goldfish-models
commited on
Commit
•
6ae7c26
1
Parent(s):
7dec56c
Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
@@ -2,8 +2,8 @@
|
|
2 |
---
|
3 |
license: apache-2.0
|
4 |
language:
|
5 |
-
- chi
|
6 |
- zho
|
|
|
7 |
datasets:
|
8 |
- allenai/nllb
|
9 |
- cis-lmu/Glot500
|
@@ -12,7 +12,7 @@ library_name: transformers
|
|
12 |
pipeline_tag: text-generation
|
13 |
tags:
|
14 |
- goldfish
|
15 |
-
|
16 |
---
|
17 |
|
18 |
# zho_hant_10mb
|
@@ -25,7 +25,7 @@ Note: This language is available in Goldfish with other scripts (writing systems
|
|
25 |
|
26 |
Note: zho_hant is a [macrolanguage](https://iso639-3.sil.org/code_tables/639/data) code. Individual language codes yue_hant (Yue Chinese) and lzh_hant (Literary Chinese) are included in Goldfish, although with less data.
|
27 |
|
28 |
-
All training and hyperparameter details are in our paper, [Goldfish: Monolingual Language Models for 350 Languages (Chang et al., 2024)](https://
|
29 |
|
30 |
Training code and sample usage: https://github.com/tylerachang/goldfish
|
31 |
|
@@ -35,6 +35,7 @@ Sample usage also in this Google Colab: [link](https://colab.research.google.com
|
|
35 |
|
36 |
To access all Goldfish model details programmatically, see https://github.com/tylerachang/goldfish/blob/main/model_details.json.
|
37 |
All models are trained with a [CLS] (same as [BOS]) token prepended, and a [SEP] (same as [EOS]) token separating sequences.
|
|
|
38 |
Details for this model specifically:
|
39 |
|
40 |
* Architecture: gpt2
|
@@ -63,5 +64,6 @@ If you use this model, please cite:
|
|
63 |
author={Chang, Tyler A. and Arnett, Catherine and Tu, Zhuowen and Bergen, Benjamin K.},
|
64 |
journal={Preprint},
|
65 |
year={2024},
|
|
|
66 |
}
|
67 |
```
|
|
|
2 |
---
|
3 |
license: apache-2.0
|
4 |
language:
|
|
|
5 |
- zho
|
6 |
+
- chi
|
7 |
datasets:
|
8 |
- allenai/nllb
|
9 |
- cis-lmu/Glot500
|
|
|
12 |
pipeline_tag: text-generation
|
13 |
tags:
|
14 |
- goldfish
|
15 |
+
- arxiv:2408.10441
|
16 |
---
|
17 |
|
18 |
# zho_hant_10mb
|
|
|
25 |
|
26 |
Note: zho_hant is a [macrolanguage](https://iso639-3.sil.org/code_tables/639/data) code. Individual language codes yue_hant (Yue Chinese) and lzh_hant (Literary Chinese) are included in Goldfish, although with less data.
|
27 |
|
28 |
+
All training and hyperparameter details are in our paper, [Goldfish: Monolingual Language Models for 350 Languages (Chang et al., 2024)](https://www.arxiv.org/abs/2408.10441).
|
29 |
|
30 |
Training code and sample usage: https://github.com/tylerachang/goldfish
|
31 |
|
|
|
35 |
|
36 |
To access all Goldfish model details programmatically, see https://github.com/tylerachang/goldfish/blob/main/model_details.json.
|
37 |
All models are trained with a [CLS] (same as [BOS]) token prepended, and a [SEP] (same as [EOS]) token separating sequences.
|
38 |
+
For best results, make sure that [CLS] is prepended to your input sequence (see sample usage linked above)!
|
39 |
Details for this model specifically:
|
40 |
|
41 |
* Architecture: gpt2
|
|
|
64 |
author={Chang, Tyler A. and Arnett, Catherine and Tu, Zhuowen and Bergen, Benjamin K.},
|
65 |
journal={Preprint},
|
66 |
year={2024},
|
67 |
+
url={https://www.arxiv.org/abs/2408.10441},
|
68 |
}
|
69 |
```
|