Adding Evaluation Results (#2)

- Adding Evaluation Results (a023a2126eaec9e1adcc22e952b358f1a5f3949f)


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

README.md

@@ -2,6 +2,109 @@
 license: cc-by-nc-4.0
 tags:
 - DPO
+model-index:
+- name: SJ-SOLAR-10.7b-DPO
+  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: 68.26
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=SJ-Donald/SJ-SOLAR-10.7b-DPO
+      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: 86.95
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=SJ-Donald/SJ-SOLAR-10.7b-DPO
+      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: 66.73
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=SJ-Donald/SJ-SOLAR-10.7b-DPO
+      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: 67.74
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=SJ-Donald/SJ-SOLAR-10.7b-DPO
+      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: 84.21
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=SJ-Donald/SJ-SOLAR-10.7b-DPO
+      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: 62.09
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=SJ-Donald/SJ-SOLAR-10.7b-DPO
+      name: Open LLM Leaderboard
 ---
 
 # SJ-Donald/SJ-SOLAR-10.7b-DPO
@@ -66,4 +169,17 @@ template = """### System:
 
 ## GGUF Version
 
-You can use gguf model file here! -> [SJ-Donald/SJ-SOLAR-10.7b-DPO-GGUF](https://huggingface.co/SJ-Donald/SJ-SOLAR-10.7b-DPO-GGUF)
+You can use gguf model file here! -> [SJ-Donald/SJ-SOLAR-10.7b-DPO-GGUF](https://huggingface.co/SJ-Donald/SJ-SOLAR-10.7b-DPO-GGUF)
+# [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_SJ-Donald__SJ-SOLAR-10.7b-DPO)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |72.67|
+|AI2 Reasoning Challenge (25-Shot)|68.26|
+|HellaSwag (10-Shot)              |86.95|
+|MMLU (5-Shot)                    |66.73|
+|TruthfulQA (0-shot)              |67.74|
+|Winogrande (5-shot)              |84.21|
+|GSM8k (5-shot)                   |62.09|
+