ZGCM-1-7B releases full weights, data, and code for math and agentic search
Zhongguancun Academy and Zhongguancun AI Institute released ZGCM-1-7B, a dense 7.39B-parameter model with open weights, data, and training code under MIT license. It uses hybrid attention (27 gated sliding-window layers and 5 global), 256K token context, and thinking and direct answer modes; trained on ~4.19 trillion tokens.
- 7.39B parameters, MIT license, weights and code on Hugging Face and GitHub
- 256K token context, 27 gated sliding-window and 5 global layers
- MATH-500: 97.13%, AIME 2026: 75.00%, HMMT 2025: 70.42%
- WebWalkerQA: 63.09%, BrowseComp: 19.43%, Binary Function Search: 62.00%
Read next
AI