justus27/qwen-math-long
Full fine-tune vs Qwen/Qwen2.5-Math-72B. Fine-tune: 100% of the weights changed, across 80 of 80 layers.
Tensors changed: Embeddings 1/1, Norms 161/161, MLP 240/240, Attention 560/560, lm_head 1/1
1 derivatives checked
- featherless-ai-quants/justus27-qwen-math-long-GGUF: Quantization
2 other repos hold byte-for-byte identical weight files.