marcuscedricridia/Springer-32B-RP-1
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
3 derivatives checked
- mradermacher/Springer-32B-RP-1-GGUF: Quantization
- marcuscedricridia/Springer1.0-32B-Qwen2.5-RP: Full fine-tune
- marcuscedricridia/Springer1.1-32B-Qwen2.5-RP: Full fine-tune