Dinesh Singh

Support small businesses: —29 million small businesses in the US —Small businesses employ 57 million people —Small businesses account for 99.7% of all business in US —2/3 of business survive 2 years, half of all will survive 5, and 1/3 will survive 10. #SmallBusinessSaturday

Hugging Face has released a 214-page MASTERCLASS on how to train LLMs > it’s called The Smol Training Playbook > and if want to learn how to train LLMs, > this GIFT is for you > this training bible walks you through the ENTIRE pipeline > covers every concept that matters from why you train, > to what you train, to how you actually pull it off > from pre-training, to mid-training, to post-training > it turns vague buzzwords into step-by-step decisions > architecture, tokenization, data strategy, and infra > highlights the real-world gotchas > instabilities, scaling headaches, debugging nightmares > distills lessons from building actual > state-of-the-art LLMs, not just toy models how modern transformer models are actually built > tokenization: the secret foundation of every LLM > tokenizer fundamentals > vocabulary size > byte pair encoding > custom vs existing tokenizers > all the modern attention mechanisms are here > multi-head attention > multi-query attention > grouped-query attention > multi-latent attention > every positional encoding trick in the book > absolute position embedding > rotary position embedding > yaRN (yet another rotary network) > ablate-by-frequency positional encoding > no position embedding > randomized no position embedding > stability hacks that actually work > z-loss regularization > query-key normalization > removing weight decay from embedding layers > sparse scaling, handled > mixture-of-experts scaling > activation ratio tuning > choosing the right granularity > sharing experts between layers > load balancing across experts > long-context handling via ssm > hybrid models: transformer plus state space models data curation = most of your real model quality > data curation is the main driver of your model’s actual quality > architecture alone won’t save you > building the right data mixture is an art, > not just dumping in more web scrapes > curriculum learning, adaptive mixes, ablate everything > you need curriculum learning: > design data mixes hat evolve as training progresses > use adaptive mixtures that shift emphasis > based on model stage and performance > ablate everything: run experiments to systematically > test how each data source or filter impacts results > smollm3 data > the smollm3 recipe: balanced english web data, > broad multilingual sources, high-quality code, and diverse math datasets > without the right data pipeline, > even the best architecture will underperform the training marathon > do your preflight checklist or die > check your infrastructure, > validate your evaluation pipelines, > set up logging, and configure alerts > so you don’t miss silent failures > scaling surprises are inevitable > things will break at scale in ways they never did in testing > vanishing throughput? that usually means > you’ve got a hidden shape mismatch or > batch dimension bug killing your GPU utilization > sudden drops in throughput? > check your software stack for inefficiencies, > resource leaks, or bad dataloader code > seeing noisy, spiky loss values? > your data shuffling is probably broken, > and the model is seeing repeated or ordered data > performance worse than expected? > look for subtle parallelism bugs > tensor parallel, data parallel, > or pipeline parallel gone rogue > monitor like your GPUs depend on it (because they do) > watch every metric, track utilization, spot anomalies fast > mid-training is not autopilot > swap in higher-quality data to improve learning, > extend the context window if you want bigger inputs, > and use multi-stage training curricula to maximize gains > the difference between a good model and a failed run is > almost always vigilance and relentless debugging during this marathon post-training > post-training is where your raw base model > actually becomes a useful assistant > always start with supervised fine-tuning (sft) > use high-quality, well-structured chat data and > pick a solid template for consistent turns > sft gives you a stable, cost-effective baseline > don’t skip it, even if you plan to go deeper > next, optimize for user preferences > direct preference optimization (dpo), > or its variants like kernelized (kto), > online (orpo), or adversarial (apo) > these methods actually teach the model > what “better” looks like beyond simple mimicry > once you’ve got preference alignment,go on-policy: > reinforcement learning from human feedback (rlhf) > or on-policy distillation, which lets your model learn > from real interactions or stronger models > this is how you get reliability and sharper behaviors > the post-training pipeline is where > assistants are truly sculpted; > skipping steps means leaving performance, > safety, and steerability on the table infra is the boss fight > this is where most teams lose time, > money, and sanity if they’re not careful > inside every gpu > you’ve got tensor cores and cuda cores for the heavy math, > plus a memory hierarchy (registers, shared memory, hbm) > that decides how fast you can feed data to the compute units > outside the gpu, your interconnects matter > pcie for gpu-to-cpu, > nvlink for ultra-fast gpu-to-gpu within a node, > infiniband or roce for communication between nodes, > and gpudirect storage for feeding massive datasets > straight from disk to gpu memory > make your infra resilient: > checkpoint your training constantly, > because something will crash; > monitor node health so you can kill or restart > sick nodes before they poison your run > scaling isn’t just “add more gpus” > you have to pick and tune the right parallelism: > data parallelism (dp), pipeline parallelism (pp), tensor parallelism (tp), > or fully sharded data parallel (fsdp); > the right combo can double your throughput, > the wrong one can bottleneck you instantly to recap > always start with WHY > define the core reason you’re training a model > is it research, a custom production need, or to fill an open-source gap? > spec what you need: architecture, model size, data mix, assistant type > transformer or hybrid > set your model size > design the right data mixture > decide what kind of assistant or > use case you’re targeting > build infra for the job, plan for chaos, pick your stability tricks > build infrastructure that matches your goals > choose the right GPUs > set up reliable storage > and plan for network bottlenecks > expect failures, weird bugs, > and sudden bottlenecks at scale > select your stability tricks in advance: > know which techniques you’ll use to fight loss spikes, > unstable gradients, and hardware hiccups closing notes > the pace of LLM development is relentless, > but the underlying principles never go out of style > and this PDF covers what actually matters > no matter how fast the field changes > systematic experimentation is everything > run controlled tests, change one variable at a time, and document every step > sharp debugging instincts will save you > more time (and compute budget) than any paper or library > deep knowledge of both your software stack > and your hardware is the ultimate unfair advantage; > know your code, know your chips > in the end, success comes from relentless curiosity, > tight feedback loops, and a willingness to question everything > even your own assumptions if i had this two years ago, it would have saved me so much time > if you’re building llms, > read this before you burn gpu months happy hacking

If God wanted us to build Type 1 Civilization, he would have: 1. put a giant fusion reactor in the sky (emitting blackbody radiation around 5800 K) 2. made 28% of Earth's crust out of a semiconductor with a matching bandgap (~1.1 eV or so) 3. filled the oceans with an alkali metal we could use to store limitless quantities of energy (sodium or something similar) That would be a crazy coincidence...

Automatic pizza machine vs worker

Big policy shifts matter, but so do small changes on the ground. If every local business reclaimed two hours/week, that’s time reinvested in customers, hiring, and innovation. ⚡ We’ll show one change you can make in 3 hours. Start here ➡️ celux.co/#get-in-touch

Australia can back its businesses in two ways: policy and practice. Policy takes time - practice can start today. We focus on practical work. Free 3-hr audit ➡️ celux.co/#get-in-touch #BackAustralia #CeluxTips

Still printing paper business cards? Blinq the world’s #1 digital business card Perfect for startups and small businesses who want to look professional and stay paper-free. Try it now➡️ partners.blinq.me/ms72cogiar… #CeluxTips #Networking #SmallBusiness #Productivity