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 live demo Space badge + section to model card
Browse files
README.md
CHANGED
|
@@ -79,6 +79,7 @@ model-index:
|
|
| 79 |
### *Dynamic Graph Attention · Temporal Semantic Decay · Per-Token Adaptive Depth Routing*
|
| 80 |
|
| 81 |
[](https://doi.org/10.5281/zenodo.20287390)
|
|
|
|
| 82 |
[](https://github.com/vignesh2027/TemporalMesh-Transformer)
|
| 83 |
[](https://doi.org/10.5281/zenodo.20287390)
|
| 84 |
[](https://huggingface.co/datasets/vigneshwar234/TMT-Benchmarks)
|
|
@@ -230,6 +231,16 @@ k_m ← 0.99 · k_m + 0.01 · mean(attending tokens)
|
|
| 230 |
|
| 231 |
---
|
| 232 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 233 |
## Quick Start
|
| 234 |
|
| 235 |
### Installation
|
|
|
|
| 79 |
### *Dynamic Graph Attention · Temporal Semantic Decay · Per-Token Adaptive Depth Routing*
|
| 80 |
|
| 81 |
[](https://doi.org/10.5281/zenodo.20287390)
|
| 82 |
+
[](https://huggingface.co/spaces/vigneshwar234/TemporalMesh-Transformer-Demo)
|
| 83 |
[](https://github.com/vignesh2027/TemporalMesh-Transformer)
|
| 84 |
[](https://doi.org/10.5281/zenodo.20287390)
|
| 85 |
[](https://huggingface.co/datasets/vigneshwar234/TMT-Benchmarks)
|
|
|
|
| 231 |
|
| 232 |
---
|
| 233 |
|
| 234 |
+
## 🚀 Live Demo
|
| 235 |
+
|
| 236 |
+
Try TMT interactively — no install needed:
|
| 237 |
+
|
| 238 |
+
👉 **[huggingface.co/spaces/vigneshwar234/TemporalMesh-Transformer-Demo](https://huggingface.co/spaces/vigneshwar234/TemporalMesh-Transformer-Demo)**
|
| 239 |
+
|
| 240 |
+
Visualise exit gates, dynamic attention graphs, and per-token compute depth on any sentence you type.
|
| 241 |
+
|
| 242 |
+
---
|
| 243 |
+
|
| 244 |
## Quick Start
|
| 245 |
|
| 246 |
### Installation
|