Adding Evaluation Results (#2)

- Adding Evaluation Results (f85fa8930aadc5236da60170b3b5238ab5efac69)


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

README.md

@@ -1,14 +1,117 @@
 ---
-library_name: transformers
+language:
+- en
 license: other
+library_name: transformers
 datasets:
 - teknium/OpenHermes-2.5
 - LDJnr/Capybara
 - Intel/orca_dpo_pairs
 - argilla/distilabel-capybara-dpo-7k-binarized
-language:
-- en
 pipeline_tag: text-generation
+model-index:
+- name: Quyen-Plus-v0.1
+  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: 55.72
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vilm/Quyen-Plus-v0.1
+      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: 78.52
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vilm/Quyen-Plus-v0.1
+      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: 60.45
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vilm/Quyen-Plus-v0.1
+      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: 53.6
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vilm/Quyen-Plus-v0.1
+      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: 71.27
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vilm/Quyen-Plus-v0.1
+      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: 60.05
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vilm/Quyen-Plus-v0.1
+      name: Open LLM Leaderboard
 ---
 
 # Quyen
@@ -60,4 +163,17 @@ model.generate(**gen_input)
 
 # Acknowledgement
 - We're incredibly grateful to **Tensoic** and **Ontocord** for their generous support with compute and data preparation.
-- Special thanks to the Qwen team for letting us access the models early for these amazing finetunes.
+- Special thanks to the Qwen team for letting us access the models early for these amazing finetunes.
+# [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_vilm__Quyen-Plus-v0.1)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |63.27|
+|AI2 Reasoning Challenge (25-Shot)|55.72|
+|HellaSwag (10-Shot)              |78.52|
+|MMLU (5-Shot)                    |60.45|
+|TruthfulQA (0-shot)              |53.60|
+|Winogrande (5-shot)              |71.27|
+|GSM8k (5-shot)                   |60.05|
+