sail/Sailor-1.8B
Full fine-tune vs Qwen/Qwen1.5-1.8B. Fine-tune: 100% of the weights changed, across 24 of 24 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 4/49, MLP 72/72, Attention 168/168
5 derivatives checked
- mradermacher/Sailor-1.8B-GGUF: Same weights, converted
- sail/Sailor-1.8B-Chat-gguf: Full fine-tune
- featherless-ai-quants/sail-Sailor-1.8B-GGUF: Quantization
- sail/Sailor-1.8B-Chat: Full fine-tune
- tensorblock/Sailor-1.8B-GGUF: Quantization