pthinc/Cicikus-v3-1.4B-Opus4.6-Powered

Partial fine-tune vs meta-llama/Llama-3.2-1B. Partial change: 79% of the weights changed (attention, mlp, norms), in 16 of 16 layers.

Tensors changed: Embeddings 0/1, Norms 16/33, MLP 48/48, Attention 64/64

2 derivatives checked

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

On the Hub · Downloads on Model Pulse