关于GCU、沐曦GPGPU、MLU、0卡V100资源4月7日恢复上架的公告>>> 关于共建具身智能开源数据集的倡议>>> 关于云脑任务中统一路径访问方式的公告>>> 关于将启智集群GPU资源迁移至智算集群的公告>>>
jikuai
/
PaddleNLP
forked from PaddlePaddle/PaddleNLP
Not watched
1
0
Fork 0
Code
Releases 0 Wiki Activity
Issues 0 Pull Requests 0 Datasets Model Cloudbrain
You can not select more than 25 topics Topics must start with a chinese character,a letter or number, can include dashes ('-') and can be up to 35 characters long.
4068 Commits
20 Branches
558 MiB
14 Download
 
 
 
 
 
 
Branch: develop
Branches Tags
${ item.name }
Create branch ${ searchTerm }
from 'develop'
${ noResults }
PaddleNLP/llm
lugimzzz e8a03e47a5
change (#6562) 		9 months ago
..
bloom Unify finetune_generation (#6433) 9 months ago
causallm revert (#6561) 9 months ago
chatglm support chatglmv2 (#6513) 9 months ago
ernie-3.5-se Update README.md 9 months ago
glm create the llm directory and remove the example llm model to the llm directory (#6426) 9 months ago
gpt-3 [llm]gpt3 add lora (#6532) 9 months ago
llama change (#6562) 9 months ago
opt create the llm directory and remove the example llm model to the llm directory (#6426) 9 months ago
README.md Update README.md 9 months ago

README.md

飞桨大语言模型

飞桨大模型套件PaddleFleetX是基于PaddlePaddle的4D分布式并行能力的大模型全流程套件，旨在提供高性能、灵活易用大模型工具，可以根据自己的需求轻易来定制化百亿和千亿大模型训练，同时支持高性能的压缩推理和服务化，最终使用大模型能力提升业务效果。

支持模型列表

LLM模型
LLaMA
LLaMA2
ChatGLM-6B
ChatGLM2-6B
GPT-3
Bloom
OPT
GLM

全流程功能

Model Pretrain SFT LoRA P-Tuning Model Compression FastGeneration
LLaMA ✅ ✅ ✅ ✅ ✅ ✅
LLaMA2 WIP WIP WIP WIP WIP WIP
ChatGLM-6B NA ✅ ✅ ✅ ✅ ✅
ChatGLM2-6B NA ✅ ✅ ✅ ✅ ✅
GPT-3 ✅ ✅ ✅ WIP WIP ✅
Bloom NA ✅ ✅ ✅ ✅ ✅
OPT WIP ✅ ✅ ✅ ✅ ✅
GLM NA ✅ ✅ ✅ ✅ ✅
Delete task

Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.

cancel
confirm

👑 Easy-to-use and powerful NLP library with 🤗 Awesome model zoo, supporting wide-range of NLP tasks from research to industrial applications, including 🗂Text Classification, 🔍 Neural Search, ❓ Question Answering, ℹ️ Information Extraction, 📄 Documen

Python C++ Cuda Shell Markdown other

Please read the following content carefully:

Dear OpenI User

Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.

For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》

Agree and continue
Disagree, exit