inference-optimization/Qwen3-1.6B-A0.9B
Full fine-tune (fewer layers) vs Qwen/Qwen3-30B-A3B. inference-optimization/Qwen3-1.6B-A0.9B matches part of Qwen/Qwen3-30B-A3B (563 of its 18867 tensors; the rest of Qwen/Qwen3-30B-A3B has no counterpart). On the shared part: Fine-tune: 100% of the weights changed, across 10 of 10 layers.
Tensors changed: Embeddings 1/1, Norms 41/41, MLP 70/70, Attention 40/40, lm_head 1/1
2 derivatives checked
- mradermacher/Qwen3-1.6B-A0.9B-i1-GGUF: Quantization
- mradermacher/Qwen3-1.6B-A0.9B-GGUF: Same weights, converted