Adding Evaluation Results

README.md

@@ -2,8 +2,111 @@
 language:
 - en
 - ko
-pipeline_tag: text-generation
 license: cc-by-nc-sa-4.0
+pipeline_tag: text-generation
+model-index:
+- name: SOLAR-tail-10.7B-Merge-v1.0
+  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: 66.13
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=PracticeLLM/SOLAR-tail-10.7B-Merge-v1.0
+      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: 86.54
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=PracticeLLM/SOLAR-tail-10.7B-Merge-v1.0
+      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: 66.52
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=PracticeLLM/SOLAR-tail-10.7B-Merge-v1.0
+      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: 60.57
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=PracticeLLM/SOLAR-tail-10.7B-Merge-v1.0
+      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: 84.77
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=PracticeLLM/SOLAR-tail-10.7B-Merge-v1.0
+      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: 65.58
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=PracticeLLM/SOLAR-tail-10.7B-Merge-v1.0
+      name: Open LLM Leaderboard
 ---
 
 # **SOLAR-tail-10.7B-Merge-v1.0**  
@@ -91,4 +194,17 @@ OpenOrca = AutoModelForCausalLM.from_pretrained(
 OpenOrca_tokenizer = AutoTokenizer.from_pretrained(repo)
 ```
 
----
+---
+# [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_PracticeLLM__SOLAR-tail-10.7B-Merge-v1.0)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |71.68|
+|AI2 Reasoning Challenge (25-Shot)|66.13|
+|HellaSwag (10-Shot)              |86.54|
+|MMLU (5-Shot)                    |66.52|
+|TruthfulQA (0-shot)              |60.57|
+|Winogrande (5-shot)              |84.77|
+|GSM8k (5-shot)                   |65.58|
+