Stars
📰 Must-read papers and blogs on Speculative Decoding ⚡️
NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.
Codes for our paper "Speculative Decoding: Exploiting Speculative Execution for Accelerating Seq2seq Generation" (EMNLP 2023 Findings)
OneDiff: An out-of-the-box acceleration library for diffusion models.
A list of papers, docs, codes about model quantization. This repo is aimed to provide the info for model quantization research, we are continuously improving the project. Welcome to PR the works (p…
Making large AI models cheaper, faster and more accessible
Databricks’ Dolly, a large language model trained on the Databricks Machine Learning Platform
Code and documentation to train Stanford's Alpaca models, and generate the data.
Flops counter for convolutional networks in pytorch framework
High-Resolution Image Synthesis with Latent Diffusion Models
Transfer learning / domain adaptation / domain generalization / multi-task learning etc. Papers, codes, datasets, applications, tutorials.-迁移学习
Repository for the paper "Optimal Subarchitecture Extraction for BERT"
Predict customer lifetime value using AutoML Tables, or ML Engine with a TensorFlow neural network and the Lifetimes Python library.
Efficient GPU kernels for block-sparse matrix multiplication and convolution
An open source AutoML toolkit for automate machine learning lifecycle, including feature engineering, neural architecture search, model compression and hyper-parameter tuning.
Jittor is a high-performance deep learning framework based on JIT compiling and meta-operators.
Multi Model Server is a tool for serving neural net models for inference
Matrix Shadow:Lightweight CPU/GPU Matrix and Tensor Template Library in C++/CUDA for (Deep) Machine Learning
Deep Learning papers reading roadmap for anyone who are eager to learn this amazing tech!
tensorflow实战练习,包括强化学习、推荐系统、nlp等
Visualizer for neural network, deep learning and machine learning models
FAIR's research platform for object detection research, implementing popular algorithms like Mask R-CNN and RetinaNet.