ghost-actual/Qwen3.8-Flash-Next-Abliterated-EXL3-2.50bpw

Partial fine-tune vs Qwen/Qwen3.8-Flash-Next. Partial change: 46% of the weights changed (embeddings, other), in 1 of 48 layers.

Tensors changed: Norms 0/302, other 1/7, Attention 0/357, MLP 0/274, Embeddings 1/4

On the Hub · Downloads on Model Pulse