marcuscedricridia/Springer-32B-RP-7
Full fine-tune vs marcuscedricridia/Springer-32B. Fine-tune: 100% of the weights changed, across 64 of 64 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 128/129, MLP 192/192, Attention 448/448
1 derivatives checked
- mradermacher/Springer-32B-RP-7-GGUF: Quantization