Venastine-Research/Xing4.0-29B-A4B-GGUF

Same weights, converted vs XingChen-AGI/Xing4.0-29B-A4B. Same weights stored in another dtype (BF16/F32 → F16/F32), plus 478 new tensors.

Tensors changed: Embeddings 0/2, Norms 0/168, MLP 0/162, Attention 0/164, lm_head 0/1, other 0/2

On the Hub · Downloads on Model Pulse