SultanR/SmolTulu-1.7b-RM
Full fine-tune vs SultanR/SmolTulu-1.7b-Instruct. Fine-tune: 100% of the weights changed, across 24 of 24 layers.
Tensors changed: Norms 49/49, MLP 72/72, Attention 96/96
3 derivatives checked
- mradermacher/SmolTulu-1.7b-RM-i1-GGUF: Quantization
- MaziyarPanahi/SmolTulu-1.7b-RM-GGUF: Same weights, converted
- mradermacher/SmolTulu-1.7b-RM-GGUF: Same weights, converted