DevQuasar/Kwaipilot.KwaiCoder-AutoThink-preview-GGUF

Same weights, converted vs Kwaipilot/KwaiCoder-AutoThink-preview. Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: Embeddings 0/1, Norms 0/161, MLP 0/240, Attention 0/560, lm_head 0/1

On the Hub · Downloads on Model Pulse