透過Gemma實踐FT-RAG By Jerry

議題

RB102 [[ new Date( '2024-08-03 05:50:00+00:00' ).toLocaleDateString('ja', {year: 'numeric', month: '2-digit', day: '2-digit'}) ]] [[ new Date( '2024-08-03 05:50:00+00:00' ).toLocaleTimeString('zh-Hant', {hour12: false, hour: '2-digit', minute:'2-digit'}) ]] ~ [[ new Date( '2024-08-03 06:20:00+00:00' ).toLocaleTimeString('zh-Hant', {hour12: false, hour: '2-digit', minute:'2-digit'}) ]] 中文 Chinese

加入行事曆加入關注加入關注已關注

本主題主要介紹Google Gemma的模型，同時分享如何在Gemma微調之後，也一併使用微調後的模型進行RAG。同時比較在沒有微調與微調後的RAG差異。

講者

Jerry

JerryWu is a Google Developer Expert (GDE) in Machine Learning. He is also a Founder in the APMIC. Jerry led product and engineering for APMIC, Applications Accelerated on NVIDIA's Platforms #1 rank GPT turnkey solutions for 2023. Here, he built technology to enable enterprises to build their own GPT-conversational AI assistants, providing services that have reached over 5,000,000 individuals. Before APMIC, Jerry held data scientist at Yulon Motor, where he managed data services platform, the core software systems and AI capabilities that underpin the Car Voice Assistants, and led product and engineering for Data Science Vehicle-to-Cloud-to-Vehicle. He has an Doctoral Candidate from NTUST and research interests include Machine Intelligence and Natural Language Understanding (NLU).

Google Developer Party Google 開發者派對 BVUAUF general (30mins)