train-llm-from-scratch alternatives
Curated alternatives to train-llm-from-scratch — and why you'd switch.
trl
Hugging Face's post-training library: SFT, DPO, GRPO, KTO and reward-model trainers on top of Transformers — from a Colab LoRA run to multi-GPU deployments.
Why switchSame post-training algorithms, opposite purposes: TRL is the production library you call; this re-implements SFT/PPO/DPO/GRPO by hand so you can read them. Learn here, ship with TRL.
Full comparison →mini-AGI
Continual-learning byte-level LM trained from scratch on one 8 GB GPU: weights page in from disk, capacity grows and prunes itself while it keeps reading a single data stream.
Why switchBoth train your own small LM from scratch on a single GPU; train-llm-from-scratch teaches the standard pretrain→SFT→RL pipeline, mini-AGI experiments with never-ending continual learning instead.
Full comparison →