Giter Site home page Giter Site logo

starwhisper's People

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

starwhisper's Issues

SFT

Dear Dr. Li
The work of StarGLM has inspired me a lot. What kind of fine-tuning method is this based on?

有点困惑请教一下

readme的功能展示说明是20w条天文对话数据分布微调
我想请教一下,一个大模型纯微调是应该没有办法增加新的领域知识的吧,所以这里我们仅仅只做了微调(sft),还是也做了预训练(pt)。
如果能够通过微调就增加新的领域知识的话,我们微调的硬件大概是一个什么配置,谢谢。

Potentially open sourcing the model on HF and create a demo there?

Hi YuYang,

Congratulations on your great work! It would be really nice if you can upload the model to Hugging Face hub.

This would help model discovery and integration with tools.

For example, this is the ChatGLM repo on Hugging Face. https://huggingface.co/THUDM/chatglm2-6b
With that, the model can be invoked with a few lines of code.

from transformers import AutoTokenizer, AutoModel
tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm2-6b", trust_remote_code=True)
model = AutoModel.from_pretrained("THUDM/chatglm2-6b", trust_remote_code=True).half().cuda()
model = model.eval()
response, history = model.chat(tokenizer, "你好", history=[])
print(response)
你好👋!我是人工智能助手 ChatGLM-6B,很高兴见到你,欢迎问我任何问题。
response, history = model.chat(tokenizer, "晚上睡不着应该怎么办", history=history)
print(response)

Also you can fork nice demos like https://huggingface.co/spaces/mikeee/chatglm2-6b-4bit to create your own demos. It will make it very easy for users to use and amplify the impact of your project.

If you run into any issues, feel free to let us know and we're happy to help. :-) My WeChat ID is zhou_a_zhou

[Feature Request] Support InternLM

Dear StarGLM developer,

我是 InternLM 社区开发者&志愿者尖米, 大佬开源的工作对我的启发很大,希望可以探讨使用 InternLM 实现 StarGLM 的可能性和实现路径,我的微信是 mzm312,希望可以取得联系进行更深度的交流;

Best regards,
尖米

训练数据

请问用于多模态部分训练的数据会开源吗

二次训练数据

您好,您是怎么对原始的文档处理得到训练数据的?谢谢

Agent能力数据

您好,请问提升模型Agent能力的交互数据会开源吗?

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.