SpaceTimee/Suri-Qwen-3.5-27B-Uncensored
Partial fine-tune vs Qwen/Qwen3.5-27B. Partial change: 70% of the weights changed (attention, mlp, norms), in 64 of 64 layers.
Tensors changed: lm_head 0/1, Embeddings 0/1, MLP 192/192, Attention 64/448, Norms 48/209
3 derivatives checked
- SpaceTimee/Suri-Qwen-3.5-27B-Uncensored-GGUF: Quantization
- mradermacher/Suri-Qwen-3.5-27B-Uncensored-i1-GGUF: Quantization
- mradermacher/Suri-Qwen-3.5-27B-Uncensored-GGUF: Quantization
1 other repos hold byte-for-byte identical weight files.