nchapman/Ministral-3-3B-Instruct-2512-heretic-BF16

Partial fine-tune vs mistralai/Ministral-3-3B-Base-2512. Partial change: 89% of the weights changed (attention, embeddings, mlp, norms, other), in 26 of 26 layers.

Tensors changed: Embeddings 1/1, Norms 43/103, MLP 78/150, Attention 104/200, other 2/4

1 derivatives checked

On the Hub · Downloads on Model Pulse