shazzadulimun/NDP-Nemotron-3-Nano-4B-tool-calling

Partial fine-tune vs unsloth/NVIDIA-Nemotron-3-Nano-4B. Partial change: 67% of the weights changed (attention, mlp, other), in 42 of 42 layers.

Tensors changed: Embeddings 0/1, other 21/147, Norms 0/64, MLP 34/34, Attention 16/16, lm_head 0/1

On the Hub · Downloads on Model Pulse