nn-tech/MetalGPT-1

Full fine-tune vs t-tech/T-pro-it-2.0. Fine-tune: 100% of the weights changed, across 64 of 64 layers.

Tensors changed: Norms 255/257, MLP 192/192, Attention 256/256

1 derivatives checked

• NuisanceValue/MetalGPT-1-GGUF: Quantization

1 other repos hold byte-for-byte identical weight files.

On the Hub · Downloads on Model Pulse