Jiarui-Wang/MemSFT-Qwen3-Bio-Memory-1.7B
Full fine-tune vs Qwen/Qwen3-1.7B. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: Norms 108/113, MLP 84/84, Attention 112/112
2 derivatives checked
- mradermacher/MemSFT-Qwen3-Bio-Memory-1.7B-i1-GGUF: Quantization
- mradermacher/MemSFT-Qwen3-Bio-Memory-1.7B-GGUF: Same weights, converted