Adding Evaluation Results

README.md

@@ -1,14 +1,117 @@
 ---
-license: other
-license_name: tongyi-qianwen
-license_link: https://huggingface.co/Qwen/Qwen1.5-7B-Chat/blob/main/LICENSE
 language:
 - en
-pipeline_tag: text-generation
+license: other
 tags:
 - code
 datasets:
 - reciprocate/dpo_ultra-capybara-code_filtered-best
+license_name: tongyi-qianwen
+license_link: https://huggingface.co/Qwen/Qwen1.5-7B-Chat/blob/main/LICENSE
+pipeline_tag: text-generation
+model-index:
+- name: Coder1.8-ORPO-TEST
+  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: 38.82
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=raincandy-u/Coder1.8-ORPO-TEST
+      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: 60.48
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=raincandy-u/Coder1.8-ORPO-TEST
+      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: 46.7
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=raincandy-u/Coder1.8-ORPO-TEST
+      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: 41.38
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=raincandy-u/Coder1.8-ORPO-TEST
+      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: 59.75
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=raincandy-u/Coder1.8-ORPO-TEST
+      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: 27.45
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=raincandy-u/Coder1.8-ORPO-TEST
+      name: Open LLM Leaderboard
 ---
 
 # Coder1.8-ORPO-TEST
@@ -37,4 +140,17 @@ Limited training data and quantization may impact performance.
 
 # Join the Discussion
 
-Have questions or feedback? Join our Discord server [Here](https://discord.gg/KugcbJX5).
+Have questions or feedback? Join our Discord server [Here](https://discord.gg/KugcbJX5).
+# [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__Coder1.8-ORPO-TEST)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |45.76|
+|AI2 Reasoning Challenge (25-Shot)|38.82|
+|HellaSwag (10-Shot)              |60.48|
+|MMLU (5-Shot)                    |46.70|
+|TruthfulQA (0-shot)              |41.38|
+|Winogrande (5-shot)              |59.75|
+|GSM8k (5-shot)                   |27.45|
+