aesir-unlimited/Qwen3.5-4B-Base40-Uncensored60
Partial fine-tune vs Qwen/Qwen3.5-4B. Partial change: 19% of the weights changed (attention, mlp, norms), in 18 of 32 layers.
Tensors changed: Embeddings 0/5, MLP 32/199, Attention 13/324, Norms 3/209, other 0/1
2 derivatives checked
- mradermacher/Qwen3.5-4B-Base40-Uncensored60-i1-GGUF: Quantization
- mradermacher/Qwen3.5-4B-Base40-Uncensored60-GGUF: Same weights, converted
1 other repos hold byte-for-byte identical weight files.