Qwen/Qwen2.5-Math-72B-Instruct
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
8 derivatives checked
- Qwen/Qwen2.5-Math-RM-72B: Full fine-tune
- bartowski/Qwen2.5-Math-72B-Instruct-GGUF: Quantization
- mradermacher/Qwen2.5-Math-72B-Instruct-i1-GGUF: Quantization
- mradermacher/Qwen2.5-Math-72B-Instruct-GGUF: Quantization
- lmstudio-community/Qwen2.5-Math-72B-Instruct-GGUF: Quantization
- featherless-ai-quants/Qwen-Qwen2.5-Math-72B-Instruct-GGUF: Quantization
- Qwen/Qwen2.5-Math-PRM-72B: Full fine-tune
- mlx-community/Qwen2.5-Math-72B-Instruct-4bit: Quantization
2 other repos hold byte-for-byte identical weight files.