fanghui

一個hello world通，无用程序员，本人github 地址： 基於chatgpt davinci模型的discord bot

[Science girl @sciencegirl]

The fragile beauty of snowflakes up close

[fanghui @xufanghui]

@VnetLink 体验一下

[fanghui @xufanghui]

@manateelazycat 翻译不错，70b 更好一点，但是运行太慢了，如果只是简单应用，更划算

[fanghui @xufanghui]

CodeGPT 插件, pycharm/intellij idea的 可以用的开源插件 https://t.co/fJTPs5tkAb, 支持基本所有的开源模型接入，这个插件就是类似github copilot 辅助你写程序 ,开源就是定制化比较强

codegpt idea 官方介绍：https://t.co/fCcMcdQpJL

github copilot idea官方介绍：https://t.co/7fK8eD9vCT

[fanghui @xufanghui]

在农历新年/新春到来之际，用chatgpt写了祝福词，以大家共勉。

[Michael Bronstein @mmbronstein]

https://t.co/atLrZkB85p

**Cooperative GNNs** with @benfinkelshtein @hxyscott @ismaililkanc

In message-passing GNNs, each node is updated based on messages from its neighborhood. In Co-GNNs, every node can choose to either ‘listen’, ‘broadcast’, ‘listen&broadcast’, or ‘isolate’

[fanghui @xufanghui]

捕鼠器与老鼠的故事

[fanghui @xufanghui]

@indigox 另一个版本，可以参考一下

[fanghui @xufanghui]

哈哈，我也晒下

[fanghui @xufanghui]

@blackanger 非常有用，👍

[fanghui @xufanghui]

@abacaj it's very good! i like it

[fanghui @xufanghui]

欢迎分享您的经验

[fanghui @xufanghui]

最近twitter友都对类chatgpt的模型及其替代品特别感兴趣。有没有对已有数据，生成prompt提示词的，有这方面想法的或需要的，咱们可以聊聊这方面的话题。
#prompt生成 #提示词 #提示词生成

[Binxu Wang 🐱 @WangBinxu]

Excited to have given a 2-day ML from Scratch tutorial on Transformers #GPT at Harvard Medical School this week! Thanks to the huge interest, it was one of the most popular of its kind!
Check out
Slides: https://t.co/8paPdOZ5BB
Links to coding exercise: https://t.co/EWmiCLimVF

[Lior Alexander @LiorOnAI]

BREAKING: StabilityAI just released their own LLM, called StableLM.

"The Alpha version of the model is available in 3 billion and 7 billion parameters, with 15 billion to 65 billion parameter models to follow."

The models are available on GitHub!

Repo: https://t.co/TwWWeVJDIh
Blog: https://t.co/prPxncAMFF

[fanghui @xufanghui]

@dotey 喜欢这个，👍一个

[fanghui @xufanghui]

@NalaGinrut 一語道破真諦

[fanghui @xufanghui]

@tinyfool 沒看，先👍一個

[fanghui @xufanghui]

@dotey 哈哈，這個還需要進一步的場景化，比如：對長記憶的需求和關聯