Qwen/Qwen3Guard-Gen-0.6B
Full fine-tune vs Qwen/Qwen3-0.6B. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 106/113, MLP 84/84, Attention 112/112
5 derivatives checked
- mradermacher/Qwen3Guard-Gen-0.6B-GGUF: Same weights, converted
- i1see1you/VirbiusGuard: LoRA-style
- Yunhao-Feng/AdaGuard-0.6B: Partial fine-tune
- DevQuasar/Qwen.Qwen3Guard-Gen-0.6B-GGUF: Same weights, converted
- geoffmunn/Qwen3Guard-Gen-0.6B: Quantization