Skip to content
New issue

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

[PaddleNLP 3.0] Update README.md #8666

Merged
merged 19 commits into from
Jun 27, 2024

Conversation

DrownFish19
Copy link
Collaborator

@DrownFish19 DrownFish19 commented Jun 26, 2024

PR types

Others

PR changes

Docs

Description

Update README.md
LLM
LLM_EN

Copy link

paddle-bot bot commented Jun 26, 2024

Thanks for your contribution!

Copy link

codecov bot commented Jun 26, 2024

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 55.79%. Comparing base (c6c2cd8) to head (91827c3).
Report is 232 commits behind head on develop.

Additional details and impacted files
@@           Coverage Diff            @@
##           develop    #8666   +/-   ##
========================================
  Coverage    55.79%   55.79%           
========================================
  Files          620      620           
  Lines        96659    96659           
========================================
  Hits         53928    53928           
  Misses       42731    42731           

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

README.md Outdated

## News 📢

* **2024.06.27 [PaddleNLP v3.0 Beta](https://github.com/PaddlePaddle/PaddleNLP/releases/tag/v3.0.0)**:拥抱大模型,体验全升级。统一大模型工具链,实现国产计算芯片全流程接入;全面支持飞桨4D并行配置、高效精调策略、高效对齐算法、高性能推理等大模型产业级应用流程;自研极致收敛的RsLoRA+算法、全断点存储机制Unified Checkpoint和通用化支持FastFNN、FusedQKV助力大模型训推;主流模型持续支持更新,提供高效解决方案。
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

全断点存储?

Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

FastFNN-->FastFFN?

README.md Outdated
<a href=#社区交流> 社区交流 </a>
</h4>

**PaddleNLP**是一款**简单易用**且**功能强大**的自然语言处理和大语言模型(LLM)开发库。聚合业界**优质预训练模型**并提供**开箱即用**的开发体验,覆盖NLP多场景的模型库搭配**产业实践范例**可满足开发者**灵活定制**的需求
**PaddleNLP**是一款基于飞桨深度学习框架的大语言模型(LLM)开发套件,支持在多种硬件上进行高效的大模型训练、无损压缩以及快速推理。PaddleNLP具备**简单易用**和**性能极致**的特点,致力于助力开发者实现高效的大模型产业级应用
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

快速推理-->高性能推理

Copy link
Member

@ZeyuChen ZeyuChen left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

不建议上传图片到Github,会增大Repo Size。
加你走Github Comment粘贴图片后用图床链接

Copy link
Member

@ZeyuChen ZeyuChen left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

image 飞桨的这个图还得再优化下,比如飞桨框架核心这些描述。

README_en.md Outdated
## Quick Start
```python
>>> from paddlenlp.transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("linly-ai/chinese-llama-2-7b")
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

有更好的模型推荐吗?或者选一个更小的模型如Qwen-1.5B作为快速开始

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

改为使用Qwen-0.5B作为快速开始

@sijunhe sijunhe merged commit 04c2f2b into PaddlePaddle:develop Jun 27, 2024
9 of 11 checks passed
@DrownFish19 DrownFish19 deleted the dev_update_readme_3.0 branch June 28, 2024 03:59
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

4 participants