Block or Report
Block or report vaclavbelak
Contact GitHub support about this user’s behavior. Learn more about reporting abuse.
Report abuseStars
Language: Python
Sort by: Most stars
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
A high-throughput and memory-efficient inference and serving engine for LLMs
Interactive Data Visualization in the browser, from Python
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
🦉 ML Experiments and Data Management with Git
Python package built to ease deep learning on graph, on top of existing DL frameworks.
Fast and memory-efficient exact attention
Private chat with local GPT with document, images, video, etc. 100% private, Apache 2.0. Supports oLLaMa, Mixtral, llama.cpp, and more. Demo: https://gpt.h2o.ai/ https://codellama.h2o.ai/
Databricks’ Dolly, a large language model trained on the Databricks Machine Learning Platform
A Python Automated Machine Learning tool that optimizes machine learning pipelines using genetic programming.
Train transformer language models with reinforcement learning.
Bayesian Modeling and Probabilistic Programming in Python
Large Language Model Text Generation Inference
🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support
An implementation of model parallel autoregressive transformers on GPUs, based on the Megatron and DeepSpeed libraries
XLNet: Generalized Autoregressive Pretraining for Language Understanding
Uplift modeling and causal inference with machine learning algorithms
A collection of important graph embedding, classification and representation learning papers with implementations.
Tools for merging pretrained large language models.
Realtime Web Apps and Dashboards for Python and R
Power CLI and Workflow manager for LLMs (core package)
Hummingbird compiles trained ML models into tensor computation for faster inference.
Let ChatGPT teach your own chatbot in hours with a single GPU!