Update README.md
Browse files
README.md
CHANGED
@@ -69,7 +69,8 @@ inference:
|
|
69 |
|
70 |
# Longformer Encoder-Decoder (LED) fine-tuned on Booksum
|
71 |
|
72 |
-
- **Use cases:** long narrative summarization (think stories - as the dataset intended), article/paper/textbook/other summarization, technical:simple summarization.
|
|
|
73 |
- This is an 'upgraded' version of [`pszemraj/led-base-16384-finetuned-booksum`](https://huggingface.co/pszemraj/led-base-16384-finetuned-booksum), it was trained for an additional epoch with a max summary length of 1024 tokens (original was trained with 512) as a small portion of the summaries are between 512-1024 tokens long.
|
74 |
- all the parameters for generation on the API are the same for easy comparison between versions.
|
75 |
- works well on lots of text, can hand 16384 tokens/batch.
|
|
|
69 |
|
70 |
# Longformer Encoder-Decoder (LED) fine-tuned on Booksum
|
71 |
|
72 |
+
- **Use cases:** long narrative summarization (think stories - as the dataset intended), article/paper/textbook/other summarization, technical:simple summarization.
|
73 |
+
- Models trained on this dataset tend to also _explain_ what they are summarizing, which IMO is awesome.
|
74 |
- This is an 'upgraded' version of [`pszemraj/led-base-16384-finetuned-booksum`](https://huggingface.co/pszemraj/led-base-16384-finetuned-booksum), it was trained for an additional epoch with a max summary length of 1024 tokens (original was trained with 512) as a small portion of the summaries are between 512-1024 tokens long.
|
75 |
- all the parameters for generation on the API are the same for easy comparison between versions.
|
76 |
- works well on lots of text, can hand 16384 tokens/batch.
|