We set out to improve instruction-following capabilities in Thai, our native language, and ended up discovering one of today’s AI most urgent and critical inequality issues: the shape of subword tokens.

logo

YOU INSTRUCT,

GENERATES

เขียน อธิบาย สรุป ค้นคว้า และสร้างข้อความสื่อความหมายด้วย WangchanGLM โมเดลภาษาที่เชี่ยวชาญด้านภาษาไทยพัฒนาโมเดล โดยสถาบันวิทยสิริเมธี (VISTEC)
นำเสนอโดยบริษัท SCB 10X จำกัด

ตัวอย่าง

คำสั่ง

บริบทของคำสั่ง

circle-info

(ไม่จำเป็น)

Disclaimer: The responses generated by this Artificial Intelligence (AI) system are autonomously constructed and do not necessarily reflect the views or positions of the developing organizations, their affiliates, or any of their employees. These AI-generated responses do not represent those of the organizations. The organizations do not endorse, support, sanction, encourage, verify, or agree with the comments, opinions, or statements generated by this AI. The information produced by this AI is not intended to malign any religion, ethnic group, club, organization, company, individual, anyone, or anything. It is not the intent of the organizations to malign any group or individual. The AI operates based on its programming and training data and its responses should not be interpreted as the explicit intent or opinion of the organizations.

This is a technology demo of the WangChanGLM Multilingual Instruction Following Large Language Model by VISTEC, presented by SCB10X.

You can learn more about WangChanGLM from

this post

Ⓒ 2023 SCB10X Co. Ltd. - All rights reserved

GitHub Repo

Ⓒ 2023 SCB10X Co. Ltd. - All rights reserved