Adding Evaluation Results

README.md

@@ -1,10 +1,113 @@
 ---
+language:
+- en,
 license: other
 license_name: yi-license
 license_link: https://huggingface.co/01-ai/Yi-34B/blob/main/LICENSE
-language:
-- en,
 pipeline_tag: conversational
+model-index:
+- name: SG-Raccoon-Yi-200k-2.0
+  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: 62.54
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlinmg/SG-Raccoon-Yi-200k-2.0
+      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: 80.26
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlinmg/SG-Raccoon-Yi-200k-2.0
+      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: 73.29
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlinmg/SG-Raccoon-Yi-200k-2.0
+      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: 53.21
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlinmg/SG-Raccoon-Yi-200k-2.0
+      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: 76.32
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlinmg/SG-Raccoon-Yi-200k-2.0
+      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: 30.71
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlinmg/SG-Raccoon-Yi-200k-2.0
+      name: Open LLM Leaderboard
 ---
 <p align="center">
   <img src="https://cdn-uploads.huggingface.co/production/uploads/644ba0c76ebb3ebf7264dbe9/PWn9I-0XH7kSP_YXcyxIg.png" width="400"/>
@@ -67,4 +170,17 @@ Coming soon.
 
 - Also credits to the [01-ai](https://huggingface.co/01-ai) team for their amazing models
 
-- This merged model is inspired by [Goliath 120B](https://huggingface.co/alpindale/goliath-120b)
+- This merged model is inspired by [Goliath 120B](https://huggingface.co/alpindale/goliath-120b)
+# [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_mlinmg__SG-Raccoon-Yi-200k-2.0)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |62.72|
+|AI2 Reasoning Challenge (25-Shot)|62.54|
+|HellaSwag (10-Shot)              |80.26|
+|MMLU (5-Shot)                    |73.29|
+|TruthfulQA (0-shot)              |53.21|
+|Winogrande (5-shot)              |76.32|
+|GSM8k (5-shot)                   |30.71|
+