karpathy / minbpeLinks
Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.
☆9,922Updated last year
Alternatives and similar repositories for minbpe
Users that are interested in minbpe are comparing it to the libraries listed below
Sorting:
- Video+code lecture on building nanoGPT from scratch☆4,366Updated last year
- The official PyTorch implementation of Google's Gemma models☆5,543Updated 3 months ago
- PyTorch native post-training library☆5,484Updated last week
- Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.☆6,093Updated 3 weeks ago
- llama3 implementation one matrix multiplication at a time☆15,148Updated last year
- LLM training in simple, raw C/CUDA☆27,588Updated 2 months ago
- lightweight, standalone C++ inference engine for Google's Gemma models.☆6,565Updated this week
- ☆4,092Updated last year
- The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.☆8,741Updated last year
- Modeling, training, eval, and inference code for OLMo☆5,985Updated last week
- 20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.☆12,748Updated this week
- NanoGPT (124M) in 3 minutes☆3,117Updated 2 months ago
- A PyTorch native platform for training generative AI models☆4,395Updated this week
- nanoGPT style version of Llama 3.1☆1,423Updated last year
- Large World Model -- Modeling Text and Video with Millions Context☆7,339Updated 10 months ago
- An autoregressive character-level language model for making more things☆3,304Updated last year
- Inference Llama 2 in one file of pure C☆18,735Updated last year
- A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API☆12,736Updated last year
- ☆4,193Updated last year
- The n-gram Language Model☆1,442Updated last year
- tiktoken is a fast BPE tokeniser for use with OpenAI's models.☆15,911Updated 2 weeks ago
- Solve puzzles. Improve your pytorch.☆3,714Updated last year
- PyTorch code and models for V-JEPA self-supervised learning from video.☆3,200Updated 6 months ago
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆44,331Updated 9 months ago
- Official inference library for Mistral models☆10,459Updated 5 months ago
- Go ahead and axolotl questions☆10,405Updated this week
- Tensor library for machine learning☆13,170Updated this week
- Training LLMs with QLoRA + FSDP☆1,528Updated 10 months ago
- Run Mixtral-8x7B models in Colab or consumer desktops☆2,319Updated last year
- Official implementation for the paper: "Code Generation with AlphaCodium: From Prompt Engineering to Flow Engineering""☆3,892Updated 9 months ago