llama.cpp
Better perplexity for 2- and 3-bit quantization for LLaMA-v2-70B
#2807
Merged
Merged
Better perplexity for 2- and 3-bit quantization for LLaMA-v2-70B #2807
ikawrakow
merged
2 commits into
master
from
ik/refine_70B
Login to write a write a comment.
Login via GitHub