Qwen/Qwen3Guard-Gen-4B
Full fine-tune vs Qwen/Qwen3-4B. Fine-tune: 100% of the weights changed, across 36 of 36 layers.
Tensors changed: Embeddings 1/1, Norms 120/145, MLP 108/108, Attention 144/144
11 derivatives checked
- mradermacher/Qwen3Guard-Gen-4B-GGUF: Same weights, converted
- Yunhao-Feng/AdaGuard-4B: Full fine-tune
- i1see1you/VirbiusGuard-4B: LoRA-style
- DevQuasar/Qwen.Qwen3Guard-Gen-4B-GGUF: Same weights, converted
- JeremyLiShuhao/UD_model_v1: Full fine-tune
- liodon-ai/Qwen3Guard-Gen-4B-imatrix-GGUF: Quantization
- mediterranean1973/Qwen3Guard-Gen-4B-awq-int4: Quantization
- PLJIANGG05/qwen3guard-gen-4b-danger-intent-opendata-qwensynth-supplement-sampled4000-v9: LoRA-style
- geoffmunn/Qwen3Guard-Gen-4B-GGUF: Quantization
- zenlm/zen-guard: Identical copy
- amalia-llm/amaliaguard-4b: Full fine-tune
2 other repos hold byte-for-byte identical weight files.