tomg-group-umd/DynaGuard-1.7B
Full fine-tune vs Qwen/Qwen3-1.7B. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: Embeddings 1/1, Norms 108/113, MLP 84/84, Attention 112/112, lm_head 1/1
4 derivatives checked
- prithivMLmods/DynaGuard-AIO-GGUF: Same weights, converted
- mradermacher/DynaGuard-1.7B-i1-GGUF: Quantization
- mradermacher/DynaGuard-1.7B-GGUF: Same weights, converted
- DevQuasar/tomg-group-umd.DynaGuard-1.7B-GGUF: Same weights, converted