Qwen1.5-14B

Training compute

3.4×10²³ FLOP

Parameters

14B

Published

Feb 4, 2024

Qwen1.5-14B is an AI model developed by Alibaba (China), first published in February 2024. It works in the language domain, on tasks such as chat, language modeling/generation, quantitative reasoning and 2 more.

Training it took an estimated 3.4×10²³ FLOP of compute (estimation method: operation counting). The model has 14,000,000,000 parameters.

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

Full record

Organization: Alibaba
Country of organization: China
Domain: Language
Task: Chat, Language modeling/generation, Quantitative reasoning, Code generation, Translation
Training compute: 3.4×10²³ FLOP
Compute estimation method: Operation counting
Parameters: 14,000,000,000
Model accessibility: Open weights (unrestricted)
Open weights: Yes
Epoch confidence: Confident

Benchmark results

01

MMLU

0.69