BlackHC

BatchBALD

Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning.

batchbald_redux

Reusable BatchBALD implementation

dart_repl

Proof of concept REPL shell for Dart

llm-strategy

Directly Connecting Python to LLMs via Strongly-Typed Functions, Dataclasses, Interfaces & Generic Types

llmtracer

Trace LLM calls (and others) and visualize them in WandB, as interactive SVG or using a streaming local webapp

mdp

Make it easy to specify simple MDPs that are compatible with the OpenAI Gym.

mnist_by_zip

Compression algorithms (like the well-known zip file compression) can be used for machine learning purposes, specifically for classifying hand-written digits (MNIST)

neural_net_checklist

tfpyth

Putting TensorFlow back in PyTorch, back in TensorFlow (differentiable TensorFlow PyTorch adapters).

toma

Helps you write algorithms in PyTorch that adapt to the available (CUDA) memory

BlackHC/toma

Helps you write algorithms in PyTorch that adapt to the available (CUDA) memory

BlackHC/llm-strategy

Directly Connecting Python to LLMs via Strongly-Typed Functions, Dataclasses, Interfaces & Generic Types

BlackHC/BatchBALD

Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning.

BlackHC/neural_net_checklist

BlackHC/batchbald_redux

Reusable BatchBALD implementation

BlackHC/llmtracer

Trace LLM calls (and others) and visualize them in WandB, as interactive SVG or using a streaming local webapp

BlackHC/chatplayground

Chat Playground for LLMs

BlackHC/blackboard-pagi

BlackHC/2302.08981

BlackHC/pytorch_datadiet

BlackHC/hello-slurm

BlackHC/active-bayesian-coresets

BlackHC/iclr_2024_blog_post

BlackHC/ordl

Open Research and Derivatives License (ORDL)

BlackHC/active_learning_redux

BlackHC/blackhc

BlackHC/BMS-hlb-CIFAR10

Train to 94% on CIFAR-10 in <6.3 seconds on a single A100, the current world speed record. Or ~95.79% in ~110 seconds (or less!)

BlackHC/dss_sprint

BlackHC/dvc

🦉Data Version Control | Git for Data & Models | ML Experiments Management

BlackHC/hf-datasets

🤗 The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools

BlackHC/notebook_setup

Some batteries for Jupyter notebooks

BlackHC/ObsidianGitHubTemplate

BlackHC/peft

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

BlackHC/prettyprinter

Syntax-highlighting, declarative and composable pretty printer for Python 3.5+

BlackHC/pynecone

🕸 Web apps in pure Python 🐍

BlackHC/pytorch-lightning

The lightweight PyTorch wrapper for ML researchers. Scale your models. Write less boilerplate

BlackHC/reversal_curse

BlackHC/skorch

A scikit-learn compatible neural network library that wraps PyTorch

BlackHC/streamlit

Streamlit — A faster way to build and share data apps.

BlackHC/vscode-notebook-renderers