Commit
•
3358b54
1
Parent(s):
1fc6303
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,23 +1,47 @@
|
|
| 1 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
license: mit
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
metrics:
|
| 6 |
- precision
|
| 7 |
- recall
|
| 8 |
- f1
|
| 9 |
- accuracy
|
| 10 |
model-index:
|
| 11 |
-
- name: lilt-xlm-roberta-base-finetuned-DocLayNet-
|
| 12 |
results: []
|
| 13 |
---
|
| 14 |
|
| 15 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 16 |
should probably proofread and complete it, then remove this comment. -->
|
| 17 |
|
| 18 |
-
#
|
| 19 |
|
| 20 |
-
This model is a fine-tuned version of [nielsr/lilt-xlm-roberta-base](https://huggingface.co/nielsr/lilt-xlm-roberta-base)
|
| 21 |
It achieves the following results on the evaluation set:
|
| 22 |
- Loss: 1.0003
|
| 23 |
- Precision: 0.8584
|
|
|
|
| 1 |
---
|
| 2 |
+
language:
|
| 3 |
+
- en
|
| 4 |
+
- de
|
| 5 |
+
- fr
|
| 6 |
+
- ja
|
| 7 |
license: mit
|
| 8 |
tags:
|
| 9 |
- generated_from_trainer
|
| 10 |
+
- DocLayNet
|
| 11 |
+
- COCO
|
| 12 |
+
- PDF
|
| 13 |
+
- IBM
|
| 14 |
+
- Financial-Reports
|
| 15 |
+
- Finance
|
| 16 |
+
- Manuals
|
| 17 |
+
- Scientific-Articles
|
| 18 |
+
- Science
|
| 19 |
+
- Laws
|
| 20 |
+
- Law
|
| 21 |
+
- Regulations
|
| 22 |
+
- Patents
|
| 23 |
+
- Government-Tenders
|
| 24 |
+
- object-detection
|
| 25 |
+
- image-segmentation
|
| 26 |
+
- token-classification
|
| 27 |
+
datasets:
|
| 28 |
+
- pierreguillou/DocLayNet-base
|
| 29 |
metrics:
|
| 30 |
- precision
|
| 31 |
- recall
|
| 32 |
- f1
|
| 33 |
- accuracy
|
| 34 |
model-index:
|
| 35 |
+
- name: lilt-xlm-roberta-base-finetuned-with-DocLayNet-base-at-linelevel-ml384
|
| 36 |
results: []
|
| 37 |
---
|
| 38 |
|
| 39 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 40 |
should probably proofread and complete it, then remove this comment. -->
|
| 41 |
|
| 42 |
+
# Document Understanding model (at line level)
|
| 43 |
|
| 44 |
+
This model is a fine-tuned version of [nielsr/lilt-xlm-roberta-base](https://huggingface.co/nielsr/lilt-xlm-roberta-base) with the [DocLayNet base](https://huggingface.co/datasets/pierreguillou/DocLayNet-base) dataset.
|
| 45 |
It achieves the following results on the evaluation set:
|
| 46 |
- Loss: 1.0003
|
| 47 |
- Precision: 0.8584
|