karpathy / micrograd
A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API
☆10,520Updated 3 months ago
Related projects ⓘ
Alternatives and complementary repositories for micrograd
- An autoregressive character-level language model for making more things☆2,607Updated 5 months ago
- You like pytorch? You like micrograd? You love tinygrad! ❤️☆26,908Updated this week
- Pure Python from-scratch zero-dependency implementation of Bitcoin for educational purposes☆1,613Updated 3 years ago
- Neural Networks: Zero to Hero☆11,892Updated 3 months ago
- A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training☆20,199Updated 3 months ago
- ☆3,570Updated 9 months ago
- LLM training in simple, raw C/CUDA☆24,460Updated last month
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆37,411Updated 3 months ago
- Solve puzzles. Improve your pytorch.☆3,282Updated 4 months ago
- Inference Llama 2 in one file of pure C☆17,476Updated 3 months ago
- Some ipython notebooks implementing AI algorithms☆1,271Updated last month
- Train transformer language models with reinforcement learning.☆10,086Updated this week
- Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.☆9,195Updated 4 months ago
- Machine Learning Engineering Open Book☆11,655Updated last week
- The full minitorch student suite.☆1,917Updated 3 months ago
- Video+code lecture on building nanoGPT from scratch☆3,611Updated 3 months ago
- Explanation to key concepts in ML☆7,321Updated this week
- tiktoken is a fast BPE tokeniser for use with OpenAI's models.☆12,427Updated last month
- LLM101n: Let's build a Storyteller☆30,214Updated 3 months ago
- An unnecessarily tiny implementation of GPT-2 in NumPy.☆3,252Updated last year
- Tensor library for machine learning☆11,233Updated this week
- Fast and memory-efficient exact attention☆14,279Updated this week
- The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.☆7,919Updated 6 months ago
- 20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.☆10,734Updated last week
- An implementation of model parallel autoregressive transformers on GPUs, based on the Megatron and DeepSpeed libraries☆6,947Updated this week
- Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM☆7,705Updated 10 months ago
- Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"☆10,776Updated 3 months ago
- ☆2,688Updated 6 months ago
- QLoRA: Efficient Finetuning of Quantized LLMs☆10,059Updated 5 months ago
- llama3 implementation one matrix multiplication at a time☆13,741Updated 5 months ago