HFCK99/Qwen3.8-27B-OBLITERATED

Partial fine-tune vs Qwen/Qwen3.8-27B. Partial change: 55% of the weights changed (attention, lm_head, mlp), in 39 of 64 layers.

Tensors changed: Norms 0/325, Attention 98/560, MLP 117/307, Embeddings 0/5, lm_head 1/1, other 0/1

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

On the Hub · Downloads on Model Pulse