nassimjp/MiniCPM5-2B-SFT-Pashto
Full fine-tune vs openbmb/MiniCPM5-2B. Fine-tune: 100% of the weights changed, across 42 of 42 layers.
Tensors changed: Norms 1/85, MLP 126/126, Attention 168/168
2 derivatives checked
- tinyopsec/MiniCPM5-2B-SFT-Pashto-GGUF: Same weights, converted
- mradermacher/MiniCPM5-2B-SFT-Pashto-GGUF: Same weights, converted