Reza2kn/Motarjem-v0.1
Full fine-tune vs tiiuae/Falcon-H1-Tiny-Multilingual-100M-Instruct. Fine-tune: 100% of the weights changed, across 24 of 24 layers.
Tensors changed: Norms 49/49, MLP 72/72, other 168/168, Attention 96/96
1 derivatives checked
- mradermacher/Motarjem-v0.1-GGUF: Same weights, converted