add pt model, readme
Browse files- README.md +79 -0
- config.json +2 -1
- pytorch_model.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
language:
|
| 4 |
+
- af
|
| 5 |
+
- az
|
| 6 |
+
- be
|
| 7 |
+
- bg
|
| 8 |
+
- bn
|
| 9 |
+
- ca
|
| 10 |
+
- cs
|
| 11 |
+
- cy
|
| 12 |
+
- da
|
| 13 |
+
- de
|
| 14 |
+
- el
|
| 15 |
+
- en
|
| 16 |
+
- eo
|
| 17 |
+
- es
|
| 18 |
+
- et
|
| 19 |
+
- eu
|
| 20 |
+
- fa
|
| 21 |
+
- fi
|
| 22 |
+
- fr
|
| 23 |
+
- fy
|
| 24 |
+
- ga
|
| 25 |
+
- gl
|
| 26 |
+
- gu
|
| 27 |
+
- he
|
| 28 |
+
- hi
|
| 29 |
+
- hu
|
| 30 |
+
- hy
|
| 31 |
+
- id
|
| 32 |
+
- is
|
| 33 |
+
- it
|
| 34 |
+
- ka
|
| 35 |
+
- kk
|
| 36 |
+
- ky
|
| 37 |
+
- la
|
| 38 |
+
- lt
|
| 39 |
+
- lv
|
| 40 |
+
- mg
|
| 41 |
+
- mk
|
| 42 |
+
- ml
|
| 43 |
+
- mt
|
| 44 |
+
- nl
|
| 45 |
+
- pa
|
| 46 |
+
- pl
|
| 47 |
+
- pt
|
| 48 |
+
- ro
|
| 49 |
+
- ru
|
| 50 |
+
- sk
|
| 51 |
+
- sq
|
| 52 |
+
- sv
|
| 53 |
+
- ta
|
| 54 |
+
- te
|
| 55 |
+
- th
|
| 56 |
+
- tr
|
| 57 |
+
- uk
|
| 58 |
+
- yi
|
| 59 |
+
- yo
|
| 60 |
+
datasets:
|
| 61 |
+
- benjamin/compoundpiece
|
| 62 |
+
---
|
| 63 |
+
|
| 64 |
+
CompoundPiece model trained only on Stage 1 training data (self-supervised training on hyphenated and non-hyphenated words scraped from the web). See [CompoundPiece: Evaluating and Improving Decompounding Performance of Language Models](https://arxiv.org/abs/2305.14214).
|
| 65 |
+
|
| 66 |
+
# Citation
|
| 67 |
+
|
| 68 |
+
```
|
| 69 |
+
@article{minixhofer2023compoundpiece,
|
| 70 |
+
title={CompoundPiece: Evaluating and Improving Decompounding Performance of Language Models},
|
| 71 |
+
author={Minixhofer, Benjamin and Pfeiffer, Jonas and Vuli{\'c}, Ivan},
|
| 72 |
+
journal={arXiv preprint arXiv:2305.14214},
|
| 73 |
+
year={2023}
|
| 74 |
+
}
|
| 75 |
+
```
|
| 76 |
+
|
| 77 |
+
# License
|
| 78 |
+
|
| 79 |
+
MIT
|
config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "
|
| 3 |
"architectures": [
|
| 4 |
"T5ForConditionalGeneration"
|
| 5 |
],
|
|
@@ -26,6 +26,7 @@
|
|
| 26 |
"relative_attention_num_buckets": 32,
|
| 27 |
"tie_word_embeddings": false,
|
| 28 |
"tokenizer_class": "ByT5Tokenizer",
|
|
|
|
| 29 |
"transformers_version": "4.26.0",
|
| 30 |
"use_cache": true,
|
| 31 |
"vocab_size": 384
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": ".",
|
| 3 |
"architectures": [
|
| 4 |
"T5ForConditionalGeneration"
|
| 5 |
],
|
|
|
|
| 26 |
"relative_attention_num_buckets": 32,
|
| 27 |
"tie_word_embeddings": false,
|
| 28 |
"tokenizer_class": "ByT5Tokenizer",
|
| 29 |
+
"torch_dtype": "float32",
|
| 30 |
"transformers_version": "4.26.0",
|
| 31 |
"use_cache": true,
|
| 32 |
"vocab_size": 384
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9f52371ba6fe38aaaae24eb8321f23d805848674cf4e8f6daaad632af2bb2319
|
| 3 |
+
size 2326696509
|