LLM training

AI agents running research on single-GPU nanochat training automatically

The best ChatGPT that $100 can buy.

Fully open reproduction of DeepSeek-R1

verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework

🧠 Train a 64M-parameter LLM from scratch in just 2h!

📚 从零开始构建大模型

LLM101n: Let's build a Storyteller

llama3 implementation one matrix multiplication at a time

LLM training in simple, raw C/CUDA

《动手学大模型Dive into LLMs》系列编程实践教程

Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.8, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM5.3, Gemma4, Llava, Phi4, ...) (AAAI 2025).

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

Inference Llama 2 in one file of pure C

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

Code and documentation to train Stanford's Alpaca models, and generate the data.

The simplest, fastest repository for training/finetuning medium-sized GPTs.

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training

Train transformer language models with reinforcement learning.

Ongoing research training transformer models at scale