Git Product home page Git Product logo

hf-for-rwkvraven-alpaca's Introduction

HF-For-RWKVRaven-Alpaca

将RWKV Raven/Pile/PilePlus系列模型由原生pth转为HF格式(这三种模型的词表及tokenizer一致，推荐V11或V12的Raven版本)，并进行Alpaca全量微调。

环境：WIN10+Torch1.31+Cuda11.6

代码说明：
configuration_rwkv.py：RWKV模型的配置
convert_rwkv_checkpoint_to_hf.py：RWKV的原生pth格式转为HF格式
generate.py：使用HF的RWKV模型架设服务
hello.py：测试HF的RWKV模型
modeling_rwkv.py：RWKV模型的网络结构
alpacatrain.py：使用test.json的alpaca全量微调模型
alpacatest.py：测试alpaca全量微调模型

一个基于RWKV-430M-Pile的Alpaca全量微调范例（2条数据，1个epoch，仅测试）：
HF开源地址：
https://huggingface.co/StarRing2022/RWKV-430M-Pile-Alpaca/

一个RWKV-4-Raven-3B-v11-Eng49%-Chn49%的原生pth格式转为HF格式范例：
https://huggingface.co/StarRing2022/RWKV-4-Raven-3B-v11-zh/

hf-for-rwkvraven-alpaca's People

Contributors

starring2022 avatar

Watchers

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.