nbeerbower/TriplePotato-Mistral-Nemo-15B
Partial fine-tune vs nbeerbower/mistral-nemo-kartoffel-12B. Partial change: 31% of the weights changed (attention, mlp, norms), in 14 of 40 layers.
Tensors changed: Embeddings 0/1, Norms 28/81, MLP 42/120, Attention 56/160, lm_head 0/1
2 derivatives checked
- mradermacher/TriplePotato-Mistral-Nemo-15B-i1-GGUF: Quantization
- mradermacher/TriplePotato-Mistral-Nemo-15B-GGUF: Quantization