aisingapore/Nemotron-SEA-LION-v4.8-30B-A3B

Full fine-tune vs aisingapore/Nemotron-SEA-LION-v4.8-30B-A3B-Base. Fine-tune: 100% of the weights changed, across 52 of 52 layers.

Tensors changed: other 207/207, Embeddings 1/1, Norms 76/76, MLP 2566/2568, Attention 24/24, lm_head 1/1

2 derivatives checked

• aisingapore/Nemotron-SEA-LION-v4.8-30B-A3B-GGUF: Same weights, converted
• aisingapore/Nemotron-SEA-LION-v4.8-30B-A3B-NVFP4: Quantization

On the Hub · Downloads on Model Pulse