Synthia-7B-v1.3 hits 64.85 on 4-evals; LLaMA-2-70B-Chat at 66.8 (twitter.com) 2 points by JackRumford 2y ago ↗ HN
[–] sgolem 2y ago ↗ Can this be run with llama.cpp? [–] JackRumford 2y ago ↗ yep. this guy keeps up to date with quantised models: https://huggingface.co/TheBloke
[–] JackRumford 2y ago ↗ yep. this guy keeps up to date with quantised models: https://huggingface.co/TheBloke
3 comments
[ 3.3 ms ] story [ 27.8 ms ] thread