update desc
Browse files
README.md
CHANGED
@@ -68,9 +68,11 @@ inference:
|
|
68 |
|
69 |
- **Use cases:** long narrative summarization (think stories - as the dataset intended), article/paper/textbook/other summarization, technical:simple summarization.
|
70 |
- Models trained on this dataset tend to also _explain_ what they are summarizing, which IMO is awesome.
|
71 |
-
-
|
|
|
|
|
72 |
- all the parameters for generation on the API are the same for easy comparison between versions.
|
73 |
-
- works well on lots of text, can hand 16384 tokens/batch.
|
74 |
|
75 |
## Other Checkpoints on Booksum
|
76 |
|
|
|
68 |
|
69 |
- **Use cases:** long narrative summarization (think stories - as the dataset intended), article/paper/textbook/other summarization, technical:simple summarization.
|
70 |
- Models trained on this dataset tend to also _explain_ what they are summarizing, which IMO is awesome.
|
71 |
+
- Trained for 16 epochs vs. [`pszemraj/led-base-16384-finetuned-booksum`](https://huggingface.co/pszemraj/led-base-16384-finetuned-booksum),
|
72 |
+
|
73 |
+
- parameters adjusted for _very_ fine-tuning type training (super low LR, etc)
|
74 |
- all the parameters for generation on the API are the same for easy comparison between versions.
|
75 |
+
- works well on lots of text, and can hand 16384 tokens/batch.
|
76 |
|
77 |
## Other Checkpoints on Booksum
|
78 |
|