sail/Sailor2-1B-Chat
Full fine-tune vs sail/Sailor2-1B. Fine-tune: 100% of the weights changed, across 48 of 48 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 33/97, MLP 144/144, Attention 336/336
4 derivatives checked
- bartowski/Sailor2-1B-Chat-GGUF: Same weights, converted
- MaziyarPanahi/Sailor2-1B-Chat-GGUF: Same weights, converted
- mradermacher/Sailor2-1B-Chat-GGUF: Same weights, converted
- DevQuasar-6/sail.Sailor2-1B-Chat-GGUF: Quantization