jeff-legacy/Jeff-Qwen3.5-2B
Partial fine-tune vs Qwen/Qwen3.5-2B. Partial change: 62% of the weights changed (attention, mlp, norms), in 24 of 24 layers.
Tensors changed: Attention 138/264, Norms 51/177, Embeddings 0/4, MLP 72/172
Partial fine-tune vs Qwen/Qwen3.5-2B. Partial change: 62% of the weights changed (attention, mlp, norms), in 24 of 24 layers.
Tensors changed: Attention 138/264, Norms 51/177, Embeddings 0/4, MLP 72/172