llmfan46/Qwen3.5-27B-Nikusui-v1-Uncensored-Heretic-Native-MTP-Preserved

Partial fine-tune vs llmfan46/Qwen3.5-27B-uncensored-heretic-v2-Native-MTP-Preserved. Partial change: 60% of the weights changed (attention, lm_head, mlp), in 59 of 64 layers.

Tensors changed: lm_head 1/1, Embeddings 0/5, Norms 0/325, Attention 221/560, MLP 118/307, other 0/1

1 derivatives checked

• llmfan46/Qwen3.5-27B-Nikusui-v1-Uncensored-Heretic-Native-MTP-Preserved-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse