Code Monkey home page Code Monkey logo

characterglm-6b's People

Contributors

aaa123git avatar amorykiet avatar jfzhouyoo avatar zrzrzrzrzrzrzr avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

characterglm-6b's Issues

模型

请问还开放吗?

运行streamlit报错

System Info / 系統信息

Ubuntu20.04, Python 3.10, Pytorch 2.1.1, CUDA 11.8, cuDNN 8, NVCC, VNC

Who can help? / 谁可以帮助到您?

No response

Information / 问题信息

  • The official example scripts / 官方的示例脚本
  • My own modified scripts / 我自己修改的脚本和任务

Reproduction / 复现过程

FileNotFoundError: [Errno 2] No such file or directory: 'character.json'
Traceback:
File "/root/miniconda3/envs/myconda/lib/python3.10/site-packages/streamlit/runtime/scriptrunner/script_runner.py", line 535, in _run_script
exec(code, module.dict)
File "/root/CharacterGLM-6B/basic_demo/web_demo_streamlit.py", line 22, in
with open('character.json', 'r', encoding='utf-8') as file:

Expected behavior / 期待表现

成功运行

web_demo中的预设角色功能是如何实现的?

Feature request / 功能建议

请问论文中提到的语料库子集公开的地址在哪?

Motivation / 动机

web_demo中预设的几个角色是如何实现的,模型本身是否有这几个角色的信息,还是通过模型泛化后用prompt限定生成的?

Your contribution / 您的贡献

本地运行了下web_demo示例代码,对话中出现了死循环回复相同语句的问题

CharacterGLM-6B如何自定义prompt内容?

您好,我通过阅读cli_demo.py代码,看到如下代码:

session_meta = {
'user_info': '我是陆星辰,是一个男性,是一位知名导演,也是苏梦远的合作导演。我擅长拍摄音乐题材的电影。苏梦远对我的态度是尊敬的,并视我为良师益友。',
'bot_info': '苏梦远,本名苏远心,是一位当红的国内女歌手及演员。在参加选秀节目后,凭借独特的嗓音及出众的舞台魅力迅速成名,进入娱乐圈。'
'她外表美丽动人,但真正的魅力在于她的才华和勤奋。苏梦远是音乐学院毕业的优秀生,善于创作,拥有多首热门原创歌曲。'
'除了音乐方面的成就,她还热衷于慈善事业,积极参加公益活动,用实际行动传递正能量。'
'在工作中,她对待工作非常敬业,拍戏时总是全身心投入角色,赢得了业内人士的赞誉和粉丝的喜爱。'
'虽然在娱乐圈,但她始终保持低调、谦逊的态度,深得同行尊重。在表达时,苏梦远喜欢使用“我们”和“一起”,强调团队精神。',
'bot_name': '苏梦远',
'user_name': '陆星辰'
}
for response, history, past_key_values in model.stream_chat(
tokenizer=tokenizer,
session_meta=session_meta,
query=query,
history=history,
top_p=1,
temperature=0.01,
past_key_values=past_key_values,
return_past_key_values=True
):

我是否可以理解为session_meta其实就是模型的prompt?
如果我想自定义一部分prompt,比如要求模型必须说中文,必须依照给定的场景描述进行回答,必须按照给定话术的语气保持一致性语气进行回答等,这些原本应该放在prompt中的内容我应该通过什么方式传递给CharacterGLM-6B模型?

感觉和RAG差不多啊,

模型没有放出来, 从示例看,问马斯克的一些成就,这些内容是不是已经在profile中提到了。

期待微调脚本

Feature request / 功能建议

期待微调脚本!想用来模拟一些虚拟角色说话~想收集数据来进行微调,非常期待!

Motivation / 动机

想用数据微调CharacterGLM模拟虚拟人物!

Your contribution / 您的贡献

没有

user_info和bot_info的提示优先级

user_info和bot_info的提示优先级

  1. 想询问info内容是以system prompt设定的吗?模型能否学习到info中的知识
  2. 智谱的characterGLM接口,temperature设定是多少?
    谢谢

数据集的语言形式(中英文)

Feature request / 功能建议

请教一下

  1. 250个角色里面**角色和外国角色都有吗?
  2. 角色扮演的数据集,采用语言是中英文都有吗?

Motivation / 动机

Your contribution / 您的贡献

启动后没有吃GPU,运行速度也很慢,是怎么回事呢

System Info / 系統信息

CUDA 10020,py 3.10

Who can help? / 谁可以帮助到您?

No response

Information / 问题信息

  • The official example scripts / 官方的示例脚本
  • My own modified scripts / 我自己修改的脚本和任务

Reproduction / 复现过程

/.conda/envs/py310/lib/python3.10/site-packages/torch/cuda/init.py:141: UserWarning: CUDA initialization: The NVIDIA driver on your system is too old (found version 10020). Please update your GPU driver by downloading and installing a new version from the URL: http://www.nvidia.com/Download/index.aspx Alternatively, go to: https://pytorch.org to install a PyTorch version that has been compiled with your version of the CUDA driver. (Triggered internally at ../c10/cuda/CUDAFunctions.cpp:108.)

Expected behavior / 期待表现

怎么样可以加速分析呢

CharacterGLM支持量化了吗

Feature request / 功能建议

CharacterGLM支持量化了吗

Motivation / 动机

显存不足

Your contribution / 您的贡献

测试

期待profile数据

Feature request / 功能建议

论文中提到会公开的profile数据,希望获得并学习

Motivation / 动机

为了学术研究

Your contribution / 您的贡献

暂无

可以公开训练的角色和作品吗

Feature request / 功能建议

可以公开训练的角色和作品的名称

Motivation / 动机

我想测一下你们的模型

Your contribution / 您的贡献

暂无

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.