Novaciano/Cerberus-3.2-1B

Full fine-tune vs AiAF/Pretrained-SCP-1B-QLoRA. Fine-tune: 100% of the weights changed, across 16 of 16 layers.

Tensors changed: Embeddings 1/1, Norms 33/33, MLP 48/48, Attention 64/64

1 derivatives checked

• mradermacher/Cerberus-3.2-1B-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse