star-ga/mind-mem-4b
Full fine-tune (fewer layers) vs Qwen/Qwen3.5-4B. star-ga/mind-mem-4b matches part of Qwen/Qwen3.5-4B (426 of its 738 tensors; the rest of Qwen/Qwen3.5-4B has no counterpart). On the shared part: Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, MLP 96/96, Attention 177/224, Norms 51/105
1 derivatives checked
- mradermacher/mind-mem-4b-GGUF: Full fine-tune