prithivMLmods/Qwen3.8-27B-abliterated-MLX

Partial fine-tune vs huihui-ai/Huihui-Qwen3.8-27B-abliterated. Partial change: 0% of the weights changed (norms), in 64 of 64 layers.

Tensors changed: Norms 161/209, Attention 0/400, MLP 0/192, Embeddings 0/1

On the Hub · Downloads on Model Pulse