Code Monkey home page Code Monkey logo

chatterbox's Introduction

Hi there 👋

I'm Enze, a research engineer in Natural language processing.

My research interests are in Natural language processing, recommender systems, computational advertising, and information retrieval, and broader interests include comparative learning, multi-modal pre-training model, transfer learning, and their applications in advertising, search, and recommendation.

Coding is probably my favorite thing. If you have anything else want to know, please drop me an email, or comment a message on my Website.

Fred's GitHub Stats

chatterbox's People

Contributors

enze5088 avatar

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

Forkers

yaoguangzi rayjuezhu iamleon121 dlxj wdud iwanglei1 rosefun londza iamfaith hui-ze duanzhihua soacker abbottkilig yugenlgy

chatterbox's Issues

关于MLP层一些疑问

class LlamaMLP(nn.Module):
def init(
self,
hidden_size: int,
intermediate_size: int,
hidden_act: str,
):
super().init()
self.gate_proj = nn.Linear(hidden_size, intermediate_size, bias=False)
self.down_proj = nn.Linear(intermediate_size, hidden_size, bias=False)
self.up_proj = nn.Linear(hidden_size, intermediate_size, bias=False)
self.act_fn = ACT2FN[hidden_act]

def forward(self, x):
    return self.down_proj(self.act_fn(self.gate_proj(x)) * self.up_proj(x))

这个是llama的mlp层，大佬知道为什么是映射一层self.gate_proj 然后激活后点积一层self.up_proj 再进行self.up_proj的映射吗，按照类似transfomer的FFN结构应该没有self.gate_proj(x)) * self.up_proj(x)，类似的操作

block_size和max_position_embeddings

在src/train/model_file/LLaMA-zh-base/config.json中max_position_embeddings是2048，也就是说最长输入为2048。但是在src/train/preprocess.py里block_size默认为512，请问是什么原因呢？

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.