reaperdoesntknow/DiStil-Qwen3-1.7B-uncensored
Partial fine-tune vs reaperdoesntknow/TopologicalQwen. Partial change: 85% of the weights changed (attention, lm_head, mlp, norms), in 28 of 28 layers.
Tensors changed: lm_head 1/1, Embeddings 0/1, Norms 98/113, MLP 84/84, Attention 112/112
4 derivatives checked
- reaperdoesntknow/DualMind: Partial fine-tune
- reaperdoesntknow/Disctil-Qwen3-1.7B: Identical copy
- mradermacher/DiStil-Qwen3-1.7B-uncensored-i1-GGUF: Quantization
- mradermacher/DiStil-Qwen3-1.7B-uncensored-GGUF: Same weights, converted
1 other repos hold byte-for-byte identical weight files.