-7B-Slerp)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |66.39|
+|AI2 Reasoning Challenge (25-Shot)|62.63|
+|HellaSwag (10-Shot)              |84.17|
+|MMLU (5-Shot)                    |63.90|
+|TruthfulQA (0-shot)              |45.62|
+|Winogrande (5-shot)              |79.48|
+|GSM8k (5-shot)                   |62.55|
+