Adding Evaluation Results (#3)

- Adding Evaluation Results (b570767b61691b2d33d974e54f576c6dfc07d079)


Co-authored-by: Open LLM Leaderboard PR Bot <[email protected]>

README.md

@@ -1,15 +1,118 @@
 ---
-license: apache-2.0
 language:
 - en
-pipeline_tag: text-generation
+license: apache-2.0
+library_name: transformers
 tags:
 - llama
 - open-llama
 - mpt
 - model-fusion
 - fusellm
-library_name: transformers
+pipeline_tag: text-generation
+model-index:
+- name: FuseLLM-7B
+  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: 53.24
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Wanfq/FuseLLM-7B
+      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: 78.72
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Wanfq/FuseLLM-7B
+      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: 47.93
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Wanfq/FuseLLM-7B
+      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: 38.17
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Wanfq/FuseLLM-7B
+      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: 74.03
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Wanfq/FuseLLM-7B
+      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: 14.33
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Wanfq/FuseLLM-7B
+      name: Open LLM Leaderboard
 ---
 <p align="center" width="100%">
 </p>
@@ -375,4 +478,17 @@ If you find this work is relevant with your research or applications, please fee
     year={2024},
     url={https://openreview.net/pdf?id=jiDsk12qcz}
 }
-```
+```
+# [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_Wanfq__FuseLLM-7B)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |51.07|
+|AI2 Reasoning Challenge (25-Shot)|53.24|
+|HellaSwag (10-Shot)              |78.72|
+|MMLU (5-Shot)                    |47.93|
+|TruthfulQA (0-shot)              |38.17|
+|Winogrande (5-shot)              |74.03|
+|GSM8k (5-shot)                   |14.33|
+