Aris TsakpinisinTowards Data ScienceA Deep Dive into In-Context LearningStepping out of the “comfort zone” — part 2/3 of a deep-dive into domain adaptation approaches for LLMs10 min read·22 hours ago--
Shlomo TannorExploring RAG Applications Across Languages: Conversing with the MishnahRobot studying The Mishnah. Credit: DALL-E-3.15 min read·May 23, 2024--
Ida SilfverskiöldinTowards Data ScienceFine-Tune Smaller Transformer Models: Text ClassificationUsing Microsoft’s Phi-3 to generate synthetic data17 min read·3 days ago----
Jan MajewskiinTowards Data ScienceImprove LLM output reliability with Python guardrailsLeverage validation functions to prevent your LLM outputs from falling of a cliff·9 min read·1 day ago--1--1
Bradney SmithinTowards Data ScienceSelf-Attention Explained with CodeHow large language models create rich, contextual embeddings31 min read·Feb 9, 2024--1--1
Aris TsakpinisinTowards Data ScienceA Deep Dive into In-Context LearningStepping out of the “comfort zone” — part 2/3 of a deep-dive into domain adaptation approaches for LLMs10 min read·22 hours ago--
Shlomo TannorExploring RAG Applications Across Languages: Conversing with the MishnahRobot studying The Mishnah. Credit: DALL-E-3.15 min read·May 23, 2024--
Ida SilfverskiöldinTowards Data ScienceFine-Tune Smaller Transformer Models: Text ClassificationUsing Microsoft’s Phi-3 to generate synthetic data17 min read·3 days ago--
Jan MajewskiinTowards Data ScienceImprove LLM output reliability with Python guardrailsLeverage validation functions to prevent your LLM outputs from falling of a cliff·9 min read·1 day ago--1
Bradney SmithinTowards Data ScienceSelf-Attention Explained with CodeHow large language models create rich, contextual embeddings31 min read·Feb 9, 2024--1
Bradney SmithinTowards Data ScienceA Complete Guide to BERT with CodeHistory, Architecture, Pre-training, and Fine-tuning43 min read·May 13, 2024--3
Nida AibaniThe Art of Prompt Engineering: The APE FrameworkThe Art of Prompt Engineering: The APE Framework3 min read·2 hours ago--
Michał Marcińczuk, Ph.D.inTowards Data ScienceReducing the Size of Docker Images Serving Large Language ModelsHave you encountered a problem where a 1 GB transformer-based model increases even up to 8 GB when deployed using Docker containerization?·6 min read·May 3, 2024--4