Transformers
PyTorch
English
language-model
graph-attention
adaptive-depth
temporal-decay
efficient-llm
Eval Results (legacy)
Instructions to use vigneshwar234/TemporalMesh-Transformer with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use vigneshwar234/TemporalMesh-Transformer with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("vigneshwar234/TemporalMesh-Transformer", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Add CITATION.cff
Browse files- CITATION.cff +38 -0
CITATION.cff
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
cff-version: 1.2.0
|
| 2 |
+
message: "If you use TMT in your research, please cite it as below."
|
| 3 |
+
type: software
|
| 4 |
+
title: "TemporalMesh Transformer (TMT)"
|
| 5 |
+
abstract: >
|
| 6 |
+
A novel autoregressive language model architecture that simultaneously fuses
|
| 7 |
+
dynamic graph topology (Mesh Attention), token-level temporal semantic decay,
|
| 8 |
+
and per-token adaptive depth routing into a single unified model.
|
| 9 |
+
Achieves ~50% compute reduction and lower perplexity vs. parameter-matched baselines.
|
| 10 |
+
authors:
|
| 11 |
+
- name: "Vignesh"
|
| 12 |
+
alias: "vignesh2027"
|
| 13 |
+
repository-code: "https://github.com/vignesh2027/TemporalMesh-Transformer"
|
| 14 |
+
url: "https://huggingface.co/vigneshwar234/TemporalMesh-Transformer"
|
| 15 |
+
license: MIT
|
| 16 |
+
version: "1.0.0"
|
| 17 |
+
date-released: "2026-05-19"
|
| 18 |
+
keywords:
|
| 19 |
+
- transformer
|
| 20 |
+
- mesh-attention
|
| 21 |
+
- temporal-decay
|
| 22 |
+
- adaptive-depth
|
| 23 |
+
- graph-neural-network
|
| 24 |
+
- efficient-transformer
|
| 25 |
+
- language-model
|
| 26 |
+
- PyTorch
|
| 27 |
+
- NLP
|
| 28 |
+
- deep-learning
|
| 29 |
+
preferred-citation:
|
| 30 |
+
type: generic
|
| 31 |
+
title: >
|
| 32 |
+
TemporalMesh Transformer: Dynamic Graph Attention with Temporal Decay
|
| 33 |
+
and Adaptive Depth Routing
|
| 34 |
+
authors:
|
| 35 |
+
- name: "Vignesh"
|
| 36 |
+
year: 2026
|
| 37 |
+
url: "https://huggingface.co/vigneshwar234/TemporalMesh-Transformer"
|
| 38 |
+
notes: "Preprint. Available at GitHub and Hugging Face."
|