Baichuan-Omni-1.5

Training compute

3.3×10²² FLOP

Parameters

11B

Published

Jan 26, 2025

Baichuan-Omni-1.5 is an AI model developed by Baichuan (China), first published in January 2025. It works in the multimodal, language, speech and 3 more domain, on tasks such as language modeling/generation, question answering, audio question answering and 8 more.

Training it took an estimated 3.3×10²² FLOP of compute (estimation method: operation counting). The model has 11,000,000,000 parameters. It was trained on roughly 500B datapoints.

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

Full record

Organization: Baichuan
Country of organization: China
Domain: Multimodal, Language, Speech, Vision, Video, Audio
Task: Language modeling/generation, Question answering, Audio question answering, Speech recognition (ASR), Speech-to-text, Visual question answering, Image captioning, Speech synthesis, Text-to-speech (TTS), Video, Video classification
Training compute: 3.3×10²² FLOP
Compute estimation method: Operation counting
Parameters: 11,000,000,000
Dataset size: 500B
Model accessibility: Open weights (restricted use)
Open weights: Yes
Epoch confidence: Likely