TelperionAI/Qwen3.8-27B-GLA-g2
Partial fine-tune vs Qwen/Qwen3.8-27B. Partial change: 0% of the weights changed (norms), in 16 of 64 layers.
Tensors changed: Norms 32/325, Attention 0/528, MLP 0/307, Embeddings 0/5, lm_head 0/1, other 0/1
Partial fine-tune vs Qwen/Qwen3.8-27B. Partial change: 0% of the weights changed (norms), in 16 of 64 layers.
Tensors changed: Norms 32/325, Attention 0/528, MLP 0/307, Embeddings 0/5, lm_head 0/1, other 0/1