DevQuasar/eousphoros.kappa-20b-131k-GGUF

Same weights, converted vs eousphoros/kappa-20b-131k. Same weights stored in another dtype (BF16 → F16/F32), plus 168 new tensors.

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/49, MLP 0/48, Attention 0/192

On the Hub · Downloads on Model Pulse