Yugen.aiinYugen.ai Technology BlogLLM Model Composition from scratchA simplified implementation of Google Research & Google DeepMind’s CALM (Composition to Augment Language Models) paperAug 18Aug 18
Yugen.aiinYugen.ai Technology BlogUnlocking Financial Insights: RAGs for Precise Information Retrieval from 10-K reportsBy Deepak Jangra, Akshay SinghAug 13Aug 13
Yugen.aiinYugen.ai Technology BlogEfficient LLM Fine-Tuning: LoRA, DoRA, and Apple’s Innovative ApproachUnderstanding the impact of LoRA Adapters and breaking down the Model adaptation optimization techniques to enhance the ability of…Jun 23Jun 23
Yugen.aiinYugen.ai Technology BlogAchieving a 6x improvement in Data Ingestion in ImplyRunning the (experimental) Multi-Stage Query Ingestion in ProductionApr 3Apr 3
Yugen.aiinYugen.ai Technology BlogRAFT — RAGs Meet Fine-TuningRAFTs (Retrieval-Augmented Fine-Tuning) combine strengths of RAGs and Domain Specific Fine-tuning to better adapt pre-trained LLMs for…Mar 311Mar 311
Yugen.aiinYugen.ai Technology BlogOptimise Cloud Composer 1 Costs — From $188/day to $11/dayIntroductionFeb 14Feb 14
Yugen.aiinYugen.ai Technology BlogYugen.ai Turns OneLearnings from 2020 and Predictions for 2021Jan 7, 20211Jan 7, 20211