srush / Transformer-PuzzlesLinks
Puzzles for exploring transformers
☆349Updated 2 years ago
Alternatives and similar repositories for Transformer-Puzzles
Users that are interested in Transformer-Puzzles are comparing it to the libraries listed below
Sorting:
- ☆435Updated 8 months ago
- What would you do with 1000 H100s...☆1,053Updated last year
- A puzzle to learn about prompting☆128Updated 2 years ago
- An interactive exploration of Transformer programming.☆264Updated last year
- ☆270Updated 11 months ago
- Legible, Scalable, Reproducible Foundation Models with Named Tensors and Jax☆595Updated this week
- Annotated version of the Mamba paper☆485Updated last year
- MLCommons Algorithmic Efficiency is a benchmark and competition measuring neural network training speedups due to algorithmic improvement…☆385Updated this week
- seqax = sequence modeling + JAX☆159Updated last week
- For optimization algorithm research and development.☆521Updated this week
- Home for "How To Scale Your Model", a short blog-style textbook about scaling LLMs on TPUs☆397Updated last week
- Solve puzzles. Learn CUDA.☆64Updated last year
- Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.☆216Updated last year
- Building blocks for foundation models.☆508Updated last year
- A subset of PyTorch's neural network modules, written in Python using OpenAI's Triton.☆554Updated this week
- ☆303Updated last year
- ☆502Updated 11 months ago
- ☆166Updated last year
- Implementation of Diffusion Transformer (DiT) in JAX☆278Updated last year
- Extract full next-token probabilities via language model APIs☆247Updated last year
- Puzzles for learning Triton☆1,695Updated 7 months ago
- Understand and test language model architectures on synthetic tasks.☆217Updated last week
- Minimalistic, extremely fast, and hackable researcher's toolbench for GPT models in 307 lines of code. Reaches <3.8 validation loss on wi…☆345Updated 10 months ago
- Everything you want to know about Google Cloud TPU☆529Updated 11 months ago
- Fast bare-bones BPE for modern tokenizer training☆159Updated 2 months ago
- Pax is a Jax-based machine learning framework for training large scale models. Pax allows for advanced and fully configurable experimenta…☆508Updated last week
- An implementation of the transformer architecture onto an Nvidia CUDA kernel☆185Updated last year
- jax-triton contains integrations between JAX and OpenAI Triton☆400Updated 2 weeks ago
- 🧱 Modula software package☆200Updated 2 months ago
- Simple Transformer in Jax☆137Updated last year