United Kingdom

Birch-san

Elite
@Birch-san

A Very Full Stack dev. I like low-level (C++, WASM, LLVM, Graal, DTrace, BPF) and devops (Docker, networking, monitoring, logging). I like performance + scale.

juicysfplugin. Audio plugin (e.g. VST, AU) to play soundfonts on macOS, Windows, Linux

320

box2d-wasm. Box2D physics engine compiled to WebAssembly. Supports TypeScript and ES modules.

303

mpt-play. Command-line script for inferencing from models such as MPT-7B-Chat

99

stable-diffusion. Jupyter Notebook

92

falcon-play. Command-line script for inferencing from models such as falcon-7b-instruct

75

box2d3-wasm. Box2D v3 for the Web, using WASM + SIMD + Web Workers

61

diffusers-play. Repository with which to explore k-diffusion and diffusers, and within which changes to said packages may be tested.

55

llama-play. Command-line script for inferencing from models such as LLaMA, in a chat scenario, with LoRA adaptations

32

liquidfun-play-2. TypeScript

32

imagebind-guided-diffusion. Guide diffusion on ImageBind embedding similarity

29

wizardcoder-play. Command-line script for inferencing from models such as WizardCoder

25

sdxl-diffusion-decoder. Let's try and finetune the OpenAI consistency decoder to work for SDXL

25

sdxl-play. Python

25

k-diffusion. Karras et al. (2022) diffusion models for PyTorch

21

liquidfun-play. TypeScript

21

touhou-walk. Android overlay to make sprites from 東方Project walk around your screen

20

regional-attn. Python

19

mecab. Use mecab via WebAssembly to analyse Japanese on the web

17

booru-embed. [WIP] Transformer to embed Danbooru labelsets

13

arm-editor-launcher. M1 macOS Launcher for Live2D Cubism Editor

13

embedding-compare. Compare embedding similarity

12

diffusers. 🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch

9

z-loss-pytorch. Python

6

gmusicapi-node. Node bindings for Simon Weber's `gmusicapi` (Unofficial Google Music API)

6

LLaMA_MPS. Run LLaMA inference on Apple Silicon GPUs.

5

t5-booru. Python

5

huggingface-vscode-endpoint-server. starcoder server for huggingface-vscode custom endpoint

4

natten-fwd-ad. Try to demonstrate how to use forward-mode autodiff with NATTEN

4

cfg-play. try using classifier-free guidance on LLMs

3

clip-embed-sim. Python

3

audiosynth2. Streaming wave generator based on https://github.com/keithwhor/audiosynth

2

birchlabs-site. Attempt to remake Birchlabs as a static site in Jekyll

2

torch-cublas-hgemm. PyTorch half precision gemm lib w/ fused optional bias + optional relu/gelu

2

dino-guided-diffusion. Python

2

GFPGAN. GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration.

2

grid-printer. Prints a list of PIL images as a grid with text captions and a title

2

pre-tokenize. Python

1

aspect-ratio-bucketer. Jupyter Notebook

1

orbit. try to use box2d3-wasm to update my Orbit experiment

1

muse-maskgit-pytorch. Implementation of Muse: Text-to-Image Generation via Masked Generative Transformers, in Pytorch

1

scheduler-play. Jupyter Notebook

1

box2cpp. C++ bindings for box2d 3.x physics engine (aka box2c)

1

dino-embed. Python

1

guided-diffusion. Python

1

img2dataset. Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.

1

transformers. 🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

1

nanoT5. Fast & Simple repository for pre-training and fine-tuning T5-style models

1

coremltools. Core ML tools contain supporting tools for Core ML model conversion, editing, and validation.

1

mecab-native. The MeCab Japanese morphological analyzer for the Web!

1

wolf-game-frontend. wolf-game-frontend

1

deprecated-mecab-wasm. [deprecated; prefer Birch-san/mecab] Run Mecab in WebAssembly

1
51
Apply