etemiz/Ostrich-27B-Qwen3.8-260816-Abliterated
Full fine-tune vs Qwen/Qwen3.8-27B. Fine-tune: 100% of the weights changed, across 64 of 64 layers.
Tensors changed: Norms 311/325, Attention 533/560, MLP 307/307, Embeddings 5/5, lm_head 1/1, other 1/1
Full fine-tune vs Qwen/Qwen3.8-27B. Fine-tune: 100% of the weights changed, across 64 of 64 layers.
Tensors changed: Norms 311/325, Attention 533/560, MLP 307/307, Embeddings 5/5, lm_head 1/1, other 1/1