一个支持ollama本地模型的工具，用于对大模型生成回答进行排序，生成偏好数据以训练奖励模型，进而优化SFT模型。
• Copy the embed code to showcase this product on your website
• Share on X to spread the word about this amazing tool
描述：简单来说就是你经过sft微调后，想通过RLHF（ppo奖励模型）训练怎么样的模型，就给你的模型生成回答进行排序，最后再导出偏好数据去训练奖励模型，再用奖励模型去训练sft模型开源地址：https://github.com/zjrwtx/preference_databuilder演示视频地址：https://www.bilibili.com/video/BV1P1421675z/?spm_id_from=333.999.0.0&vd_source=5531fb0981ef79f87198a3c2651dff93
Generate, optimize, test, and manage AI prompts in one place. Turn an idea into a ready-to-use prompt in seconds.
Find and contact web design leads and businesses without websites, like local dentists, effortlessly from any location in just a few clicks.
the art of having something to say
How Pretty Are You? Let AI Decide.
Impromptu Speech Topics & Timer
Seedance 2.0: Multimodal AI video creator. Precisely direct characters and cameras to create production-ready, multi-shot cinematic stories in one click.