Update README.md
Browse files
README.md
CHANGED
@@ -347,15 +347,16 @@ model-index:
|
|
347 |
verified: true
|
348 |
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOWI2NjVlYjgwYWJiMjcyMDUzMzEwNDNjZTMxMDM0MjAzMzk1ZmIwY2Q1ZDQ2Y2M5NDBlMDEzYzFkNWEyNzJmNiIsInZlcnNpb24iOjF9.iZ1Iy7FuWL4GH7LS5EylVj5eZRC3L2ZsbYQapAkMNzR_VXPoMGvoM69Hp-kU7gW55tmz2V4Qxhvoz9cM8fciBA
|
349 |
---
|
350 |
-
#
|
351 |
|
352 |
<a href="https://colab.research.google.com/gist/pszemraj/3eba944ddc9fc9a4a1bfb21e83b57620/summarization-token-batching.ipynb">
|
353 |
<img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/>
|
354 |
</a>
|
355 |
|
356 |
-
This model is a fine-tuned version of [allenai/led-large-16384](https://huggingface.co/allenai/led-large-16384) on the `BookSum` dataset. It aims to generalize well and be useful in summarizing lengthy text for both academic and everyday purposes.
|
357 |
|
358 |
-
|
|
|
359 |
|
360 |
> **Note:** Due to inference API timeout constraints, outputs may be truncated before the fully summary is returned (try python or the demo)
|
361 |
|
@@ -466,6 +467,7 @@ For detailed explanations and documentation, check the [README](https://github.c
|
|
466 |
|
467 |
Check out these other related models, also trained on the BookSum dataset:
|
468 |
|
|
|
469 |
- [Long-T5-tglobal-base](https://huggingface.co/pszemraj/long-t5-tglobal-base-16384-book-summary)
|
470 |
- [BigBird-Pegasus-Large-K](https://huggingface.co/pszemraj/bigbird-pegasus-large-K-booksum)
|
471 |
- [Pegasus-X-Large](https://huggingface.co/pszemraj/pegasus-x-large-book-summary)
|
|
|
347 |
verified: true
|
348 |
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOWI2NjVlYjgwYWJiMjcyMDUzMzEwNDNjZTMxMDM0MjAzMzk1ZmIwY2Q1ZDQ2Y2M5NDBlMDEzYzFkNWEyNzJmNiIsInZlcnNpb24iOjF9.iZ1Iy7FuWL4GH7LS5EylVj5eZRC3L2ZsbYQapAkMNzR_VXPoMGvoM69Hp-kU7gW55tmz2V4Qxhvoz9cM8fciBA
|
349 |
---
|
350 |
+
# led-large-book-summary
|
351 |
|
352 |
<a href="https://colab.research.google.com/gist/pszemraj/3eba944ddc9fc9a4a1bfb21e83b57620/summarization-token-batching.ipynb">
|
353 |
<img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/>
|
354 |
</a>
|
355 |
|
356 |
+
This model is a fine-tuned version of [allenai/led-large-16384](https://huggingface.co/allenai/led-large-16384) on the `BookSum` dataset (`kmfoda/booksum`). It aims to generalize well and be useful in summarizing lengthy text for both academic and everyday purposes.
|
357 |
|
358 |
+
- Handles up to 16,384 tokens input
|
359 |
+
- See the Colab demo linked above or try the [demo on Spaces](https://huggingface.co/spaces/pszemraj/summarize-long-text)
|
360 |
|
361 |
> **Note:** Due to inference API timeout constraints, outputs may be truncated before the fully summary is returned (try python or the demo)
|
362 |
|
|
|
467 |
|
468 |
Check out these other related models, also trained on the BookSum dataset:
|
469 |
|
470 |
+
- [LED-large continued](https://huggingface.co/pszemraj/led-large-book-summary-continued) - experiment with further fine-tuning
|
471 |
- [Long-T5-tglobal-base](https://huggingface.co/pszemraj/long-t5-tglobal-base-16384-book-summary)
|
472 |
- [BigBird-Pegasus-Large-K](https://huggingface.co/pszemraj/bigbird-pegasus-large-K-booksum)
|
473 |
- [Pegasus-X-Large](https://huggingface.co/pszemraj/pegasus-x-large-book-summary)
|