Adding Evaluation Results (#1)

- Adding Evaluation Results (79c2a6040e682d39d290ad1375a77409df75b366)


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

README.md

@@ -1,15 +1,117 @@
 ---
-datasets:
-- Open-Orca/OpenOrca
 language:
 - zh
 - en
+license: other
 library_name: transformers
+datasets:
+- Open-Orca/OpenOrca
 pipeline_tag: text-generation
-license: other
 license_name: tongyi-qianwen-research
-license_link: >-
-  https://huggingface.co/Qwen/Qwen1.5-32B/blob/main/LICENSE
+license_link: https://huggingface.co/Qwen/Qwen1.5-32B/blob/main/LICENSE
+model-index:
+- name: Quark-464M-v0.1.alpha
+  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: 31.4
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=raincandy-u/Quark-464M-v0.1.alpha
+      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: 47.31
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=raincandy-u/Quark-464M-v0.1.alpha
+      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: 34.55
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=raincandy-u/Quark-464M-v0.1.alpha
+      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: 41.84
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=raincandy-u/Quark-464M-v0.1.alpha
+      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: 55.17
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=raincandy-u/Quark-464M-v0.1.alpha
+      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: 3.79
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=raincandy-u/Quark-464M-v0.1.alpha
+      name: Open LLM Leaderboard
 ---
 
 # 🌟⚛ Introducing Quark Series: Empowering Edge Devices with Swift Bilingual Conversational AI
@@ -29,4 +131,17 @@ Quark models focus on delivering exceptional English and Chinese conversational
 # 🔍 Disclaimer
 As an alpha preview release without RLHF fine-tuning, we do not take responsibility for potentially harmful responses and are committed to continuous improvement based on user feedback and research.
 
-# 👥 Join [Our Discord community](https://discord.gg/ATfjwje3)!
+# 👥 Join [Our Discord community](https://discord.gg/ATfjwje3)!
+# [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_raincandy-u__Quark-464M-v0.1.alpha)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |35.68|
+|AI2 Reasoning Challenge (25-Shot)|31.40|
+|HellaSwag (10-Shot)              |47.31|
+|MMLU (5-Shot)                    |34.55|
+|TruthfulQA (0-shot)              |41.84|
+|Winogrande (5-shot)              |55.17|
+|GSM8k (5-shot)                   | 3.79|
+