twobe3/nemotron-czech-0.6b-v1
Full fine-tune vs nvidia/nemotron-3.5-asr-streaming-0.6b. twobe3/nemotron-czech-0.6b-v1 is a GGUF (Q8_0) of different weights. Fine-tune: 100% of the weights changed, across 24 of 24 layers.
Tensors changed: other 24/24, MLP 96/96, Norms 240/240