Qwen/Qwen2.5-Math-72B
Full fine-tune vs Qwen/Qwen2.5-72B. Fine-tune: 100% of the weights changed, across 80 of 80 layers.
Tensors changed: Embeddings 1/1, MLP 240/240, Attention 560/560, Norms 161/161, lm_head 1/1
7 derivatives checked
- Qwen/Qwen2.5-Math-72B-Instruct: Full fine-tune
- mradermacher/Qwen2.5-Math-72B-i1-GGUF: Quantization
- featherless-ai-quants/Qwen-Qwen2.5-Math-72B-GGUF: Quantization
- mradermacher/Qwen2.5-Math-72B-GGUF: Quantization
- redponike/AceMath-72B-Instruct-GGUF: Full fine-tune
- DevQuasar-4/Qwen2.5-Math-72B-GGUF: Quantization
- justus27/qwen-math-long: Full fine-tune