OpenYourMind/OpenYourMind-NVIDIA-Nemotron-3-Ultra-550B-A55B-abliterated-uncensored

Partial fine-tune vs nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16. Partial change: 14% of the weights changed (attention, mlp, other), in 71 of 108 layers.

Tensors changed: Embeddings 0/1, other 32/435, Norms 0/162, MLP 62/2349, Attention 8/52, lm_head 0/1

1 other repos hold byte-for-byte identical weight files.

On the Hub · Downloads on Model Pulse