Adding Evaluation Results

README.md

@@ -1,11 +1,106 @@
 ---
 language:
-  - en
-  - ja
+- en
+- ja
+license: llama3
 library_name: transformers
 pipeline_tag: text-generation
-license: llama3
 model_type: llama
+model-index:
+- name: Llama-3-Swallow-8B-Instruct-v0.1
+  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: 55.08
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=tokyotech-llm/Llama-3-Swallow-8B-Instruct-v0.1
+      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: 29.27
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=tokyotech-llm/Llama-3-Swallow-8B-Instruct-v0.1
+      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: 6.65
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=tokyotech-llm/Llama-3-Swallow-8B-Instruct-v0.1
+      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: 5.26
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=tokyotech-llm/Llama-3-Swallow-8B-Instruct-v0.1
+      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: 13.8
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=tokyotech-llm/Llama-3-Swallow-8B-Instruct-v0.1
+      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: 23.2
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=tokyotech-llm/Llama-3-Swallow-8B-Instruct-v0.1
+      name: Open LLM Leaderboard
 ---
 
 # Llama3 Swallow
@@ -253,4 +348,17 @@ Loem and Rio Yokota and Sakae Mizuki},
     year={2024},
     url = {https://github.com/meta-llama/llama3/blob/main/MODEL_CARD.md}
 }
-```
+```
+# [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_tokyotech-llm__Llama-3-Swallow-8B-Instruct-v0.1)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |22.21|
+|IFEval (0-Shot)    |55.08|
+|BBH (3-Shot)       |29.27|
+|MATH Lvl 5 (4-Shot)| 6.65|
+|GPQA (0-shot)      | 5.26|
+|MuSR (0-shot)      |13.80|
+|MMLU-PRO (5-shot)  |23.20|
+