Adding Evaluation Results

README.md

@@ -10,6 +10,109 @@ tags:
 base_model:
 - LDCC/LDCC-SOLAR-10.7B
 - upstage/SOLAR-10.7B-Instruct-v1.0
+model-index:
+- name: SOLAR-10.7B-slerp
+  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: 68.17
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=SJ-Donald/SOLAR-10.7B-slerp
+      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: 86.91
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=SJ-Donald/SOLAR-10.7B-slerp
+      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/SOLAR-10.7B-slerp
+      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: 67.42
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=SJ-Donald/SOLAR-10.7B-slerp
+      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: 84.06
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=SJ-Donald/SOLAR-10.7B-slerp
+      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: 62.17
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=SJ-Donald/SOLAR-10.7B-slerp
+      name: Open LLM Leaderboard
 ---
 
 # SOLAR-10.7B-slerp
@@ -69,4 +172,17 @@ parameters:
 tokenizer_source: union
 dtype: float16
 
-```
+```
+# [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__SOLAR-10.7B-slerp)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |72.58|
+|AI2 Reasoning Challenge (25-Shot)|68.17|
+|HellaSwag (10-Shot)              |86.91|
+|MMLU (5-Shot)                    |66.73|
+|TruthfulQA (0-shot)              |67.42|
+|Winogrande (5-shot)              |84.06|
+|GSM8k (5-shot)                   |62.17|
+