DevQuasar/inclusionAI.Ling-lite-1.5-2506-GGUF

Same weights, converted vs inclusionAI/Ling-lite-1.5-2506. Same weights stored in another dtype (BF16 → F16/F32), plus 168 new tensors.

Tensors changed: lm_head 0/1, Attention 0/28, Norms 0/57, MLP 0/112, Embeddings 0/1

On the Hub · Downloads on Model Pulse