Manish ChablaniAligning LLMs with Direct Preference Optimization (DPO)— background, overview, intuition and paper…Direct Preference Optimization (DPO) is a stable, performant, and computationally lightweight, technique for aligning LLM’s with a simple…3 min read·Feb 9, 2024----
Manish ChablaniASR ML Systems: Overview and latest model architectures: Transducers, TDTTraditional ASR pipeline:8 min read·Feb 8, 2024----
Manish ChablaniLarge Language Models: Collection of papers, architectures and ideas across different LLM’s: GPT…Here we summarize key insights from following:5 min read·Feb 3, 2024----
Manish ChablaniLarge Language Models: Collection of papers, architectures and ideas across different LLM’s: PART…OLMo: https://arxiv.org/abs/2402.008384 min read·Feb 3, 2024----
Manish ChablaniVision Transformer (ViT) — AN IMAGE IS WORTH 16X16 WORDS: TRANSFORMERS FOR IMAGE RECOGNITION AT…Paper Summary: Vision Transformer (ViT)5 min read·Feb 2, 2024----
Manish ChablaniRecommendation system / Search / IR evaluation metricsMetrics in Recommendation Systems / Retrival / Ranking:3 min read·Dec 28, 2023----
Manish ChablaniEmbedding-based Retrieval in Facebook SearchPaper: https://arxiv.org/abs/2006.11632·16 min read·Dec 14, 2023----
Manish ChablaniMeasuring feature importance, removing correlated featuresLinear model like linear regression or logistic regression: Identify the coefficients ( β ) in the linear regression equation for each…·6 min read·Dec 13, 2023----
Manish ChablaniGPT and other LLM’s: decoder only v/s encoder-decoder models?Pre LLM, during the times of seq2seq models, encoder-decoder architectures were popular for Q&A, language translation and summarization…·1 min read·Dec 9, 2023--1--1
Manish ChablaniGraph Neural Nets Explained: Summary of different graph embedding methods.Node2Vec :13 min read·Dec 5, 2023----