-
zgcagi/ZGCM-1-7B
Text Generation • 7B • Updated • 406 • 14 -
zgcagi/ZGCM-1-Data
Viewer • Updated • 5.44B • 1.1k • 11 -
ZGCM-1: A Fully Open and Extremely Efficient Foundation Model for Math and Agentic Search
Paper • 2609.13356 • Published • 290 -
zgcagi/ZGCM-1-7B-Pretrain-Curriculum
Text Generation • 7B • Updated • 19 • 1
AI & ML interests
Pushing the Frontiers of Intelligence
Recent Activity
View all activity
Papers
View all Papers Organization Card
ZGCAGI on Hugging Face
ZGCAGI is a special interest group organized by students from Zhongguancun Academy and the Zhongguancun Institute of Artificial Intelligence. We aim to push the frontiers of intelligence through open research and collaboration.
New open-weight language models
- ZGCM-1-7B: ZGCM-1-7B is a 7.39B-parameter dense language model trained from scratch, built for mathematical reasoning and tool-assisted search. It combines deliberate internal thinking with active information gathering, supporting 256K-token context and both thinking and direct-response modes in a single model.
-
zgcagi/ZGCM-1-7B
Text Generation • 7B • Updated • 406 • 14 -
zgcagi/ZGCM-1-Data
Viewer • Updated • 5.44B • 1.1k • 11 -
ZGCM-1: A Fully Open and Extremely Efficient Foundation Model for Math and Agentic Search
Paper • 2609.13356 • Published • 290 -
zgcagi/ZGCM-1-7B-Pretrain-Curriculum
Text Generation • 7B • Updated • 19 • 1
models 6
zgcagi/ZGCM-1-7B
Text Generation • 7B • Updated • 406 • 14
zgcagi/ZGCM-1-7B-Midtrain-Staged-16K
Text Generation • 7B • Updated • 15 • 1
zgcagi/ZGCM-1-7B-Midtrain-Staged-256K
Text Generation • 7B • Updated • 21 • 1
zgcagi/ZGCM-1-7B-Midtrain-Staged-64K
Text Generation • 7B • Updated • 8
zgcagi/ZGCM-1-7B-Pretrain
Text Generation • 7B • Updated • 8
zgcagi/ZGCM-1-7B-Pretrain-Curriculum
Text Generation • 7B • Updated • 19 • 1