TitleOS/Linden-4B-FP32
Partial fine-tune (fewer layers) vs Qwen/Qwen3.5-4B. TitleOS/Linden-4B-FP32 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: Partial change: 61% of the weights changed (attention, mlp, norms), in 32 of 32 layers.
Tensors changed: Embeddings 0/1, MLP 96/96, Attention 32/224, Norms 24/105
2 derivatives checked
- mradermacher/Linden-4B-FP32-i1-GGUF: Quantization
- mradermacher/Linden-4B-FP32-GGUF: Same weights, converted