Update README.md
Browse files
README.md
CHANGED
@@ -433,12 +433,12 @@ The Longformer Encoder-Decoder (LED) for Narrative-Esque Long Text Summarization
|
|
433 |
|
434 |
## Key Features and Use Cases
|
435 |
|
436 |
-
- Ideal for summarizing long narratives, articles, papers, textbooks, and other
|
437 |
-
-
|
438 |
- High capacity: Handles up to 16,384 tokens per batch.
|
439 |
-
-
|
440 |
|
441 |
-
> **Note:** The API is configured to generate a maximum of
|
442 |
|
443 |
## Training Details
|
444 |
|
@@ -446,16 +446,14 @@ The model was trained on the BookSum dataset released by SalesForce, which leads
|
|
446 |
|
447 |
Model checkpoint: [`pszemraj/led-base-16384-finetuned-booksum`](https://huggingface.co/pszemraj/led-base-16384-finetuned-booksum).
|
448 |
|
449 |
-
For comparison, all generation parameters for the API have been kept consistent across versions.
|
450 |
-
|
451 |
## Other Related Checkpoints
|
452 |
|
453 |
Apart from the LED-based model, I have also fine-tuned other models on `kmfoda/booksum`:
|
454 |
|
455 |
-
- [Long-T5-
|
456 |
- [BigBird-Pegasus-Large-K](https://huggingface.co/pszemraj/bigbird-pegasus-large-K-booksum)
|
457 |
- [Pegasus-X-Large](https://huggingface.co/pszemraj/pegasus-x-large-book-summary)
|
458 |
-
- [Long-T5-
|
459 |
|
460 |
There are also other variants on other datasets etc on my hf profile, feel free to try them out :)
|
461 |
|
@@ -524,6 +522,8 @@ out_str = summarizer.summarize_string(long_string)
|
|
524 |
print(f"summary: {out_str}")
|
525 |
```
|
526 |
|
527 |
-
Currently implemented interfaces include a Python API, a Command-Line Interface (CLI), and a shareable demo
|
|
|
|
|
528 |
|
529 |
---
|
|
|
433 |
|
434 |
## Key Features and Use Cases
|
435 |
|
436 |
+
- Ideal for summarizing long narratives, articles, papers, textbooks, and other documents.
|
437 |
+
- the sparknotes-esque style leads to 'explanations' in the summarized content, offering insightful output.
|
438 |
- High capacity: Handles up to 16,384 tokens per batch.
|
439 |
+
- demos: try it out in the notebook linked above or in the [demo on Spaces](https://huggingface.co/spaces/pszemraj/summarize-long-text)
|
440 |
|
441 |
+
> **Note:** The API is configured to generate a maximum of ~96 tokens due to inference timeout constraints. For better results, use the Python approach detailed below.
|
442 |
|
443 |
## Training Details
|
444 |
|
|
|
446 |
|
447 |
Model checkpoint: [`pszemraj/led-base-16384-finetuned-booksum`](https://huggingface.co/pszemraj/led-base-16384-finetuned-booksum).
|
448 |
|
|
|
|
|
449 |
## Other Related Checkpoints
|
450 |
|
451 |
Apart from the LED-based model, I have also fine-tuned other models on `kmfoda/booksum`:
|
452 |
|
453 |
+
- [Long-T5-tglobal-base](https://huggingface.co/pszemraj/long-t5-tglobal-base-16384-book-summary)
|
454 |
- [BigBird-Pegasus-Large-K](https://huggingface.co/pszemraj/bigbird-pegasus-large-K-booksum)
|
455 |
- [Pegasus-X-Large](https://huggingface.co/pszemraj/pegasus-x-large-book-summary)
|
456 |
+
- [Long-T5-tglobal-XL](https://huggingface.co/pszemraj/long-t5-tglobal-xl-16384-book-summary)
|
457 |
|
458 |
There are also other variants on other datasets etc on my hf profile, feel free to try them out :)
|
459 |
|
|
|
522 |
print(f"summary: {out_str}")
|
523 |
```
|
524 |
|
525 |
+
Currently implemented interfaces include a Python API, a Command-Line Interface (CLI), and a shareable demo/web UI.
|
526 |
+
|
527 |
+
For detailed explanations and documentation, check the [README](https://github.com/pszemraj/textsum) or the [wiki](https://github.com/pszemraj/textsum/wiki.
|
528 |
|
529 |
---
|