windowsxp811203/Qwen3.8-Flash-Next-Abliterated
Partial fine-tune vs Qwen/Qwen3.8-Flash-Next. Partial change: 24% of the weights changed (attention, embeddings, mlp, other), in 48 of 48 layers.
Tensors changed: Norms 0/302, other 2/8, Attention 49/608, MLP 98/602, Embeddings 2/137, lm_head 0/1
2 derivatives checked
- windowsxp811203/Qwen3.8-Flash-Next-Abliterated-GGUF: Not comparable yet
- windowsxp811203/Qwen3.8-Flash-Next-Abliterated-NVFP4: Quantization
1 other repos hold byte-for-byte identical weight files.