merge Dev (#258)

This commit is contained in:
xzw 2024-06-28 22:27:11 +08:00 committed by GitHub
commit 65bcf20aac
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
5 changed files with 195558 additions and 3 deletions

View File

@ -98,7 +98,7 @@
</table>
## 🎇最近更新
- 【2024.6】新增基于[LLaMA-Factory](https://github.com/hiyouga/LLaMA-Factory)[GLM4-9B-chat微调指南](./doc/GLM-4-9B-chat%20Lora%20微调llama-factory.md)、新增[基于swift的微调指南](./swift/)、论文[ESC-Eval: Evaluating Emotion Support Conversations in Large Language Models](https://arxiv.org/abs/2406.14952)引用了EmoLLM且EmoLLM取得了较好的效果。
- 【2024.05.28】EmoLLM使用的多轮对话数据集CPsyCounD和专业评测方法已公开详见2024 ACL findings[《CPsyCoun: A Report-based Multi-turn Dialogue Reconstruction and Evaluation Framework for Chinese Psychological Counseling》](https://arxiv.org/abs/2405.16433)!
- 【2024.05.08】EmoLLM**爹系男友阅览体验版**上线 [1. **百度AppBuilder**](https://appbuilder.baidu.com/s/4cLyw) [2. **OpenXLab**](https://openxlab.org.cn/apps/detail/chg0901/EmoLLM3.0_Gradio_Llama3-8B-Instruct3.0), 欢迎点赞收藏
- 【2024.05.07】[增量预训练指南](xtuner_config/pt/README.md)
@ -142,12 +142,14 @@
## 🏆荣誉栏
- 项目荣获上海人工智能实验室举办的**2024浦源大模型系列挑战赛春季赛*****创新创意奖***
<p align="center">
<a href="https://github.com/SmartFlowAI/EmoLLM/">
<img src="assets/Shusheng.png" alt="浦语挑战赛创新创意奖">
</p>
- 荣获[AI 赋能大学计划“全国高校行”](https://mp.weixin.qq.com/s/yyaulQ1wBzKq5cXaGl2Wag)一等奖
- 🎉感谢以下媒体及公众号朋友对本项目的报道和支持(以下排名不分先后! 若有遗漏、十分抱歉, 一并感激! 欢迎补充!): [NLP工程化](https://mp.weixin.qq.com/s/78lrRl2tlXEKUfElnkVx4A), [机智流](https://mp.weixin.qq.com/s/_wMCmssRMGd0Oz5OVVkjAA), [爱可可爱生活](https://mp.weixin.qq.com/s/4WaCg4OpkCWXEuWHuV4r3w), [阿郎小哥](https://mp.weixin.qq.com/s/_MSMeL1XHP0v5lDi3YaPVw), [大模型日知路](https://mp.weixin.qq.com/s/FYYibsCXtfU6FFM9TuKILA), [AI Code](https://mp.weixin.qq.com/s/yDWGY3S4CwCi6U_irsFmqA) 等!
- 项目宣传视频 [EmoLLM](https://www.bilibili.com/video/BV1N7421N76X/) 已发布,欢迎大家围观 😀

View File

@ -101,7 +101,7 @@ The Model aims to fully understand and promote the mental health of individuals,
</table>
## Recent Updates
- 【2024.6】 Added [LLaMA-Factory](https://github.com/hiyouga/LLaMA-Factory)[GLM4-9B-chat fine-tuning guide](./doc/GLM-4-9B-chat%20Lora%20微调llama-factory.md), added [swift-based fine-tuning guide](./swift/), the paper [ESC-Eval: Evaluating Emotion Support Conversations in Large Language Models](https://arxiv.org/abs/2406.14952) cited EmoLLM and EmoLLM achieved good results.
- 【2024.05.28】The multi-turn dialogue dataset **CPsyCunD** and **professional evaluation method** used by EmoLLM have been released. For details, please see the 2024 ACL findings[《CPsyCoun: A Report-based Multi-turn Dialogue Reconstruction and Evaluation Framework for Chinese Psychological Counseling》](https://arxiv.org/abs/2405.16433)!
- [2024.05.08] EmoLLM**Daddy-like BF V0.1** is public now in [1. **Baidu AppBuilder**](https://appbuilder.baidu.com/s/4cLyw) and [2. **OpenXLab**](https://openxlab.org.cn/apps/detail/chg0901/EmoLLM3.0_Gradio_Llama3-8B-Instruct3.0), welcome to like and add it to your collections!
- [2024.05.07] [Incremental Pre-training Guide](xtuner_config/pt/README.md)
@ -155,6 +155,8 @@ The Model aims to fully understand and promote the mental health of individuals,
<img src="assets/Shusheng.png" alt="Challenge Innovation and Creativity Award">
</p>
- Won the first prize of [AI-enabled university programme "National College Tour"](https://mp.weixin.qq.com/s/yyaulQ1wBzKq5cXaGl2Wag).
- The project has been promoted by the official WeChat account **NLP Engineering**. Here's the [link](https://mp.weixin.qq.com/s/78lrRl2tlXEKUfElnkVx4A).
## Roadmap

195546
datasets/pt/pt.json Normal file

File diff suppressed because it is too large Load Diff

View File

@ -26,6 +26,9 @@ SWIFT具有丰富的文档体系如有使用问题请请查看[这里](https:
GPU设备: A10, 3090, V100, A100均可.
项目Swift微调使用魔搭社区提供的基于英特尔CPU的免费计算资源使用GPU环境8核 32GB 显存24G
SWIFT在Python环境中运行。请确保您的Python版本高于3.8。
这里我们对实验环境进行安装其中包含了虚拟环境的创建、ms-swift以及相关依赖的安装。

View File

@ -26,6 +26,8 @@ You can find it in the [Huggingface space](https://huggingface.co/spaces/tasteli
GPU devices: A10, 3090, V100, A100 are acceptable.
The project Swift fine-tuning uses free computing resources based on Intel CPUs provided by the Magic Community, and uses the GPU environment (8 cores, 32GB video memory, 24G);
SWIFT runs in a Python environment. Please make sure your Python version is higher than 3.8.
Here we install the experimental environment, which includes the creation of the virtual environment, ms-swift and the installation of related dependencies.