shenzhi-wang/Llama3-70B-Chinese-Chat-GGUF-4bit
Full fine-tune vs meta-llama/Meta-Llama-3-70B-Instruct. shenzhi-wang/Llama3-70B-Chinese-Chat-GGUF-4bit is a GGUF (Q4_0) of different weights. Fine-tune: 100% of the weights changed, across 80 of 80 layers.
Tensors changed: Embeddings 1/1, Norms 126/161, MLP 240/240, Attention 320/320, lm_head 1/1