mmiiguell10/Qwen3.8-27B-OBLITERATED-archive

Full fine-tune vs Qwen/Qwen3.8-27B. Fine-tune: 97% of the weights changed, across 64 of 64 layers.

Tensors changed: Norms 207/325, Attention 441/560, MLP 192/307, Embeddings 1/5, lm_head 1/1, other 0/1

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

On the Hub · Downloads on Model Pulse