nvidia/OpenMath-Nemotron-32B
Full fine-tune vs Qwen/Qwen2.5-32B. Fine-tune: 100% of the weights changed, across 64 of 64 layers.
Tensors changed: Embeddings 1/1, Norms 129/129, MLP 192/192, Attention 448/448, lm_head 1/1
5 derivatives checked
- bartowski/nvidia_OpenMath-Nemotron-32B-GGUF: Same weights, converted
- mradermacher/OpenMath-Nemotron-32B-i1-GGUF: Quantization
- DevQuasar/nvidia.OpenMath-Nemotron-32B-GGUF: Same weights, converted
- mradermacher/OpenMath-Nemotron-32B-GGUF: Quantization
- lmstudio-community/OpenMath-Nemotron-32B-GGUF: Quantization
2 other repos hold byte-for-byte identical weight files.