Downloads · 30 days
19
5% of all-time downloads
pszemraj/long-t5-tglobal-xl-qmsum-wip
long-t5-tglobal-xl-qmsum-wip is a summarization model from pszemraj. Use it when you need a shorter version of a longer text. It is set up for transformers. The card lists the license as apache-2.0.
⚠️ warning - this is a work in progress ⚠️
Downloads · 30 days
19
5% of all-time downloads
All-time downloads
369
Public
Parameters
2.9B
23.3 GB on disk
Likes
1
Public
Click a slice to open those files.
.bin11.7 GB · 50%
From the Hugging Face model README
<a href="https://colab.research.google.com/gist/pszemraj/ea0ac20dae4ad84bea4ea64543f84a85/long-t5-tglobal-xl-qmsum-wip.ipynb"> <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/> </a>⚠️ warning - this is a work in progress ⚠️
This model is a fine-tuned version of google/long-t5-tglobal-xl on the pszemraj/qmsum-cleaned dataset.
input which means that inference should be run in a similar fashion.It achieves the following results on the evaluation set:
The following hyperparameters were used during training:
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 1.5376 | 1.0 | 99 | 2.0104 | 35.8802 | 11.4595 | 23.6656 | 31.49 | 77.77 |
| 1.499 | 2.0 | 198 | 2.0358 | 35.1265 | 11.549 | 23.1062 | 30.8815 | 88.88 |
| 1.5034 | 3.0 | 297 | 2.0505 | 35.3881 | 11.509 | 23.1543 | 31.3295 | 80.8 |