The Rise of AI Scams
Author(s): Derrick Mwiti Originally published on Towards AI. Discover the biggest AI scams of 2024 This member-only story is on us. Upgrade to access all of Medium. Photo by Zanyar Ibrahim on Unsplash Some AI companies promised the future of AI, but …
The State of AI Report 2024
Author(s): Derrick Mwiti Originally published on Towards AI. This member-only story is on us. Upgrade to access all of Medium. Photo by julien Tromeur on Unsplash The βState of AI Report 2024β just dropped. Here are the biggest highlights. Letβs start with …
Retrieval Augmented Generation
Author(s): Derrick Mwiti Originally published on Towards AI. This member-only story is on us. Upgrade to access all of Medium. Photo by ZHENYU LUO on Unsplash Retrieving documents from external sources gives language models access to data that they didnβt see during …
The Transformer Architecture
Author(s): Derrick Mwiti Originally published on Towards AI. This member-only story is on us. Upgrade to access all of Medium. Photo by Samule Sun on Unsplash In 2017, Ashish Vaswani et al wrote a paper that would change the natural language processing …
Llama Dive
Author(s): Derrick Mwiti Originally published on Towards AI. This member-only story is on us. Upgrade to access all of Medium. Photo by Gustavo EspΓndola on Unsplash Itβs no doubt that generative AI will change every industry. The current state of generative AI, …
Large Language Model Evaluation Metrics
Author(s): Derrick Mwiti Originally published on Towards AI. This member-only story is on us. Upgrade to access all of Medium. Photo by Possessed Photography on Unsplash The most common evaluating metrics for large language models are: PerplexityBLEUROUGEBERTScoreCOMETMETEORBLEURTGPTScorePRISMBARTScoreG-EvalHuman Evaluation Evaluating large language models(LLMs) …
How to Fine-Tune Llama 2 With LoRA
Author(s): Derrick Mwiti Originally published on Towards AI. This member-only story is on us. Upgrade to access all of Medium. Photo by Simon Wiedensohler on Unsplash Until recently, fine-tuning large language models (LLMs) on a single GPU was a pipe dream. This …