Adding Evaluation Results

README.md

@@ -1,16 +1,119 @@
 ---
+language:
+- nl
 license: cc-by-nc-4.0
 library_name: transformers
 tags:
-  - trl
-  - dpo
-  - conversational
-language:
-  - nl
+- trl
+- dpo
+- conversational
 datasets:
-  - BramVanroy/ultra_feedback_dutch_cleaned
+- BramVanroy/ultra_feedback_dutch_cleaned
 pipeline_tag: text-generation
 inference: false
+model-index:
+- name: Qwen1.5-7B-Dutch-Chat
+  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: 53.92
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=robinsmits/Qwen1.5-7B-Dutch-Chat
+      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: 76.03
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=robinsmits/Qwen1.5-7B-Dutch-Chat
+      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: 62.38
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=robinsmits/Qwen1.5-7B-Dutch-Chat
+      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: 45.34
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=robinsmits/Qwen1.5-7B-Dutch-Chat
+      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: 68.82
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=robinsmits/Qwen1.5-7B-Dutch-Chat
+      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: 15.47
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=robinsmits/Qwen1.5-7B-Dutch-Chat
+      name: Open LLM Leaderboard
 ---
 
 # Qwen1.5-7B-Dutch-Chat
@@ -136,4 +239,17 @@ Thanks to the creators of Qwen1.5 for there great work!
   journal={arXiv preprint arXiv:2309.16609},
   year={2023}
 }
-```
+```
+# [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_robinsmits__Qwen1.5-7B-Dutch-Chat)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |53.66|
+|AI2 Reasoning Challenge (25-Shot)|53.92|
+|HellaSwag (10-Shot)              |76.03|
+|MMLU (5-Shot)                    |62.38|
+|TruthfulQA (0-shot)              |45.34|
+|Winogrande (5-shot)              |68.82|
+|GSM8k (5-shot)                   |15.47|
+