PinnedJeremy KinThe PythoneersRed-teaming your LLM with ALERT and LlamaCPPA practical guide to assessing LLM safety: benchmarking the Mistral-Nemo-Instruct-2407 modelSep 3Sep 3
PinnedJeremy KinThe PythoneersVoice recognition VS audio deepfakesHow good is voice recognition at detecting cloned voices?May 81May 81
PinnedJeremy Kin𝐀𝐈 𝐦𝐨𝐧𝐤𝐬.𝐢𝐨MetaCLIP: pushing past the limits of CLIP — a comprehensive insightIn the ever-changing field of artificial intelligence, OpenAI’s CLIP has undeniably stood out as a pivotal model, seamlessly connecting…Jan 12Jan 12
PinnedJeremy Kin𝐀𝐈 𝐦𝐨𝐧𝐤𝐬.𝐢𝐨Image similarity with DINOv2 and FAISSExplore the robust performance of DINOv2 in image similarity tasks and gain valuable insights into its capabilities…Sep 27, 20236Sep 27, 20236
Jeremy KinThe PythoneersOffline RAG with LlamaIndex and tiny and small LLMsA walk through to build a simple RAG system using LlamaIndex and TinyLlama1.1B and Zephyr-7B-Gemma-v0.1. Insights and potential…Mar 131Mar 131
Jeremy Kin𝐀𝐈 𝐦𝐨𝐧𝐤𝐬.𝐢𝐨Exploring offline RAG with Langchain, Zephyr-7b-beta and DeciLM-7bIn 2023, large language models (LLMs) have taken center stage, with Retrieval Augmented Generation (RAG) becoming the buzzword of recent…Dec 26, 20233Dec 26, 20233
Jeremy Kin𝐀𝐈 𝐦𝐨𝐧𝐤𝐬.𝐢𝐨Optimizing Transformers Models for Peak PerformanceWith each passing day, a fresh wave of AI models emerges, surpassing their predecessors in both intelligence and intricacy. This…Oct 31, 2023Oct 31, 2023
Jeremy Kin𝐀𝐈 𝐦𝐨𝐧𝐤𝐬.𝐢𝐨Large Language Models and Data PrivacyNowadays, Large Language Models (LLMs) have become ubiquitous, with names like ChatGPT, BARD, PaLM, and Claude leading the way. These…Oct 5, 2023Oct 5, 2023
Jeremy Kin𝐀𝐈 𝐦𝐨𝐧𝐤𝐬.𝐢𝐨CLIP Vs DINOv2 in image similarityTwo giants stand tall in the realm of computer vision: CLIP and DINOv2. This story benchmarks their performance for image similarity tasks.Oct 3, 20234Oct 3, 20234
Jeremy Kin𝐀𝐈 𝐦𝐨𝐧𝐤𝐬.𝐢𝐨SeamlessM4T vs. Whisper — A Speech-to-Text BenchmarkRecently, MetaAI unveiled their latest creation: “SeamlessM4T,” a groundbreaking, all-in-one multimodal translation model. This remarkable…Sep 22, 20232Sep 22, 20232