sail/Sailor2-20B-Chat-1203
Full fine-tune vs sail/Sailor2-20B. Fine-tune: 100% of the weights changed, across 64 of 64 layers.
Tensors changed: Embeddings 1/1, Norms 127/129, MLP 192/192, Attention 448/448, lm_head 1/1
1 derivatives checked
- mradermacher/Sailor2-20B-Chat-1203-GGUF: Quantization