karpathy / minbpeLinks
Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.
☆9,859Updated last year
Alternatives and similar repositories for minbpe
Users that are interested in minbpe are comparing it to the libraries listed below
Sorting:
- Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.☆6,044Updated 4 months ago
- llama3 implementation one matrix multiplication at a time☆15,108Updated last year
- PyTorch native post-training library☆5,418Updated this week
- Video+code lecture on building nanoGPT from scratch☆4,314Updated last year
- The official PyTorch implementation of Google's Gemma models☆5,526Updated 2 months ago
- 20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.☆12,640Updated this week
- ☆4,086Updated last year
- Modeling, training, eval, and inference code for OLMo☆5,911Updated last week
- Large World Model -- Modeling Text and Video with Millions Context☆7,327Updated 10 months ago
- A PyTorch native platform for training generative AI models☆4,240Updated this week
- An autoregressive character-level language model for making more things☆3,250Updated last year
- lightweight, standalone C++ inference engine for Google's Gemma models.☆6,541Updated this week
- tiktoken is a fast BPE tokeniser for use with OpenAI's models.☆15,615Updated last week
- [ICLR 2024] Efficient Streaming Language Models with Attention Sinks☆7,025Updated last year
- LLM training in simple, raw C/CUDA☆27,392Updated last month
- nanoGPT style version of Llama 3.1☆1,417Updated last year
- NanoGPT (124M) in 3 minutes☆3,037Updated last month
- The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.☆8,700Updated last year
- PyTorch code and models for V-JEPA self-supervised learning from video.☆3,174Updated 5 months ago
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆43,694Updated 8 months ago
- Inference Llama 2 in one file of pure C☆18,652Updated last year
- Go ahead and axolotl questions☆10,245Updated this week
- The n-gram Language Model☆1,438Updated last year
- Implementation for MatMul-free LM.☆3,031Updated last month
- ☆4,142Updated last year
- Accessible large language models via k-bit quantization for PyTorch.☆7,490Updated last week
- A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API☆12,574Updated last year
- Gemma open-weight LLM library, from Google DeepMind☆3,635Updated this week
- Solve puzzles. Improve your pytorch.☆3,684Updated last year
- Train transformer language models with reinforcement learning.☆15,174Updated this week