nGPT pytorch
0.2.7
Implementasi nGPT yang cepat, pembelajaran sepenuhnya di hipersfer, dari NvidiaAI. Pertanyaannya adalah apakah ada hilangnya ekspresi yang mereka sembunyikan, tapi saya akan menerimanya dengan itikad baik.
Jenis jaringan ini juga harus dipelajari dalam konteks pembelajaran terus-menerus dan hilangnya plastisitas
Adaptasi terhadap transformator visi telah hadir
$ pip install nGPT-pytorch
import torch
from nGPT_pytorch import nGPT
model = nGPT (
num_tokens = 256 ,
dim = 512 ,
depth = 4 ,
attn_norm_qk = True
)
x = torch . randint ( 0 , 256 , ( 2 , 2048 ))
loss = model ( x , return_loss = True )
loss . backward ()
logits = model ( x ) # (2, 2048, 256)
Enwik8
$ python train.py
@inproceedings { Loshchilov2024nGPTNT ,
title = { nGPT: Normalized Transformer with Representation Learning on the Hypersphere } ,
author = { Ilya Loshchilov and Cheng-Ping Hsieh and Simeng Sun and Boris Ginsburg } ,
year = { 2024 } ,
url = { https://api.semanticscholar.org/CorpusID:273026160 }
}
@article { Luo2017CosineNU ,
title = { Cosine Normalization: Using Cosine Similarity Instead of Dot Product in Neural Networks } ,
author = { Chunjie Luo and Jianfeng Zhan and Lei Wang and Qiang Yang } ,
journal = { ArXiv } ,
year = { 2017 } ,
volume = { abs/1702.05870 } ,
url = { https://api.semanticscholar.org/CorpusID:1505432 }
}
@inproceedings { Zhou2024ValueRL ,
title = { Value Residual Learning For Alleviating Attention Concentration In Transformers } ,
author = { Zhanchao Zhou and Tianyi Wu and Zhiyun Jiang and Zhenzhong Lan } ,
year = { 2024 } ,
url = { https://api.semanticscholar.org/CorpusID:273532030 }
}