NovaCorp/Novaciano.Requiem-3.2-1B

Full fine-tune vs NovaCorp/Novaciano-3.2-1B. Fine-tune: 100% of the weights changed, across 16 of 16 layers.

Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 8/33, MLP 48/48, Attention 64/64

2 derivatives checked

• mradermacher/Novaciano.Requiem-3.2-1B-i1-GGUF: Quantization
• mradermacher/Novaciano.Requiem-3.2-1B-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse