aisingapore/Nemotron-SEA-LION-v4.8-120B-A12B-GGUF

Same weights, converted vs aisingapore/Nemotron-SEA-LION-v4.8-120B-A12B. Same weights stored in another dtype (BF16/F32 → F16/F32), plus 176 new tensors.

Tensors changed: Embeddings 0/1, Norms 0/89, lm_head 0/1

On the Hub · Downloads on Model Pulse