QuantFactory/Sailor2-L-8B-Chat-GGUF
Full fine-tune vs sail/Sailor2-L-8B. QuantFactory/Sailor2-L-8B-Chat-GGUF is a GGUF (Q8_0) of different weights. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 56/65, MLP 96/96, Attention 224/224, lm_head 1/1