SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models

BlinkDL/RWKV-LM 18 Nov 2022

We propose SmoothQuant, a training-free, accuracy-preserving, and general-purpose post-training quantization (PTQ) solution to enable 8-bit weight, 8-bit activation (W8A8) quantization for LLMs that can be implemented efficiently.

Quantization

1,136
0.22 stars / hour

RAVE: A variational autoencoder for fast and high-quality neural audio synthesis

caillonantoine/RAVE 9 Nov 2021

By leveraging a multi-band decomposition of the raw waveform, we show that our model is the first able to generate 48kHz audio signals, while simultaneously running 20 times faster than real-time on a standard laptop CPU.

Representation Learning

639
0.22 stars / hour

ExaRanker: Explanation-Augmented Neural Ranker

unicamp-dl/exaranker 25 Jan 2023

Recent work has shown that inducing a large language model (LLM) to generate explanations prior to outputting an answer is an effective strategy to improve performance on a wide range of reasoning tasks.

Language Modelling Retrieval

12
0.20 stars / hour

Synthcity: facilitating innovative use cases of synthetic data in different data modalities

vanderschaarlab/synthcity 18 Jan 2023

Synthcity is an open-source software package for innovative use cases of synthetic data in ML fairness, privacy and augmentation across diverse tabular data modalities, including static data, regular and irregular time series, data with censoring, multi-source data, composite data, and more.

Fairness Irregular Time Series +1

51
0.20 stars / hour
179
0.20 stars / hour

Multiview Compressive Coding for 3D Reconstruction

facebookresearch/mcc 19 Jan 2023

We introduce a simple framework that operates on 3D points of single objects or whole scenes coupled with category-agnostic large-scale training from diverse RGB-D videos.

3D Reconstruction Self-Supervised Learning +1

200
0.20 stars / hour

Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation

showlab/Tune-A-Video 22 Dec 2022

To reproduce the success of text-to-image (T2I) generation, recent works in text-to-video (T2V) generation employ large-scale text-video dataset for fine-tuning.

Style Transfer Text-to-Video Generation +1

209
0.19 stars / hour

Instant Neural Graphics Primitives with a Multiresolution Hash Encoding

nerfstudio-project/nerfstudio 16 Jan 2022

Neural graphics primitives, parameterized by fully connected neural networks, can be costly to train and evaluate.

3D Reconstruction 3D Shape Reconstruction +2

3,295
0.19 stars / hour

SensorX2car: Sensors-to-car calibration for autonomous driving in road scenarios

opencalib/sensorx2car 18 Jan 2023

To this end, we present SensorX2car, a calibration toolbox for the online calibration of sensor-to-car coordinate systems in road scenes.

Autonomous Driving

48
0.18 stars / hour

CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis

salesforce/CodeGen 25 Mar 2022

To democratize this, we train and release a family of large language models up to 16. 1B parameters, called CODEGEN, on natural language and programming language data, and open source the training library JAXFORMER.

Code Generation Language Modelling +1

2,058
0.18 stars / hour