nazimali/Mistral-Nemo-Kurdish
Full fine-tune vs mistralai/Mistral-Nemo-Instruct-2407. Fine-tune: 95% of the weights changed, across 40 of 40 layers.
Tensors changed: Embeddings 0/1, Norms 0/81, MLP 120/120, Attention 160/160, lm_head 1/1
4 derivatives checked
- mradermacher/Mistral-Nemo-Kurdish-i1-GGUF: Quantization
- featherless-ai-quants/nazimali-Mistral-Nemo-Kurdish-GGUF: Quantization
- mradermacher/Mistral-Nemo-Kurdish-GGUF: Quantization
- nazimali/Mistral-Nemo-Kurdish-Instruct: LoRA-style