QuantFactory/Sailor2-1B-Chat-GGUF
Full fine-tune vs sail/Sailor2-1B. QuantFactory/Sailor2-1B-Chat-GGUF is a GGUF (Q8_0) of different weights. 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