mradermacher/Spark-X2.5-4B-Writing-EP1-GGUF

Same weights, converted vs hcnote/Spark-X2.5-4B-Writing-EP1. Same weights stored in another dtype (BF16 → F16/F32), plus 36 new tensors.

Tensors changed: Embeddings 0/1, Norms 0/73, MLP 0/108, Attention 0/72

On the Hub · Downloads on Model Pulse