DevQuasar/kakaocorp.kanana-1.5-8b-instruct-2505-GGUF

Same weights, converted vs kakaocorp/kanana-1.5-8b-instruct-2505. Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: MLP 0/96, Norms 0/65, Attention 0/128, Embeddings 0/1, lm_head 0/1

On the Hub · Downloads on Model Pulse