7B model trained by 7 PhDs in 3 months
7名博士生仅用3个月从零训练7B大模型：代码+数据+训练日志全公开
For developers, this is a rare look at the full process of training a large model from scratch, with all resources open for anyone to use or study.
Seven PhD students trained a 7B-parameter large language model from scratch in just three months.
The code, training data, and logs are all publicly available.The model achieved state-of-the-art results on the GLUE benchmark, demonstrating the efficiency of small teams in training large models.
7名博士生仅用3个月从零训练7B大模型：代码+数据+训练日志全公开
几百个Agent参与研发，AI开始造AI
This report is categorized under AITOP's "Models" desk, focusing on China's AI industry and domestic foundation model ecosystem. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows and US-China foundation model benchmarks and commercialization comparison. Key entities and technical topics under continuous tracking include 7B model, large language model, open-source models, GLUE benchmark.
Source attribution: curated from 量子位 (@思邈).
