Nimbz/Froopert-31B
Full fine-tune vs Gryphe/Pantheon-Reasoning-31B-1.1. Fine-tune: 94% of the weights changed, across 60 of 60 layers.
Tensors changed: Embeddings 0/4, Norms 199/523, other 0/62, MLP 180/261, Attention 230/338
4 derivatives checked
- bartowski/Nimbz_Froopert-31B-GGUF: Same weights, converted (fewer layers)
- mradermacher/Froopert-31B-i1-GGUF: Quantization (fewer layers)
- Nimbz/Froopert-31B-GGUF: Quantization (fewer layers)
- mradermacher/Froopert-31B-GGUF: Quantization (fewer layers)