karpathy / minbpe
Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.
☆9,168Updated 4 months ago
Related projects ⓘ
Alternatives and complementary repositories for minbpe
- [ICLR 2024] Efficient Streaming Language Models with Attention Sinks☆6,650Updated 3 months ago
- 20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.☆10,590Updated this week
- The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.☆7,835Updated 6 months ago
- Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.☆5,647Updated 3 weeks ago
- Go ahead and axolotl questions☆7,858Updated this week
- llama3 implementation one matrix multiplication at a time☆13,673Updated 5 months ago
- The official PyTorch implementation of Google's Gemma models☆5,283Updated 3 months ago
- Robust recipes to align language models with human and AI preferences☆4,663Updated last month
- PyTorch native finetuning library☆4,267Updated this week
- Scripts for fine-tuning Meta Llama with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom dataset…☆14,903Updated this week
- Inference Llama 2 in one file of pure C☆17,444Updated 3 months ago
- Video+code lecture on building nanoGPT from scratch☆3,573Updated 2 months ago
- Tensor library for machine learning☆11,160Updated this week
- A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API☆10,434Updated 3 months ago
- lightweight, standalone C++ inference engine for Google's Gemma models.☆5,984Updated this week
- ☆4,030Updated 5 months ago
- Tools for merging pretrained large language models.☆4,788Updated this week
- Large World Model -- Modeling Text and Video with Millions Context☆7,136Updated 3 weeks ago
- A framework for few-shot evaluation of language models.☆6,904Updated this week
- Train transformer language models with reinforcement learning.☆9,967Updated this week
- ☆2,732Updated last month
- Examples in the MLX framework☆6,158Updated this week
- Large Language Model Text Generation Inference☆9,011Updated this week
- LLM training in simple, raw C/CUDA☆24,335Updated last month
- Run PyTorch LLMs locally on servers, desktop and mobile☆3,350Updated this week
- A high-throughput and memory-efficient inference and serving engine for LLMs☆29,785Updated this week
- tiktoken is a fast BPE tokeniser for use with OpenAI's models.☆12,312Updated last month
- tiny vision language model☆5,421Updated this week
- Python bindings for llama.cpp☆8,072Updated this week
- Structured Text Generation☆9,247Updated this week