Adding Evaluation Results

README.md

@@ -11,6 +11,101 @@ base_model:
 datasets:
 - NekoFi/alpaca-gpt4-indonesia-cleaned
 pipeline_tag: text-generation
+model-index:
+- name: FinMatcha-3B-Instruct
+  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: 75.48
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=xMaulana/FinMatcha-3B-Instruct
+      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: 23.19
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=xMaulana/FinMatcha-3B-Instruct
+      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: 12.39
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=xMaulana/FinMatcha-3B-Instruct
+      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=xMaulana/FinMatcha-3B-Instruct
+      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: 5.02
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=xMaulana/FinMatcha-3B-Instruct
+      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: 24.24
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=xMaulana/FinMatcha-3B-Instruct
+      name: Open LLM Leaderboard
 ---
 
 ![image/jpeg](https://huggingface.co/xMaulana/FinMatcha-3B-Instruct/resolve/main/image.jpg)
@@ -92,3 +187,17 @@ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-le
 |MuSR (0-shot)      | 5.40|
 |MMLU-PRO (5-shot)  |24.54|
 
+
+# [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_xMaulana__FinMatcha-3B-Instruct)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |23.81|
+|IFEval (0-Shot)    |75.48|
+|BBH (3-Shot)       |23.19|
+|MATH Lvl 5 (4-Shot)|12.39|
+|GPQA (0-shot)      | 2.57|
+|MuSR (0-shot)      | 5.02|
+|MMLU-PRO (5-shot)  |24.24|
+