sail/Sailor2-L-1B-SFT

Full fine-tune vs sail/Sailor2-L-1B. Fine-tune: 100% of the weights changed, across 48 of 48 layers.

Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 35/97, MLP 144/144, Attention 333/336

1 derivatives checked

• mradermacher/Sailor2-L-1B-SFT-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse