zwhe99/DeepMath-Omn-1.5B
Partial fine-tune vs nvidia/OpenMath-Nemotron-1.5B. Partial change: 85% of the weights changed (attention, mlp, norms), in 28 of 28 layers.
Tensors changed: Embeddings 0/1, Norms 43/57, MLP 84/84, Attention 195/196
2 derivatives checked
- mradermacher/DeepMath-Omn-1.5B-i1-GGUF: Quantization
- mradermacher/DeepMath-Omn-1.5B-GGUF: Same weights, converted