arcee-ai/Virtuoso-Lite-PreDistill

Full fine-tune vs tiiuae/Falcon3-10B-Base. Fine-tune: 100% of the weights changed, across 40 of 40 layers.

Tensors changed: Embeddings 1/1, Norms 81/81, MLP 120/120, Attention 160/160, lm_head 1/1

2 derivatives checked

• mradermacher/Virtuoso-Lite-PreDistill-i1-GGUF: Quantization
• mradermacher/Virtuoso-Lite-PreDistill-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse