Fine-zhtw is a Traditional Chinese (zh-TW) collection inspired by Hugging Face’s Fine series, built with mostly self-designed methods.
AI & ML interests
Traditional Chinese language models
Recent Activity
View all activity
Benchmark log generated with Twinkle Eval, recording the model's outputs for each prompt, see more in https://github.com/ai-twinkle/Eval
-
twinkle-ai/gemma-3-4b-it-eval-logs-and-scores
Viewer • Updated • 103k • 285 -
twinkle-ai/gemma-3-4B-T1-it-eval-logs-and-scores
Viewer • Updated • 103k • 281 -
twinkle-ai/Gemma-3-12b-it-eval-logs-and-scores
Viewer • Updated • 103k • 147 -
twinkle-ai/gemma-3-taide-12b-chat-eval-logs-and-scores
Viewer • Updated • 103k • 232
A collection of Formosa-1 (F1) reasoning models and datasets focused on Traditional Chinese instruction-following and logic.
-
twinkle-ai/Llama-3.2-3B-F1-Instruct
Text Generation • 4B • Updated • 382 • 23 -
twinkle-ai/Llama-3.2-3B-F1-Reasoning-Instruct
Text Generation • 4B • Updated • 5 • 46 -
twinkle-ai/Llama-3.2-3B-F1-Reasoning-Instruct-GGUF
Text Generation • 4B • Updated • 1 • 13 -
lianghsun/Llama-3.2-3B-F1-Base
Text Generation • 4B • Updated • 1
Instruction-tuned Gemma-3 models optimized for agentic workflows in Traditional Chinese.
The collection related to the coding task
A curated collection of datasets designed to evaluate and train reasoning capabilities in Traditional Chinese across various domains.
Benchmark log generated with Twinkle Eval, recording the model's outputs for each prompt.
Fine-zhtw is a Traditional Chinese (zh-TW) collection inspired by Hugging Face’s Fine series, built with mostly self-designed methods.
Instruction-tuned Gemma-3 models optimized for agentic workflows in Traditional Chinese.
Benchmark log generated with Twinkle Eval, recording the model's outputs for each prompt, see more in https://github.com/ai-twinkle/Eval
-
twinkle-ai/gemma-3-4b-it-eval-logs-and-scores
Viewer • Updated • 103k • 285 -
twinkle-ai/gemma-3-4B-T1-it-eval-logs-and-scores
Viewer • Updated • 103k • 281 -
twinkle-ai/Gemma-3-12b-it-eval-logs-and-scores
Viewer • Updated • 103k • 147 -
twinkle-ai/gemma-3-taide-12b-chat-eval-logs-and-scores
Viewer • Updated • 103k • 232
The collection related to the coding task
A collection of Formosa-1 (F1) reasoning models and datasets focused on Traditional Chinese instruction-following and logic.
-
twinkle-ai/Llama-3.2-3B-F1-Instruct
Text Generation • 4B • Updated • 382 • 23 -
twinkle-ai/Llama-3.2-3B-F1-Reasoning-Instruct
Text Generation • 4B • Updated • 5 • 46 -
twinkle-ai/Llama-3.2-3B-F1-Reasoning-Instruct-GGUF
Text Generation • 4B • Updated • 1 • 13 -
lianghsun/Llama-3.2-3B-F1-Base
Text Generation • 4B • Updated • 1
A curated collection of datasets designed to evaluate and train reasoning capabilities in Traditional Chinese across various domains.
Benchmark log generated with Twinkle Eval, recording the model's outputs for each prompt.