Adding Evaluation Results

README.md

@@ -1,13 +1,108 @@
 ---
-library_name: transformers
-license: mit
-datasets:
-- heegyu/open-korean-instructions
 language:
 - ko
+license: mit
+library_name: transformers
 tags:
 - Llama-2-7b-hf
 - LoRA
+datasets:
+- heegyu/open-korean-instructions
+model-index:
+- name: llama-2-7b-hf-lora-oki100p
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: IFEval (0-Shot)
+      type: HuggingFaceH4/ifeval
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: inst_level_strict_acc and prompt_level_strict_acc
+      value: 25.13
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=LEESM/llama-2-7b-hf-lora-oki100p
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: BBH (3-Shot)
+      type: BBH
+      args:
+        num_few_shot: 3
+    metrics:
+    - type: acc_norm
+      value: 10.27
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=LEESM/llama-2-7b-hf-lora-oki100p
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MATH Lvl 5 (4-Shot)
+      type: hendrycks/competition_math
+      args:
+        num_few_shot: 4
+    metrics:
+    - type: exact_match
+      value: 1.21
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=LEESM/llama-2-7b-hf-lora-oki100p
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GPQA (0-shot)
+      type: Idavidrein/gpqa
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 2.57
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=LEESM/llama-2-7b-hf-lora-oki100p
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MuSR (0-shot)
+      type: TAUR-Lab/MuSR
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 3.56
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=LEESM/llama-2-7b-hf-lora-oki100p
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU-PRO (5-shot)
+      type: TIGER-Lab/MMLU-Pro
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 9.51
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=LEESM/llama-2-7b-hf-lora-oki100p
+      name: Open LLM Leaderboard
 ---
 
 # Llama-2 model fine tuning (TREX-Lab at Seoul Cyber University)
@@ -85,3 +180,17 @@ TrainOutput(global_step=2001,
 
 ```
 
+
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_LEESM__llama-2-7b-hf-lora-oki100p)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               | 8.71|
+|IFEval (0-Shot)    |25.13|
+|BBH (3-Shot)       |10.27|
+|MATH Lvl 5 (4-Shot)| 1.21|
+|GPQA (0-shot)      | 2.57|
+|MuSR (0-shot)      | 3.56|
+|MMLU-PRO (5-shot)  | 9.51|
+