AI Briefing#zaya1-8b
The latest AI and developer news about #zaya1-8b, with the original source and a short summary.
The latest AI and developer news about #zaya1-8b, with the original source and a short summary.
Open-weight LLMs including Gemma 4 and DeepSeek V4 are lowering long-context costs through KV sharing and compressed attention.
Zyphra has released ZAYA1-8B, an 8B MoE model trained on AMD Instinct MI300.
Zyphra has released ZAYA1-8B, a 760M active parameter MoE model.
Zyphra has released ZAYA1-8B, a reasoning-specialized MoE model with fewer than 1B active parameters.
Zyphra unveiled ZAYA1-8B, trained on AMD MI300, along with Markovian RSA.