karpathy / build-nanogptLinks
Video+code lecture on building nanoGPT from scratch
☆4,443Updated last year
Alternatives and similar repositories for build-nanogpt
Users that are interested in build-nanogpt are comparing it to the libraries listed below
Sorting:
- nanoGPT style version of Llama 3.1☆1,432Updated last year
- ☆4,257Updated last year
- NanoGPT (124M) in 3 minutes☆3,565Updated this week
- Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.☆10,021Updated last year
- The n-gram Language Model☆1,454Updated last year
- PyTorch native post-training library☆5,535Updated this week
- A PyTorch native platform for training generative AI models☆4,561Updated this week
- An autoregressive character-level language model for making more things☆3,347Updated last year
- Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.☆6,121Updated last month
- Minimalistic 4D-parallelism distributed training framework for education purpose☆1,856Updated last month
- Implementing DeepSeek R1's GRPO algorithm from scratch☆1,609Updated 6 months ago
- llama3 implementation one matrix multiplication at a time☆15,172Updated last year
- The simplest, fastest repository for training/finetuning small-sized VLMs.☆4,136Updated this week
- 20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.☆12,840Updated last week
- LLM101n: Let's build a Storyteller☆34,717Updated last year
- Modeling, training, eval, and inference code for OLMo☆6,044Updated this week
- The Autograd Engine☆636Updated last year
- Run PyTorch LLMs locally on servers, desktop and mobile☆3,615Updated last month
- The Multilayer Perceptron Language Model☆571Updated last year
- Efficient Triton Kernels for LLM Training☆5,752Updated this week
- Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.☆4,729Updated 3 months ago
- DataComp for Language Models☆1,375Updated last month
- The official PyTorch implementation of Google's Gemma models☆5,560Updated 4 months ago
- Curated list of datasets and tools for post-training.☆3,792Updated 2 months ago
- ☆4,100Updated last year
- LLM training in simple, raw C/CUDA☆27,852Updated 3 months ago
- Open-source AI cookbook☆2,322Updated last week
- The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.☆8,768Updated last year
- ☆1,301Updated 7 months ago
- Code for BLT research paper☆1,995Updated 4 months ago