sail/Sailor-1.8B-Chat
Full fine-tune vs sail/Sailor-1.8B. Fine-tune: 100% of the weights changed, across 24 of 24 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 43/49, MLP 72/72, Attention 168/168
4 derivatives checked
- mradermacher/Sailor-1.8B-Chat-GGUF: Same weights, converted
- featherless-ai-quants/sail-Sailor-1.8B-Chat-GGUF: Quantization
- tensorblock/Sailor-1.8B-Chat-GGUF: Quantization
- DevQuasar-5/sail.Sailor-1.8B-Chat-GGUF: Quantization