Zyphra Unveils ZAYA1-8B: AMD Hardware-Trained MoE Display That Punches Far Above Its Weight Class
Zyphra AI released ZAYA1-8B, a small Mixture of Experts (MoE) language model with 760 million active parameters and 8.4 billion parameters. Trained end-to-end on AMD hardware, the model outperforms open-source models many times its size in math and code benchmarks, and is now available under the Apache 2.0 license on Hugging Face and as a … Read more