sail/Sailor-0.5B-Chat

Full fine-tune vs sail/Sailor-0.5B. Fine-tune: 100% of the weights changed, across 24 of 24 layers.

Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 45/49, MLP 72/72, Attention 168/168

2 derivatives checked

• mradermacher/Sailor-0.5B-Chat-GGUF: Same weights, converted
• DevQuasar-5/sail.Sailor-0.5B-Chat-GGUF: Quantization

On the Hub · Downloads on Model Pulse