Update README.md
Browse files
README.md
CHANGED
|
@@ -30,12 +30,10 @@ inference:
|
|
| 30 |
|
| 31 |
---
|
| 32 |
|
| 33 |
-
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 34 |
-
should probably proofread and complete it, then remove this comment. -->
|
| 35 |
|
| 36 |
# checkpoints
|
| 37 |
|
| 38 |
-
This model is a fine-tuned version of [google/pegasus-large](https://huggingface.co/google/pegasus-large) on
|
| 39 |
|
| 40 |
## Model description
|
| 41 |
|
|
@@ -43,7 +41,8 @@ More information needed
|
|
| 43 |
|
| 44 |
## Intended uses & limitations
|
| 45 |
|
| 46 |
-
|
|
|
|
| 47 |
|
| 48 |
## Training and evaluation data
|
| 49 |
|
|
|
|
| 30 |
|
| 31 |
---
|
| 32 |
|
|
|
|
|
|
|
| 33 |
|
| 34 |
# checkpoints
|
| 35 |
|
| 36 |
+
This model is a fine-tuned version of [google/pegasus-large](https://huggingface.co/google/pegasus-large) on the [booksum](https://github.com/salesforce/booksum) dataset.
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
|
|
|
| 41 |
|
| 42 |
## Intended uses & limitations
|
| 43 |
|
| 44 |
+
- standard pegasus has a max input length of 1024 tokens, therefore when training, it only saw the first 1024 tokens of a chapter when training, and learned to try to make the summary from that. Keep this in mind when using this model.
|
| 45 |
+
- this was only trained on the dataset for an epoch but still provides reasonable results.
|
| 46 |
|
| 47 |
## Training and evaluation data
|
| 48 |
|