thu-coai / characterglm-6b Goto Github PK
View Code? Open in Web Editor NEWCharacterGLM: Customizing Chinese Conversational AI Characters with Large Language Models
License: Apache License 2.0
CharacterGLM: Customizing Chinese Conversational AI Characters with Large Language Models
License: Apache License 2.0
希望能在本地部署和智谱ai里面的CharacterGLM一样的api接口
我希望使用自己的CharacterGLM作为(https://github.com/Ikaros-521/AI-Vtuber)支持智谱ai里面的CharacterGLM的后端
真对不起,
我尝试用glm3的api文件改一个出来,但是不符合智谱ai的标准
请问还开放吗?
Ubuntu20.04, Python 3.10, Pytorch 2.1.1, CUDA 11.8, cuDNN 8, NVCC, VNC
No response
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:
成功运行
请问论文中提到的语料库子集公开的地址在哪?
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?
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
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?
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。
非常欢迎各种声音讨论
No response
.
.
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!
想用数据微调CharacterGLM模拟虚拟人物!
没有
请教一下
无
无
CUDA 10020,py 3.10
No response
/.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.)
怎么样可以加速分析呢
CharacterGLM支持量化了吗
显存不足
测试
希望获得代码研究研究
论文中提到会公开的profile数据,希望获得并学习
为了学术研究
暂无
/
/
/
没资源可以下载
可以公开训练的角色和作品的名称
我想测一下你们的模型
暂无
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.