Telechat2-115B

Training compute

6.9×10²⁴ FLOP

Parameters

115B

Published

Sep 20, 2024

Telechat2-115B is an AI model developed by China Telecom (China), first published in September 2024. It works in the language domain, on tasks such as language modeling/generation, question answering, quantitative reasoning and 3 more.

Training it took an estimated 6.9×10²⁴ FLOP of compute (estimation method: operation counting). The model has 115,000,000,000 parameters. It was trained on roughly 10T datapoints.

Access: Open weights (restricted use). Its weights are openly available. Epoch AI rates the confidence of this record as confident.

Full record

Organization: China Telecom
Country of organization: China
Domain: Language
Task: Language modeling/generation, Question answering, Quantitative reasoning, Chat, Text summarization, Code generation
Training compute: 6.9×10²⁴ FLOP
Compute estimation method: Operation counting
Parameters: 115,000,000,000
Dataset size: 10T
Numerical format: FP16
Model accessibility: Open weights (restricted use)
Open weights: Yes
Epoch confidence: Confident