Jeff Soules's starred repositories

tiktoken

tiktoken is a fast BPE tokeniser for use with OpenAI's models.

Language:PythonLicense:MITStargazers:11265Issues:167Issues:224

sentencepiece

Unsupervised text tokenizer for Neural Network-based text generation.

Language:C++License:Apache-2.0Stargazers:9878Issues:124Issues:733

bitsandbytes

Accessible large language models via k-bit quantization for PyTorch.

Language:PythonLicense:MITStargazers:5756Issues:48Issues:968

parallel-hashmap

A family of header-only, very fast and memory-friendly hashmap and btree containers.

Language:C++License:Apache-2.0Stargazers:2422Issues:63Issues:178

torchsde

Differentiable SDE solvers with GPU support and efficient sensitivity analysis.

Language:PythonLicense:Apache-2.0Stargazers:1529Issues:34Issues:77

aaronson-oracle

Press the 'f' and 'd' keys randomly. It's easy. Just use your "free will."

prob-stats

Probability and Statistics: a simulation-based introduction. An open-access book.

Language:TeXLicense:BSD-3-ClauseStargazers:303Issues:23Issues:9

deep-explanation-penalization

Code for using CDEP from the paper "Interpretations are useful: penalizing explanations to align neural networks with prior knowledge" https://arxiv.org/abs/1909.13584

Language:Jupyter NotebookLicense:MITStargazers:124Issues:9Issues:13
Language:PythonLicense:Apache-2.0Stargazers:20Issues:2Issues:20

dendro

Analyze neuroscience data in the cloud

Language:TypeScriptLicense:Apache-2.0Stargazers:18Issues:4Issues:46

stan-getting-started

A quarto notebook introducing Stan in Python (and maybe R).

Language:TeXLicense:BSD-3-ClauseStargazers:11Issues:5Issues:2

nomad

Non-linear Matrix Decomposition library

Language:PythonLicense:Apache-2.0Stargazers:9Issues:3Issues:9

ccn-template

Template repository for CCN software projects

Language:PythonLicense:BSD-3-ClauseStargazers:7Issues:6Issues:43

sf-fwam-2023

workshop introduction to WebGL

Language:JavaScriptLicense:GPL-3.0Stargazers:2Issues:1Issues:1
Language:PythonLicense:NOASSERTIONStargazers:2Issues:2Issues:3