jfan/Qwen3.8-27B-heretic-dflash

Full fine-tune vs z-lab/Qwen3.6-27B-DFlash. Fine-tune: 100% of the weights changed, across 5 of 5 layers.

Tensors changed: other 1/1, Norms 9/22, MLP 15/15, Attention 20/20

1 derivatives checked

• anfedoro/Qwen3.8-27B-heretic-dflash: Quantization

On the Hub · Downloads on Model Pulse