marcuscedricridia/Springer-32B
Partial fine-tune vs Qwen/Qwen2.5-32B. Partial change: 86% of the weights changed (attention, mlp, norms), in 64 of 64 layers.
Tensors changed: Norms 75/129, MLP 166/192, Attention 333/448
5 derivatives checked
- mradermacher/Springer-32B-GGUF: Quantization
- marcuscedricridia/Springer1.2-32B-1: Full fine-tune
- marcuscedricridia/Springer-32B-RP-1: Full fine-tune
- marcuscedricridia/Springer-32B-1: Full fine-tune
- marcuscedricridia/Springer-32B-RP-7: Full fine-tune