Giter Site home page Giter Site logo

maxmax2016 / chatrwkv Goto Github PK

View Code? Open in Web Editor NEW

This project forked from blinkdl/chatrwkv

0.0 0.0 0.0 1.1 MB

中文对话开源模型 ChatRWKV is like ChatGPT but powered by the RWKV (100% RNN) language model, and open source.

License: Apache License 2.0

Python 100.00%

chatrwkv's Introduction

ChatRWKV

ChatRWKV is like ChatGPT but powered by my RWKV (100% RNN) language model, which is the only RNN (as of now) that can match transformers in quality and scaling, while being faster and saves VRAM.

Download RWKV-4 weights: https://huggingface.co/BlinkDL

RWKV LM: https://github.com/BlinkDL/RWKV-LM

RWKV Discord: https://discord.gg/bDSBUMeFpc

RWKV-eval

It is not instruct-tuned for conversation yet, so don't directly ask it to do stuffs (unless it's a simple question).

Best prompt:

+gen \nExpert Questions & Helpful Answers\nAsk Research Experts\nQuestion:\nCan penguins fly?\n\nFull Answer:\n

+gen \nAsk Expert\n\nQuestion:\nCan penguins fly?\n\nExpert Full Answer:\n

Other examples:

+gen Here is a short story in which Jeff Bezos, Elon Musk, and Bill Gates fight in a tournament:

+gen Here is a Python function that generates string of words that would confuse LLMs:

+gen List of penguin facts:\n1.

+qa Can penguins fly?

+gen $ curl -i https://google.com/

+gen The following is the contents of https://en.wikipedia.org/wiki/Internet:

+gen Bob's Blog - Which is better, iOS or Android?

Chat example from a user: ChatRWKV

中文模型

QQ群 143626394(加入时请简单自我介绍)。

在 chat.py 修改 CHAT_LANG 为 Chinese,修改 MODEL_NAME 为你下载的模型路径。

必须下载双语模型(EngChn),选日期最新的。

大模型:7B 参数,需 14G 显存,效果好(以后可以优化显存占用和速度,但现在忙): https://huggingface.co/BlinkDL/rwkv-4-pile-7b/tree/main

中模型:3B 参数,需 6G 显存,效果中等: https://huggingface.co/BlinkDL/rwkv-4-pile-3b/tree/main

小模型:1.5B 参数 ,需 3G 显存,效果差些: https://huggingface.co/BlinkDL/rwkv-4-pile-1b5/tree/main

如果没显卡,或者显存不够,可以用 cpu 模式(很慢)。

试试这些指令:

+qa 奶茶好喝吗?
+qa 猫喜欢做什么?
+qa How can I learn Python?
+qa 猫会编程吗?
+qa 知乎大V有哪些特点?

+qq 请以《我的驴》为题写一篇作文
+qq 请以《企鹅》为题写一首诗歌

+gen 二向箔是一种超级武器,它的原理是
+gen 我抬头一看,竟然是
+gen 创业思路:\n1.
+gen import torch

chatrwkv's People

Contributors

blinkdl avatar www avatar masteryuan418 avatar

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.