SupraLabs/Supra2-100M-Instruct

Full fine-tune vs SupraLabs/Supra2-100M-Base. Fine-tune: 100% of the weights changed, across 12 of 12 layers.

Tensors changed: Embeddings 1/1, Norms 49/49, MLP 36/36, Attention 48/48

1 derivatives checked

• liodon-ai/Supra2-100M-Instruct-imatrix-GGUF: Quantization

On the Hub · Downloads on Model Pulse