Updated model to release version
Browse files- README.md +7 -1
- config.json +0 -1
- pytorch_model.bin +1 -1
README.md
CHANGED
|
@@ -11,4 +11,10 @@ license: cc-by-sa-4.0
|
|
| 11 |
|
| 12 |
---
|
| 13 |
|
| 14 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
|
| 12 |
---
|
| 13 |
|
| 14 |
+
This is a model for correcting spelling and grammar errors in Icelandic text. It is based on the pretrained ByT5 model (https://arxiv.org/abs/2105.13626) and finetuned on Icelandic error correction data along with synthetic error data. The model is trained using the HuggingFace and PyTorch libraries.
|
| 15 |
+
|
| 16 |
+
The model performs well on correcting a variety of common issues in Icelandic text.
|
| 17 |
+
|
| 18 |
+
This README will be updated soon along with citation reference.
|
| 19 |
+
|
| 20 |
+
|
config.json
CHANGED
|
@@ -1,5 +1,4 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "/data/scratch/svanhvit/byt5/byt5-base-finetuned-35M-is_err-to-is_corr-max-len-512-bz-8/checkpoint-510000",
|
| 3 |
"architectures": [
|
| 4 |
"T5ForConditionalGeneration"
|
| 5 |
],
|
|
|
|
| 1 |
{
|
|
|
|
| 2 |
"architectures": [
|
| 3 |
"T5ForConditionalGeneration"
|
| 4 |
],
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2326697929
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:02b7b478708ab4bd5a19480710444f1040a5009bb4dae7478fd3bcc86e9c8e56
|
| 3 |
size 2326697929
|