Show HN: Beating OpenAI's structured outputs on cost, accuracy and speed (boundaryml.com) 8 points by hellovai 1y ago ↗ HN
[–] ddematheu 1y ago ↗ Interesting performance with GPT 3.5, what does performance on Llama look like? What about smaller models like Llama 3.1? [–] hellovai 1y ago ↗ We have some preliminary data with llama3.1 and we find that the smaller model gets to around 70% with BAML (+20% from base), but we'll update this dashboard with llama3.1 by end of week!
[–] hellovai 1y ago ↗ We have some preliminary data with llama3.1 and we find that the smaller model gets to around 70% with BAML (+20% from base), but we'll update this dashboard with llama3.1 by end of week!
2 comments
[ 2.5 ms ] story [ 21.8 ms ] thread