ModelPS: An Interactive and Collaborative Platform for Editing
Pre-trained Models at Scale
- URL: http://arxiv.org/abs/2105.08275v1
- Date: Tue, 18 May 2021 04:51:56 GMT
- Title: ModelPS: An Interactive and Collaborative Platform for Editing
Pre-trained Models at Scale
- Authors: Yuanming Li, Huaizheng Zhang, Shanshan Jiang, Fan Yang, Yonggang Wen
and Yong Luo
- Abstract summary: We propose and develop a low-code solution, ModelPS, to enable collaborative DNN model editing and intelligent model serving.
The ModelPS solution embodies two transformative features: 1) a user-friendly web interface for a developer team to share and edit DNN models pictorially, in a low-code fashion, and 2) a model genie engine in the backend to aid developers in customizing model editing configurations for given deployment requirements or constraints.
- Score: 30.333660470820604
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: AI engineering has emerged as a crucial discipline to democratize deep neural
network (DNN) models among software developers with a diverse background. In
particular, altering these DNN models in the deployment stage posits a
tremendous challenge. In this research, we propose and develop a low-code
solution, ModelPS (an acronym for "Model Photoshop"), to enable and empower
collaborative DNN model editing and intelligent model serving. The ModelPS
solution embodies two transformative features: 1) a user-friendly web interface
for a developer team to share and edit DNN models pictorially, in a low-code
fashion, and 2) a model genie engine in the backend to aid developers in
customizing model editing configurations for given deployment requirements or
constraints. Our case studies with a wide range of deep learning (DL) models
show that the system can tremendously reduce both development and communication
overheads with improved productivity. The code has been released as an
open-source package at GitHub.
Related papers
- Make Some Noise: Unlocking Language Model Parallel Inference Capability through Noisy Training [54.581599828392854]
We propose the Make Some Noise (MSN) training framework as a replacement for the supervised fine-tuning stage of the large language model.
The training method simply introduces some noise at the input for the model to learn the denoising task.
Experiments in both the general and code domains have shown that MSN can improve inference speed by 2.3-2.7x times without compromising model performance.
arXiv Detail & Related papers (2024-06-25T09:25:39Z) - Model Callers for Transforming Predictive and Generative AI Applications [2.7195102129095003]
We introduce a novel software abstraction termed "model caller"
Model callers act as an intermediary for AI and ML model calling.
We have released a prototype Python library for model callers, accessible for installation via pip or for download from GitHub.
arXiv Detail & Related papers (2024-04-17T12:21:06Z) - Towards Automatic Support of Software Model Evolution with Large
Language~Models [6.872484164111954]
We propose an approach that utilizes large language models for model completion and discovering editing patterns in model histories of software systems.
We have found that large language models are indeed a promising technology for supporting software model evolution.
arXiv Detail & Related papers (2023-12-19T18:38:01Z) - FlexModel: A Framework for Interpretability of Distributed Large
Language Models [0.0]
We present FlexModel, a software package providing a streamlined interface for engaging with models distributed across multi- GPU and multi-node configurations.
The library is compatible with existing model distribution libraries and encapsulates PyTorch models.
It exposes user-registerable HookFunctions to facilitate straightforward interaction with distributed model internals.
arXiv Detail & Related papers (2023-12-05T21:19:33Z) - Model Share AI: An Integrated Toolkit for Collaborative Machine Learning
Model Development, Provenance Tracking, and Deployment in Python [0.0]
We introduce Model Share AI (AIMS), an easy-to-use MLOps platform designed to streamline collaborative model development, model provenance tracking, and model deployment.
AIMS features collaborative project spaces and a standardized model evaluation process that ranks model submissions based on their performance on unseen evaluation data.
AIMS allows users to deploy ML models built in Scikit-Learn, Keras, PyTorch, and ONNX into live REST APIs and automatically generated web apps.
arXiv Detail & Related papers (2023-09-27T15:24:39Z) - UnIVAL: Unified Model for Image, Video, Audio and Language Tasks [105.77733287326308]
UnIVAL model goes beyond two modalities and unifies text, images, video, and audio into a single model.
Our model is efficiently pretrained on many tasks, based on task balancing and multimodal curriculum learning.
Thanks to the unified model, we propose a novel study on multimodal model merging via weight generalization.
arXiv Detail & Related papers (2023-07-30T09:48:36Z) - Speculative Decoding with Big Little Decoder [108.95187338417541]
Big Little Decoder (BiLD) is a framework that can improve inference efficiency and latency for a wide range of text generation applications.
On an NVIDIA T4 GPU, our framework achieves a speedup of up to 2.12x speedup with minimal generation quality degradation.
Our framework is fully plug-and-play and can be applied without any modifications in the training process or model architecture.
arXiv Detail & Related papers (2023-02-15T18:55:29Z) - JMSNAS: Joint Model Split and Neural Architecture Search for Learning
over Mobile Edge Networks [23.230079759174902]
Joint model split and neural architecture search (JMSNAS) framework is proposed to automatically generate and deploy a DNN model over a mobile edge network.
Considering both the computing and communication resource constraints, a computational graph search problem is formulated.
Experiment results confirm the superiority of the proposed framework over the state-of-the-art split machine learning design methods.
arXiv Detail & Related papers (2021-11-16T03:10:23Z) - Data-Driven and SE-assisted AI Model Signal-Awareness Enhancement and
Introspection [61.571331422347875]
We propose a data-driven approach to enhance models' signal-awareness.
We combine the SE concept of code complexity with the AI technique of curriculum learning.
We achieve up to 4.8x improvement in model signal awareness.
arXiv Detail & Related papers (2021-11-10T17:58:18Z) - Fast Model Editing at Scale [77.69220974621425]
We propose Model Editor Networks with Gradient Decomposition (MEND)
MEND is a collection of small auxiliary editing networks that use a single desired input-output pair to make fast, local edits to a pre-trained model.
MEND can be trained on a single GPU in less than a day even for 10 billion+ parameter models.
arXiv Detail & Related papers (2021-10-21T17:41:56Z) - Making DensePose fast and light [78.49552144907513]
Existing neural network models capable of solving this task are heavily parameterized.
To enable Dense Pose inference on the end device with current models, one needs to support an expensive server-side infrastructure and have a stable internet connection.
In this work, we target the problem of redesigning the DensePose R-CNN model's architecture so that the final network retains most of its accuracy but becomes more light-weight and fast.
arXiv Detail & Related papers (2020-06-26T19:42:20Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.