We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
PPDiffusers是基于PaddlePaddle的扩散模型工具库,提供多模态的扩散模型,帮助开发者快速使用文生图、文生视频、文生文相关扩散模型
发布基于ERNIE-Tiny模型的端上语义理解压缩方案,帮助开发者快速在边缘端设备部署预训练模型
Seq2SeqTrainer
Memory Tracer
model.generate()
use_faster
use_fast
PaddleNLP首次和HuggingFace生态联合,支持所有Model和Tokenizer类支持直接从Huggingface Hub下载和上传,开发者可以直接从HuggingFace体验预训练模型效果
from_pretrained
from_pretrained_v2
The text was updated successfully, but these errors were encountered:
FrostML
wj-Mcat
joey12300
sijunhe
w5688414
wawltor
gongel
LemonNoel
LiuChiachi
JunnYu
No branches or pull requests
New Features
PPDiffusers 扩散模型工具库发布
PPDiffusers是基于PaddlePaddle的扩散模型工具库,提供多模态的扩散模型,帮助开发者快速使用文生图、文生视频、文生文相关扩散模型
SOTA扩散模型Pipelines集合
提供丰富的Noise Scheduler
支持多种Diffusion模型组件
提供丰富的训练和推理教程
端上语义理解压缩方案
发布基于ERNIE-Tiny模型的端上语义理解压缩方案,帮助开发者快速在边缘端设备部署预训练模型
ERNIE-Tiny V2 轻量级模型 发布
基于 PaddleSlim 全量化压缩方案发布
FastDeplopy 边缘部署加速
产业范例库升级
文档智能信息抽取UIE-X 应用
部署上线,降低信息抽取技术落地门槛
统一文本分类UTC应用
统一情感分析UIE-Seta应用
无监督问答应用
基础框架升级
PretrainedConfig
Trainer API
Seq2SeqTrainer
支持 seq2seq 类型模型训练。[Trainer] support sharding for trainer. #3352Memory Tracer
支持监控内存、显存 Add Memory Tracer #4181模型压缩 API
数据增强api
Prompt API
FastGeneration
model.generate()
接口调整,use_faster
参数调整为use_fast
Alter faster to fast in FG #4213FastTokenizer
HuggingFace 生态联合
PaddleNLP首次和HuggingFace生态联合,支持所有Model和Tokenizer类支持直接从Huggingface Hub下载和上传,开发者可以直接从HuggingFace体验预训练模型效果
from_pretrained
支持直接从Huggingface Hub加载torch权重的模型Others
Bugs
from_pretrained_v2
不能load fp16模型的问题。Fix can't load fp16 model #3902New Contributors
The text was updated successfully, but these errors were encountered: