LLMs-from-scratch and train-llm-from-scratch
These are competitors offering alternative pedagogical approaches to the same goal: the first provides a comprehensive, step-by-step implementation guide emphasizing architectural understanding, while the second offers a more streamlined, end-to-end training pipeline prioritizing practical results.
About LLMs-from-scratch
rasbt/LLMs-from-scratch
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
Covers the complete pipeline from tokenization and attention mechanisms through pretraining on unlabeled data and finetuning for classification and instruction-following tasks. Includes practical implementations of multi-head attention, causal masking, and parameter-efficient techniques like LoRA, alongside code for loading pretrained model weights. Organized as Jupyter notebooks and standalone Python scripts that progressively build a functional GPT architecture while explaining each component's role in modern LLM training.
About train-llm-from-scratch
FareedKhan-dev/train-llm-from-scratch
A straightforward method for training your LLM, from downloading data to generating text.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work