EchoLabs33/zamba2-2.7b-instruct-hxq

Same weights, converted vs Zyphra/Zamba2-2.7B-instruct. Same weights stored in another dtype (BF16 → U8/F16), plus 588 new tensors.

Tensors changed: Embeddings 0/1, Norms 0/113, other 0/270

On the Hub · Downloads on Model Pulse