win10/ChatML-Nemo-Pro
Full fine-tune vs cyberagent/Mistral-Nemo-Japanese-Instruct-2408. Fine-tune: 100% of the weights changed, across 40 of 40 layers.
Tensors changed: Embeddings 1/1, Norms 31/81, MLP 120/120, Attention 160/160, lm_head 1/1
3 derivatives checked
- mradermacher/ChatML-Nemo-Pro-i1-GGUF: Quantization
- mradermacher/ChatML-Nemo-Pro-GGUF: Quantization
- win10/ChatML-Nemo-Pro-model_stock: Identical copy
2 other repos hold byte-for-byte identical weight files.