UpTrain (YC W23)
open-source tool to evaluate LLM response quality. The Problem: Unlike traditional Machine learning or Deep learning models where we always have a unique Ground Truth and can define metrics like Precision, Recall, accuracy, etc.
Reactions (1)
Similar products
by description similarity
UpTrain
github.comA Practical Approach to Finetuning LLMs for Custom Use-Cases
Uptrace
github.comopen-source APM (alternative to Datadog, NewRelic)
Haven (YC S23)
haven.runQuickly iterate when fine-tuning open-source LLMs
I Made YC Rejection Simulator
yc-sim.vercel.app