mentalium's banner
mentalium's profile picture

mentalium

@mentalium_ • 5,353 subscribers

think like a mentalist. influence like one

Shorts

this is the most DANGEROUS thing on internet today Stanford’s free CS336 course teaches you how to build LLMs from scratch From tokenization and Transformer architecture to GPU kernels, scaling laws, data and post-training 01 Course site 02 Lecture 1 — Overview and Tokenization 03 Lecture 2 — PyTorch and Resource Accounting 04 Lecture 3 — Architectures 05 Lecture 4 — Attention Alternatives and Mixture of Experts 06 Lecture 6 — GPU Kernels and Triton 07 Lecture 7 — Parallelism 08 Lecture 9 — Scaling Laws 09 Lecture 13 — Data 10 Lecture 15 — Mid/Post-training (SFT/RLHF) GitHub: The course materials are FREE You can keep collecting playlists, or start building right now Save this ↓

this is the most DANGEROUS thing on internet today Stanford’s free CS336 course teaches you how to build LLMs from scratch From tokenization and Transformer architecture to GPU kernels, scaling laws, data and post-training 01 Course site 02 Lecture 1 — Overview and Tokenization 03 Lecture 2 — PyTorch and Resource Accounting 04 Lecture 3 — Architectures 05 Lecture 4 — Attention Alternatives and Mixture of Experts 06 Lecture 6 — GPU Kernels and Triton 07 Lecture 7 — Parallelism 08 Lecture 9 — Scaling Laws 09 Lecture 13 — Data 10 Lecture 15 — Mid/Post-training (SFT/RLHF) GitHub: The course materials are FREE You can keep collecting playlists, or start building right now Save this ↓

26,484 Aufrufe

andrej karpathy: “LLMs are easy. AI agents with real memory and production systems are the hard part.” Harvard just opened the free course that actually teaches the infrastructure behind it this is the real systems knowledge that separates people who understand models from people who just prompt them 01 Full site 02 Volume I — Introduction to Machine Learning Systems 03 Volume II — Scaling Machine Learning Systems 04 TinyTorch — Build your own ML framework from scratch 05 Interactive Labs 06 MLSys·im — Model system bottlenecks 07 StaffML — Systems design practice 08 Lecture slides 09 Hardware kits 10 GitHub repo 11 Instructor hub 12 Taxonomy 13 Volume III — Agentic systems (draft) 14 Volume IV — Physical AI (draft) 15 The full path. Free. you either open this now or keep collecting random playlists for another year save this ↓

andrej karpathy: “LLMs are easy. AI agents with real memory and production systems are the hard part.” Harvard just opened the free course that actually teaches the infrastructure behind it this is the real systems knowledge that separates people who understand models from people who just prompt them 01 Full site 02 Volume I — Introduction to Machine Learning Systems 03 Volume II — Scaling Machine Learning Systems 04 TinyTorch — Build your own ML framework from scratch 05 Interactive Labs 06 MLSys·im — Model system bottlenecks 07 StaffML — Systems design practice 08 Lecture slides 09 Hardware kits 10 GitHub repo 11 Instructor hub 12 Taxonomy 13 Volume III — Agentic systems (draft) 14 Volume IV — Physical AI (draft) 15 The full path. Free. you either open this now or keep collecting random playlists for another year save this ↓

15,674 Aufrufe

I spent 4 months collecting this so you don’t have to waste the same time Most people will save this and never open a single link. This is the clean path from zero to being able to build and interview for real AI roles 01 Linear algebra and calculus 02 Machine learning foundations 03 Deep learning from scratch 04 Neural networks and backprop 05 Computer vision 06 Natural language processing 07 Transformers and LLMs 08 Reinforcement learning 09 Building agents 10 The full path. Free You either walk this now or keep watching random playlists for another year Save this ⭣

I spent 4 months collecting this so you don’t have to waste the same time Most people will save this and never open a single link. This is the clean path from zero to being able to build and interview for real AI roles 01 Linear algebra and calculus 02 Machine learning foundations 03 Deep learning from scratch 04 Neural networks and backprop 05 Computer vision 06 Natural language processing 07 Transformers and LLMs 08 Reinforcement learning 09 Building agents 10 The full path. Free You either walk this now or keep watching random playlists for another year Save this ⭣

39,127 Aufrufe

Machine learning is the most f*cking DANGEROUS thing to understand and nobody is learning it like this This free collection of 500+ ML cheatsheets is the clean version I wish I had from the start. Most people will save this and never open it. This is MLCheatSheets. Theory, formulas, and code in one place. 01 The full collection 02 Learning roadmap 03 Course guide 04 All cheatsheets 05 Exercises 06 Animations and visuals 07 Setup and how to use 08 Illustrations table 09 Prospects and future 10 The full path. Free. You either open this now or keep collecting random playlists for another year. Save this ⭣

Machine learning is the most f*cking DANGEROUS thing to understand and nobody is learning it like this This free collection of 500+ ML cheatsheets is the clean version I wish I had from the start. Most people will save this and never open it. This is MLCheatSheets. Theory, formulas, and code in one place. 01 The full collection 02 Learning roadmap 03 Course guide 04 All cheatsheets 05 Exercises 06 Animations and visuals 07 Setup and how to use 08 Illustrations table 09 Prospects and future 10 The full path. Free. You either open this now or keep collecting random playlists for another year. Save this ⭣

22,699 Aufrufe

I spent 5 months collecting this so you don’t have to waste the same time Anthropic will hire you if you understand these topics well This free UCSB course covers the numerical algorithms behind data science and machine learning 01 Matrix computation 02 Systems of linear equations 03 Eigenvalues and singular values 04 Numerical optimization 05 Using numpy and scipy correctly 06 The real foundations of ML 07 Course materials (GitHub) 08 Lectures and notebooks 09 Homework and projects 10 The full path. Free. You either open this now or keep collecting random playlists for another year. Save this ⬇️

I spent 5 months collecting this so you don’t have to waste the same time Anthropic will hire you if you understand these topics well This free UCSB course covers the numerical algorithms behind data science and machine learning 01 Matrix computation 02 Systems of linear equations 03 Eigenvalues and singular values 04 Numerical optimization 05 Using numpy and scipy correctly 06 The real foundations of ML 07 Course materials (GitHub) 08 Lectures and notebooks 09 Homework and projects 10 The full path. Free. You either open this now or keep collecting random playlists for another year. Save this ⬇️

12,320 Aufrufe

Videos

Keine weiteren Inhalte verfügbar