YFC-112358/Qwen3.8-27B-Della-Deckard-Fable-Qwopus-ColdFusion-v4

Full fine-tune vs DavidAU/Qwen3.6-27B-V1.1-FF711-Darker-Hero-GAIN-H2.0. Fine-tune: 100% of the weights changed, across 64 of 64 layers.

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

1 derivatives checked

On the Hub · Downloads on Model Pulse