richardyoung/SmolLM3-3B-abliterated-obliteratus
Partial fine-tune vs HuggingFaceTB/SmolLM3-3B. Partial change: 31% of the weights changed (attention, embeddings, mlp), in 9 of 36 layers.
Tensors changed: Embeddings 1/1, Norms 0/73, MLP 27/108, Attention 36/144
2 derivatives checked
- mradermacher/SmolLM3-3B-abliterated-obliteratus-i1-GGUF: Quantization
- mradermacher/SmolLM3-3B-abliterated-obliteratus-GGUF: Same weights, converted