Adding Evaluation Results

README.md

@@ -1,12 +1,115 @@
 ---
 license: apache-2.0
-base_model: mistralai/Mistral-7B-v0.1
+library_name: transformers
 tags:
 - openchat
 - mistral
 - C-RLFT
-library_name: transformers
+base_model: mistralai/Mistral-7B-v0.1
 pipeline_tag: text-generation
+model-index:
+- name: openchat-3.5-0106
+  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: 66.04
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=openchat/openchat-3.5-0106
+      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: 82.93
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=openchat/openchat-3.5-0106
+      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: 65.04
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=openchat/openchat-3.5-0106
+      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: 51.9
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=openchat/openchat-3.5-0106
+      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: 81.77
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=openchat/openchat-3.5-0106
+      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: 68.16
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=openchat/openchat-3.5-0106
+      name: Open LLM Leaderboard
 ---
 <div align="center">
   <img src="https://raw.githubusercontent.com/imoneoi/openchat/master/assets/logo_new.png" style="width: 65%">
@@ -272,3 +375,17 @@ Our OpenChat 3.5 code and models are distributed under the Apache License 2.0.
 
 * Wang Guan [imonenext@gmail.com], Cheng Sijie [csj23@mails.tsinghua.edu.cn], Alpay Ariyak [aariyak@wpi.edu]
 * We look forward to hearing you and collaborating on this exciting project!
+
+# [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_openchat__openchat-3.5-0106)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |69.30|
+|AI2 Reasoning Challenge (25-Shot)|66.04|
+|HellaSwag (10-Shot)              |82.93|
+|MMLU (5-Shot)                    |65.04|
+|TruthfulQA (0-shot)              |51.90|
+|Winogrande (5-shot)              |81.77|
+|GSM8k (5-shot)                   |68.16|
+