mariklolik/AraToken-Qwen3-1.7B-CPT
Partial fine-tune vs Qwen/Qwen3-1.7B-Base. Partial change: 12% of the weights changed (attention, mlp, norms), in 4 of 28 layers.
Tensors changed: Embeddings 0/1, Norms 12/113, MLP 12/84, Attention 16/112
Partial fine-tune vs Qwen/Qwen3-1.7B-Base. Partial change: 12% of the weights changed (attention, mlp, norms), in 4 of 28 layers.
Tensors changed: Embeddings 0/1, Norms 12/113, MLP 12/84, Attention 16/112