fix colab link
Browse files
README.md
CHANGED
@@ -282,10 +282,11 @@ model-index:
|
|
282 |
|
283 |
# Longformer Encoder-Decoder (LED) for Narrative-Esque Long Text Summarization
|
284 |
|
|
|
|
|
|
|
285 |
|
286 |
-
[
|
287 |
-
|
288 |
-
A fine-tuned version of [allenai/led-large-16384](https://huggingface.co/allenai/led-large-16384) on the BookSum dataset.
|
289 |
|
290 |
Goal: a model that can generalize well and is useful in summarizing long text in academic and daily usage. The result works well on lots of text and can handle 16384 tokens/batch (_if you have the GPU memory to handle that_)
|
291 |
|
@@ -322,17 +323,15 @@ summarizer = pipeline(
|
|
322 |
wall_of_text = "your words here"
|
323 |
|
324 |
result = summarizer(
|
325 |
-
|
326 |
-
|
327 |
-
|
328 |
-
|
329 |
-
|
330 |
-
|
331 |
-
|
332 |
-
|
333 |
-
|
334 |
-
|
335 |
-
|
336 |
```
|
337 |
|
338 |
|
|
|
282 |
|
283 |
# Longformer Encoder-Decoder (LED) for Narrative-Esque Long Text Summarization
|
284 |
|
285 |
+
<a href="https://colab.research.google.com/gist/pszemraj/3eba944ddc9fc9a4a1bfb21e83b57620/summarization-token-batching.ipynb">
|
286 |
+
<img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/>
|
287 |
+
</a>
|
288 |
|
289 |
+
A fine-tuned version of [allenai/led-large-16384](https://huggingface.co/allenai/led-large-16384) on the `BookSum` dataset.
|
|
|
|
|
290 |
|
291 |
Goal: a model that can generalize well and is useful in summarizing long text in academic and daily usage. The result works well on lots of text and can handle 16384 tokens/batch (_if you have the GPU memory to handle that_)
|
292 |
|
|
|
323 |
wall_of_text = "your words here"
|
324 |
|
325 |
result = summarizer(
|
326 |
+
wall_of_text,
|
327 |
+
min_length=16,
|
328 |
+
max_length=256,
|
329 |
+
no_repeat_ngram_size=3,
|
330 |
+
encoder_no_repeat_ngram_size=3,
|
331 |
+
repetition_penalty=3.5,
|
332 |
+
num_beams=4,
|
333 |
+
early_stopping=True,
|
334 |
+
)
|
|
|
|
|
335 |
```
|
336 |
|
337 |
|