DevQuasar/ByteDance-Seed.academic-ds-9B-GGUF

Same weights, converted vs ByteDance-Seed/academic-ds-9B. Same weights stored in another dtype (BF16 → F16/F32), plus 92 new tensors.

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/65, MLP 0/63, Attention 0/64

On the Hub · Downloads on Model Pulse