rasbt/LLMs-from-scratch
▲ +499 ★ this week
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
Official Code for "Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents"
$ git clone https://github.com/huangwl18/language-planner.git▲ +499 ★ this week
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
▲ +5 ★ this week
RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RNN and transformer - great performance, linear time, constant space (no kv-cache), fast training, infinite ctx_len, and free sentence embedding.
▲ +16 ★ this week
Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"
▲ +7 ★ this week
《大语言模型》作者:赵鑫,李军毅,周昆,唐天一,文继荣
An open-source framework for training large multimodal models.
Self-contained Machine Learning and Natural Language Processing library in Go
Data from GitHub · snapshot Nov 16, 2026