PinnedAuro TripathyRule-based Reasoning in LLMs via Stepwise RefinementRemember learning to program? My teacher, and ardent disciple of Niklaus Wirth, taught us the principle of stepwise refinement as we worked…4 min read·6 days ago----
PinnedAuro TripathyDistilling DistillationQuestion: Is 2024 the year of slimming down LLMs into lithe and sprightly SLMs? SLM, of course stands for Small Language Model, and aptly…4 min read·Feb 4, 2024----
PinnedAuro TripathySELF-INSTRUCT, the Low-cost LLM Alignment ProcessThis post is an easy-to-digest explanation of the seminal SELF-INSTRUCT paper that led to another influential work, Stanford Alpaca.6 min read·May 8, 2023--1--1
PinnedAuro TripathySpend Tokens to Make TokensThe old adage, you have to spend money to make money can bear fruit if you know what to spend it on. In the case of ChatGPT, you have to…8 min read·Mar 20, 2023----
PinnedAuro TripathyChatGPT’s Brush with DeceptionGandhi, the storied leader of India’s fight for freedom, logged his life experiments with truth and that inspired me to log ChatGPT’s…2 min read·Dec 11, 2022----
Auro TripathyDistilling with LLM-Generated Rationales Yields Outperformance in Task-Specific Fine-tuning!Large Language Models are challenging to serve in practice making implementers gravitate towards distilled models. Distillation yields…4 min read·May 28, 2023----
Auro TripathyAstronauts Riding Horses? That’s Old. Daydream your way to riding a Unicorn.Here’s a jargon-free way to explain Dreambooth so use can dream-up hitherto unimagined use-cases. We call our app DayDream, a lightweight…2 min read·Nov 14, 2022----
Auro TripathyGPT3 does Dishes? No, use it to Query your Dishwasher Repair ManualOh, have I got your attention now? We’re on a mission to retire the phrase RTFM and coin something new; QTM (Query the Manual).3 min read·Oct 27, 2022--1--1
Auro TripathyinGeek CultureLong for Symbolic Processing? Meanwhile, get to know your TokenizerThe lively debate about augmenting machine Learning with symbolic processing rages on. Until we get a break-thru, we must live with…3 min read·Oct 10, 2022----
Auro TripathyA BERT Flavor to Sample and SavorThankfully, we can derive a variety of models from the BERT architecture to fit our memory and latency needs. Turns out, model capacity…2 min read·Jan 10, 2022----