nelhage / transformer-rsLinks
A sketch of a Transformer in Rust for a blog post
☆34Updated 3 years ago
Alternatives and similar repositories for transformer-rs
Users that are interested in transformer-rs are comparing it to the libraries listed below
Sorting:
- Inference Llama 2 in one file of zero-dependency, zero-unsafe Rust☆40Updated 2 years ago
- ☆135Updated last year
- ☆58Updated 2 years ago
- Modular Rust transformer/LLM library using Candle☆38Updated last year
- Experimental compiler for deep learning models☆74Updated 4 months ago
- LLaMA from First Principles☆51Updated 2 years ago
- Tensor library with autograd using only Rust's standard library☆71Updated last year
- Experimentation using the xla compiler from rust☆100Updated last year
- Inference Llama 2 in one file of pure Rust 🦀☆235Updated 2 years ago
- A high-performance constrained decoding engine based on context free grammar in Rust☆58Updated 8 months ago
- ☆157Updated 2 years ago
- Sample Python extension using Rust/PyO3/tch to interact with PyTorch☆40Updated last year
- l2 is a fast, Pytorch-style Tensor+Autograd library written in Rust☆196Updated 3 years ago
- An interactive exploration of Transformer programming.☆271Updated 2 years ago
- LayerNorm(SmallInit(Embedding)) in a Transformer to improve convergence☆61Updated 3 years ago
- Dataflow is a data processing library, primarily for machine learning.☆24Updated 2 years ago
- Neural syntax annotator, supporting sequence labeling, lemmatization, and dependency parsing.☆80Updated 2 years ago
- ☆18Updated last year
- A programming language for formal/informal computation.☆43Updated last month
- ☆28Updated 2 years ago
- RAI: Rust ML framework with composable transformations like JAX.☆95Updated last year
- Rust-tokenizer offers high-performance tokenizers for modern language models, including WordPiece, Byte-Pair Encoding (BPE) and Unigram (…☆333Updated last week
- ☆39Updated 3 years ago
- Locality Sensitive Hashing in Rust with Python bindings☆121Updated 2 years ago
- Experiments for efforts to train a new and improved t5☆76Updated last year
- Serialize JAX, Flax, Haiku, or Objax model params with 🤗`safetensors`☆47Updated last year
- ☆23Updated 2 years ago
- Your one stop CLI for ONNX model analysis.☆47Updated 3 years ago
- ☆32Updated 2 years ago
- LLaMa 7b with CUDA acceleration implemented in rust. Minimal GPU memory needed!☆111Updated 2 years ago