You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Log in or Sign Up to review the conditions and access this model content.

Model Card for Llama-3.2-3B-F1-Instruct

Note: The checkpoint for this model will be released soon. Please stay tuned. 🙏

Llama-3.2-3B-F1-Instruct 是由 Twinkle AIAPMIC 合作開發,並在國家高速網路與計算中心技術指導之下,針對中華民國台灣語境與任務需求所微調之繁體中文語言模型,涵蓋法律、教育、生活應用等多元場景,並以高指令跟隨能力為目標進行強化。

Model Details

Model Description

Model Sources

Evaluation

Results

下表採用 🌟 Twinkle Eval 評測框架

模型 評測模式 TMMLU+(%) 台灣法律(%) MMLU(%) 測試次數 選項排序
mistralai/Mistral-Small-24B-Instruct-2501 box 56.15 (±0.0172) 37.48 (±0.0098) 74.61 (±0.0154) 3 隨機
meta-llama/Llama-3.2-3B-Instruct box 15.49 (±0.0104) 25.68 (±0.0200) 6.90 (±0.0096) 3 隨機
meta-llama/Llama-3.2-3B-Instruct pattern 35.85 (±0.0174) 32.22 (±0.0023) 59.33 (±0.0168) 3 隨機
MediaTek-Research/Llama-Breeze2-3B-Instruct pattern 40.32 (±0.0181) 38.92 (±0.0193) 55.37 (±0.0180) 3 隨機
twinkle-ai/Llama-3.2-3B-F1-Instruct (ours) box 42.18 (±0.0197) 31.26 (±0.0354) 52.07 (±0.0189) 3 隨機

下表用 lighteval 評測框架

模型 MATH-500 GPQA Diamond
meta-llama/Llama-3.2-3B-Instruct 44.40 27.78
twinkle-ai/Llama-3.2-3B-F1-Instruct (ours) 51.40 33.84

Citation

@misc{twinkleai2025llama3.2f1,
  title        = {Llama-3.2-3B-F1-Instruct: A Traditional Chinese Instruction-Tuned Language Model for Taiwan},
  author       = {Huang, Liang Hsun and Chen, Min Yi and Lin, Wen Bin and Chuang, Chao Chun and Sung, Dave},
  year         = {2025},
  howpublished = {\url{https://huggingface.co/twinkle-ai/Llama-3.2-3B-F1-Instruct}},
  note         = {Twinkle AI and APMIC. All authors contributed equally.}
}

Acknowledge

特此感謝國家高速網路與計算中心的指導與 APMIC 的算力支援,才得以讓本專案訓利完成。

Model Card Authors

Twinkle AI

Model Card Contact

Twinkle AI

Downloads last month
4
Safetensors
Model size
3.61B params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for twinkle-ai/Llama-3.2-3B-F1-Instruct

Finetuned
(133)
this model

Datasets used to train twinkle-ai/Llama-3.2-3B-F1-Instruct

Evaluation results