Zyphra Releases ZAYA1-8B, a Reasoning Model Trained on AMD and Optimized for Maximum Intelligence Density per Parameter
10 Articles
10 Articles
Aspen Daily News
Zyphra Releases ZAYA1-8B, a Reasoning Model trained on AMD and Optimized for Maximum Intelligence Density per Parameter
ZAYA1-8B delivers reasoning, mathematics, and coding performance competitive with models many times larger, achieving high intelligence density with under one billion active parameters trained on full-stack AMD infrastructure.
Zyphra Releases ZAYA1-8B: A Reasoning MoE Trained on AMD Hardware That Punches Far Above Its Weight Class
Zyphra AI has released ZAYA1-8B, a small Mixture of Experts (MoE) language model with 760 million active parameters and 8.4 billion total parameters. Trained end-to-end on AMD hardware, the model outperforms open-weight models many times its size on math and coding benchmarks, and is now available under an Apache 2.0 license on Hugging Face and as a serverless endpoint on Zyphra Cloud. With under 1 billion active parameters, ZAYA1-8B achieves sc…
Zyphra presented ZAYA1-8B, a new open model of MoE-trained reasoning on AMD infrastructure that, according to the company, manages to compete with much larger systems in mathematics, code and complex tasks thanks to a combination of architecture, reasoning-oriented pre-training and a test-time computing method called Markovian RSA. *** ZAYA1-8B uses less than 1B of active parameters and, according to Zyphra, exceeds several larger open models in…
Coverage Details
Bias Distribution
- 100% of the sources are Center
Factuality
To view factuality data please Upgrade to Premium
