sail/Sailor2-8B-SFT

Full fine-tune vs sail/Sailor2-8B. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 1/1, Norms 55/65, MLP 96/96, Attention 224/224, lm_head 1/1

2 derivatives checked

• mradermacher/Sailor2-8B-SFT-i1-GGUF: Quantization
• mradermacher/Sailor2-8B-SFT-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse