Adding Evaluation Results (#2)

- Adding Evaluation Results (93e414d661c04bbcb46d4d3ed430cc814a3f96a5)

README.md

@@ -1,18 +1,113 @@
 ---
-base_model:
-- meta-llama/Llama-3.2-3B-Instruct
-datasets:
-- NekoFi/alpaca-gpt4-indonesia-cleaned
 language:
 - id
 - en
 license: apache-2.0
-pipeline_tag: text-generation
 tags:
 - Indonesian
 - Chat
 - Instruct
 - unsloth
+base_model:
+- meta-llama/Llama-3.2-3B-Instruct
+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: 60.85
+ 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: 6.32
+ 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: 10.2
+ 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: 0.34
+ 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: 6.62
+ 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: 16.04
+ 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)
@@ -80,4 +175,17 @@ The model is licensed under the [Apache-2.0](https://www.apache.org/licenses/LIC
 
 ## Contributing
 
-We welcome contributions to enhance and improve Finmatcha. Feel free to open issues or submit pull requests for improvements.
+We welcome contributions to enhance and improve Finmatcha. Feel free to open issues or submit pull requests for improvements.
+# [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. |16.73|
+|IFEval (0-Shot) |60.85|
+|BBH (3-Shot) | 6.32|
+|MATH Lvl 5 (4-Shot)|10.20|
+|GPQA (0-shot) | 0.34|
+|MuSR (0-shot) | 6.62|
+|MMLU-PRO (5-shot) |16.04|
+