karpathy / randomfun
Notebooks and various random fun
☆1,079Updated last year
Related projects ⓘ
Alternatives and complementary repositories for randomfun
- arxiv-sanity lite: tag arxiv papers of interest get recommendations of similar papers in a nice UI using SVMs over tfidf feature vectors …☆1,178Updated last year
- Train to 94% on CIFAR-10 in <6.3 seconds on a single A100. Or ~95.79% in ~110 seconds (or less!)☆1,223Updated last year
- 🤖 A PyTorch library of curated Transformer models and their composable components☆866Updated 7 months ago
- What would you do with 1000 H100s...☆903Updated 10 months ago
- Cramming the training of a (BERT-type) language model into limited compute.☆1,296Updated 5 months ago
- 🧠 A study guide to learn about Transformers☆1,541Updated last year
- Reproducing Yann LeCun 1989 paper "Backpropagation Applied to Handwritten Zip Code Recognition", to my knowledge the earliest real-world …☆604Updated 9 months ago
- 🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.☆109Updated 2 years ago
- An autoregressive character-level language model for making more things☆2,607Updated 5 months ago
- An interactive exploration of Transformer programming.☆246Updated last year
- Puzzles for exploring transformers☆325Updated last year
- A platform for managing machine learning experiments☆818Updated 3 months ago
- Tensors, for human consumption☆1,113Updated 3 weeks ago
- ☆391Updated last month
- Language Modeling with the H3 State Space Model☆513Updated last year
- A crude RLHF layer on top of nanoGPT with Gumbel-Softmax trick☆287Updated 11 months ago
- A JAX research toolkit for building, editing, and visualizing neural networks.☆1,679Updated this week
- Fast & Simple repository for pre-training and fine-tuning T5-style models☆970Updated 3 months ago
- ☆142Updated last year
- course.fast.ai 2022 part 2☆477Updated 6 months ago
- Compositional Differentiable Programming Library☆981Updated last week
- ☆3,570Updated 9 months ago
- 100 exercises to learn JAX☆569Updated 2 years ago
- Minimalistic, extremely fast, and hackable researcher's toolbench for GPT models in 307 lines of code. Reaches <3.8 validation loss on wi…☆334Updated 3 months ago
- ☆508Updated 9 months ago
- Language model alignment-focused deep learning curriculum☆1,269Updated 3 months ago
- Deep learning for dummies. All the practical details and useful utilities that go into working with real models.☆715Updated last month
- A walkthrough of transformer architecture code☆318Updated 9 months ago
- Fine-tune mistral-7B on 3090s, a100s, h100s☆702Updated last year