Adding Evaluation Results (#5)

- Adding Evaluation Results (75c6a63ff3b19debe991ff3702d54172249dc6e4)


Co-authored-by: Open LLM Leaderboard PR Bot <leaderboard-pr-bot@users.noreply.huggingface.co>

README.md

@@ -6,10 +6,113 @@ tags:
 - lazymergekit
 - microsoft/Orca-2-13b
 - KoboldAI/LLaMA2-13B-Psyfighter2
-license_name: microsoft-research-license
 base_model:
 - KoboldAI/LLaMA2-13B-Psyfighter2
 - microsoft/Orca-2-13b
+license_name: microsoft-research-license
+model-index:
+- name: Psyfighter2-Orca2-13B-ties
+  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: 62.46
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=tuantran1632001/Psyfighter2-Orca2-13B-ties
+      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: 81.74
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=tuantran1632001/Psyfighter2-Orca2-13B-ties
+      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: 60.31
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=tuantran1632001/Psyfighter2-Orca2-13B-ties
+      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: 55.4
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=tuantran1632001/Psyfighter2-Orca2-13B-ties
+      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: 77.27
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=tuantran1632001/Psyfighter2-Orca2-13B-ties
+      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: 43.67
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=tuantran1632001/Psyfighter2-Orca2-13B-ties
+      name: Open LLM Leaderboard
 ---
 
 # Psyfighter2-Orca2-ties
@@ -35,4 +138,17 @@ parameters:
   normalize: true
   int8_mask: true
 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_tuantran1632001__Psyfighter2-Orca2-13B-ties)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |63.48|
+|AI2 Reasoning Challenge (25-Shot)|62.46|
+|HellaSwag (10-Shot)              |81.74|
+|MMLU (5-Shot)                    |60.31|
+|TruthfulQA (0-shot)              |55.40|
+|Winogrande (5-shot)              |77.27|
+|GSM8k (5-shot)                   |43.67|
+