people spent years optimizing GANs before realizing that diffusion models were simpler and better people spent years developing RLHF before realizing that DPO is simpler and better what are we working on rn? i want to find the simpler and better version and work on that instead
LLMS
-
Building Knowledge Graphs From Text Using LangChain
By
–
Build Knowledge Graph From TextData using LangChain Converting text to knowledge graphs can be helpful for both visualizing the data and allowing for structured querying later on This blog goes through how to use LLMs to extract knowledge triplets https://
medium.com/@mahimairaja/b
uild-knowledge-graph-from-textdata-using-langchain-under-2min-ce0d0d0e44e8
… -
Practical LangChain Expression Language Guide for AI Chains
By
–
Practical Hands-on with Langchain Expression Language (LCEL) Good article by Anurag Misrah covering LCEL and some practical things you can do with it: 1) Run Two Chains in parallel 2) Insert input dynamically in Runtime
3) Dynamic Routing & more! https://
medium.com/@anuragmishra_
27746/practical-hands-on-with-langchain-expression-language-lcel-for-building-langchain-agent-chain-2a9364dc4ca3
… -
DoRA: Weight-Decomposed Low-Rank Adaptation Technique
By
–
DoRA: Weight-Decomposed Low-Rank Adaptation Liu et al.: https://
arxiv.org/abs/2402.09353 #ArtificialIntelligence #DeepLearning #MachineLearning -
Gemini-1.5 Breakthrough Overshadowed by Sora Release
By
–
I’m feeling bummed that Sora overshadowed Gemini-1.5 — the improvements there were ground breaking (10M context window that was effective, 1.5-Pro Beats 1.0-Ultra indicating a fundamental improvement). And available for access.
-
DoRA: Weight-Decomposed Low-Rank Adaptation for Models
By
–
DoRA: Weight-Decomposed Low-Rank Adaptation Liu et al.: https://
arxiv.org/abs/2402.09353 #ArtificialIntelligence #DeepLearning #MachineLearning -
Gemini 1.5 Context Window Revolutionizes RAG Capabilities
By
–
Gemini 1.5 is a much bigger deal than Sora. 1. The 10M context window fundamentally changes how we think about RAG. Not just large, but also effective. 2. Pro-1.5 Beats Ultra-1.0. There’s a fundamental modeling improvement. 3. It’s in production, you can use it today. I too
-
Anticipation for OpenAI Response to Gemini API Release
By
–
Getting hyped. Prepare for open ais answering call when Geminis API is released
-
Python, Machine Learning, MLOps, CV/NLP, LLMs tutorials daily
By
–
If you are interested in: – Python – Machine Learning – MLOps – CV/NLP – LLMs Find me → @Sumanth_077 Everyday, I share tutorials on above topics! Like/RT the first tweet to help this reach more people!
-
Questioning Arguments Against LLM Physics Understanding
By
–
So you argument against LLM understanding physics is what exactly?