>
T
Model Details
Domain:
Task:
Model Access:
Open weights (restricted use)
Introduction
Benchmarking
FLOPs6.9e+24
Notes: 6ND: 6 * 115B * 10T = 6.9e24
Training
Training Code AccessibilityApache 2.0 https://huggingface.co/Tele-AI/TeleChat2-115B "TeleChat model supports commercial use if you plan to treat TeleChat The model or its derivatives are used for commercial purposes, you need to contact the mailbox below tele_ai@chinatelecom.cn" no clear license but same disclaimer as above https://github.com/Tele-AI/TeleChat2/ this is seems to be pre-training code: https://github.com/Tele-AI/TeleChat2/tree/main/deepspeed
Size Notes: The open source TeleChat2-115B model is trained using 10 trillion tokens of high-quality Chinese and English corpus
Parameters
Parameters115000000000
Authors
Zihan Wang and Xinzhang Liu and Shixuan Liu and Yitong Yao and Yuyao Huang and Zhongjiang He and Xuelong Li and Yongxiang Li and Zhonghao Che and Zhaoxi Zhang and Yan Wang and Xin Wang and Luwen Pu and Huihan Xu and Ruiyu Fang and Yu Zhao and Jie Zhang and Xiaomeng Huang and Zhilong Lu and Jiaxin Peng and Wenjun Zheng and Shiquan Wang and Bingkai Yang and Xuewei he and Zhuoru Jiang and Qiyi Xie and Yanhan Zhang and Zhongqiu Li and Lingling Shi and Weiwei Fu and Yin Zhang and Zilu Huang and Sishi Xiong and Yuxiang Zhang and Chao Wang and Shuangyong Song
Speech