mergekit-community/2xPIMPY3xBAPE-OPP5
Partial fine-tune vs nbeerbower/Mistral-Nemo-Prism-12B-v7. Partial change: 89% of the weights changed (attention, mlp, norms), in 40 of 40 layers.
Tensors changed: Embeddings 0/1, Norms 30/81, MLP 120/120, Attention 160/160, lm_head 0/1
2 derivatives checked
- mradermacher/2xPIMPY3xBAPE-OPP5-i1-GGUF: Quantization
- mradermacher/2xPIMPY3xBAPE-OPP5-GGUF: Quantization
4 other repos hold byte-for-byte identical weight files.