Nirmalya GhoshinAI AdvancesUsing Mixtral 8x7B For NLP Tasks On Small GPUsLarge language models (LLM) are made up of billions of parameters, thus posing challenges when loading them onto GPU memory for model…Jan 15Jan 15
Nirmalya Ghosh13 Ways To Speedup Python Loops With Minimal EffortTo achieve a 1.3x to 970x speedupDec 31, 20231Dec 31, 20231
Nirmalya GhoshA Quick Overview Of Active LearningActive learning is a type of machine learning in which the learning algorithm actively selects the data it learns from, rather than…Oct 23, 2023Oct 23, 2023
Nirmalya GhoshTranscribe Singlish with OpenAI’s Whisper? “Can meh?”About a week ago, OpenAI released a new AI model that can transcribe speech with 50% fewer mistakes than previous models. The new model…Sep 27, 20221Sep 27, 20221