winglian/qwen3-14b-math
Full fine-tune vs Qwen/Qwen3-14B-Base. Fine-tune: 95% of the weights changed, across 40 of 40 layers.
Tensors changed: Embeddings 0/1, Norms 145/161, MLP 120/120, Attention 160/160, lm_head 1/1
1 derivatives checked
- tensorblock/winglian_qwen3-14b-math-GGUF: Quantization