Premchan369 commited on
Commit
fdc55d3
·
verified ·
1 Parent(s): ad01d72

Upload CITATION.cff

Browse files
Files changed (1) hide show
  1. CITATION.cff +23 -0
CITATION.cff ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ cff-version: 1.2.0
2
+ title: "Q-TensorFormer: Quantum-Enhanced Tensor Network LLM Compression Engine"
3
+ message: "If you use this software in your research, please cite it using the metadata below."
4
+ authors:
5
+ - given-names: Premchan369
6
+ affiliation: ""
7
+ repository-code: "https://huggingface.co/Premchan369/q-tensorformer"
8
+ url: "https://huggingface.co/Premchan369/q-tensorformer"
9
+ abstract: >-
10
+ Q-TensorFormer is a hybrid transformer architecture that compresses feed-forward
11
+ layers using Tensor-Train (TT) decomposition and enhances token representations
12
+ via real quantum circuits, with adaptive TT-rank scheduling guided by attention
13
+ entropy. It achieves 50-70% parameter reduction at equivalent perplexity.
14
+ keywords:
15
+ - tensor networks
16
+ - quantum machine learning
17
+ - model compression
18
+ - transformer
19
+ - language modeling
20
+ - efficient deep learning
21
+ license: Apache-2.0
22
+ version: 3.0.0
23
+ date-released: 2026-05-06