QuantFactory/Yi-Coder-9B-Chat-Instruct-TIES-GGUF
Full fine-tune vs 01-ai/Yi-Coder-9B. QuantFactory/Yi-Coder-9B-Chat-Instruct-TIES-GGUF is a GGUF (Q8_0) of different weights. Fine-tune: 100% of the weights changed, across 48 of 48 layers.
Tensors changed: Embeddings 1/1, Norms 72/97, MLP 144/144, Attention 192/192, lm_head 1/1