lukey03/Qwen3.5-9B-abliterated
Partial fine-tune (fewer layers) vs Qwen/Qwen3.5-9B. lukey03/Qwen3.5-9B-abliterated matches part of Qwen/Qwen3.5-9B (427 of its 775 tensors; the rest of Qwen/Qwen3.5-9B has no counterpart). On the shared part: Partial change: 64% of the weights changed (attention, mlp, norms), in 32 of 32 layers.
Tensors changed: lm_head 0/1, Embeddings 0/1, MLP 96/96, Attention 87/224, Norms 22/105
3 derivatives checked
- Abiray/Qwen3.5-9B-abliterated-GGUF: Quantization
- qzqdz/agent-abliterated-9b-gguf: Quantization
- groxaxo/lukey03-Qwen3.5-9B-abliterated-gptq-pro-w4g128: Quantization
6 other repos hold byte-for-byte identical weight files.