Build a Transformer from Scratch in Python
Build a working transformer block in PyTorch from scratch — attention, feed-forward, residuals, and layer norm — and see how the pieces of an LLM fit together.
Khushal Jethava
The Attention Mechanism in LLMs, Explained with Python
Understand self-attention — the core of every transformer — by building it in NumPy. Queries, keys, values, scaling, and softmax, explained with runnable code.
Prompt Engineering Techniques in Python: A Practical Guide
Practical prompt engineering in Python — few-shot prompting, chain-of-thought, structured output, and role prompting, each with runnable code and when to use it.
Build an LLM Agent from Scratch in Python
Build a working LLM agent in Python without a framework — a tool-calling loop, a tool registry, and reasoning steps. Understand what LangChain and LangGraph do under the hood.
Кортежи в Python: полное руководство с методами и примерами использования
Разбираемся с кортежами в Python — неизменяемость, упаковка и распаковка, именованные кортежи, методы count() и index() — с рабочими примерами и советами, когда выбирать кортеж вместо списка.
Множества (set) в Python: полное руководство по всем методам
Изучите множества Python — создание, уникальность, алгебра множеств и все встроенные методы (union, intersection, difference, symmetric_difference и другие) с рабочими примерами и разбором того, чт...
Python Lists: The Complete Guide with All Methods
Master Python lists — creation, indexing, slicing, comprehensions, and every built-in method (append, extend, insert, sort, and more) with runnable examples and gotchas.
Python Dictionaries: The Complete Guide with All Methods
Master Python dictionaries — creation, access, iteration, and every built-in method (get, items, keys, pop, setdefault, update, and more) with runnable examples and gotchas.
.webp)
Встроенные функции Python: полный справочник
Все встроенные функции Python с рабочими примерами, подводными камнями и советами, когда что использовать — abs, zip, map, enumerate, sorted и ещё 50+.
Build a Reasoning LLM from Scratch in Python
Build a reasoning LLM from scratch in Python — a BPE tokenizer, RoPE attention, SwiGLU transformer blocks, and chain-of-thought dual-loss training. No APIs, no wrappers, just pure PyTorch.