bobber/routangseng-qwen35-0.8b-abliterated
Partial fine-tune vs huihui-ai/Huihui-Qwen3.5-0.8B-abliterated. Partial change: 88% of the weights changed (attention, embeddings, mlp, norms), in 24 of 24 layers.
Tensors changed: Attention 133/216, Norms 25/129, Embeddings 1/4, MLP 72/124
2 derivatives checked
- mradermacher/routangseng-qwen35-0.8b-abliterated-i1-GGUF: Quantization
- mradermacher/routangseng-qwen35-0.8b-abliterated-GGUF: Same weights, converted