Shobhank-iiitdwd
commited on
Commit
•
913134b
1
Parent(s):
059bc25
Update README.md
Browse files
README.md
CHANGED
@@ -455,11 +455,9 @@ model-index:
|
|
455 |
|
456 |
|
457 |
|
458 |
-
Summarize long text and get a SparkNotes-esque summary of arbitrary topics!
|
459 |
|
460 |
- generalizes reasonably well to academic & narrative text.
|
461 |
-
|
462 |
-
- Example notebook in Colab (_click on the icon above_).
|
463 |
|
464 |
## Cheeky Proof-of-Concept
|
465 |
|
@@ -492,7 +490,7 @@ A summary of the [infamous navy seals copypasta](https://knowyourmeme.com/memes/
|
|
492 |
|
493 |
## Model description
|
494 |
|
495 |
-
A fine-tuned version of [google/long-t5-tglobal-base](https://huggingface.co/google/long-t5-tglobal-base) on the `
|
496 |
|
497 |
- 30+ epochs of fine-tuning from the base model on V100/A100 GPUs
|
498 |
- Training used 16384 token input / 1024 max output
|
@@ -553,10 +551,6 @@ This model was originally tuned on Google Colab with a heavily modified variant
|
|
553 |
|
554 |
## Training procedure
|
555 |
|
556 |
-
### Updates:
|
557 |
-
|
558 |
-
- July 22, 2022: updated to a fairly converged checkpoint
|
559 |
-
- July 3, 2022: Added a new version with several epochs of additional general training that is more performant.
|
560 |
|
561 |
### Training hyperparameters
|
562 |
|
|
|
455 |
|
456 |
|
457 |
|
|
|
458 |
|
459 |
- generalizes reasonably well to academic & narrative text.
|
460 |
+
|
|
|
461 |
|
462 |
## Cheeky Proof-of-Concept
|
463 |
|
|
|
490 |
|
491 |
## Model description
|
492 |
|
493 |
+
A fine-tuned version of [google/long-t5-tglobal-base](https://huggingface.co/google/long-t5-tglobal-base) on the `booksum` dataset:
|
494 |
|
495 |
- 30+ epochs of fine-tuning from the base model on V100/A100 GPUs
|
496 |
- Training used 16384 token input / 1024 max output
|
|
|
551 |
|
552 |
## Training procedure
|
553 |
|
|
|
|
|
|
|
|
|
554 |
|
555 |
### Training hyperparameters
|
556 |
|