PIXELZX/XION0.2-27B

Full fine-tune vs Jiunsong/SuperQwen3.8-27b-abliterated. Fine-tune: 94% of the weights changed, across 64 of 64 layers.

Tensors changed: Norms 141/319, Attention 370/556, MLP 192/304, Embeddings 0/4, lm_head 1/1

1 derivatives checked

• mradermacher/XION0.2-27B-GGUF: Quantization

On the Hub · Downloads on Model Pulse