goldfish-models commited on
Commit
d653fd8
1 Parent(s): fb519ce

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +5 -3
README.md CHANGED
@@ -2,15 +2,15 @@
2
  ---
3
  license: apache-2.0
4
  language:
5
- - est
6
  - ekk
 
7
  datasets:
8
  - cis-lmu/Glot500
9
  library_name: transformers
10
  pipeline_tag: text-generation
11
  tags:
12
  - goldfish
13
-
14
  ---
15
 
16
  # ekk_latn_full
@@ -21,7 +21,7 @@ The Goldfish models are trained primarily for comparability across languages and
21
 
22
  Note: ekk_latn is an [individual language](https://iso639-3.sil.org/code_tables/639/data) code. Macrolanguage code est_latn (Estonian) is included in Goldfish. Consider using that model depending on your use case.
23
 
24
- All training and hyperparameter details are in our paper, [Goldfish: Monolingual Language Models for 350 Languages (Chang et al., 2024)](https://github.com/tylerachang/goldfish/blob/main/goldfish_paper_20240815.pdf).
25
 
26
  Training code and sample usage: https://github.com/tylerachang/goldfish
27
 
@@ -31,6 +31,7 @@ Sample usage also in this Google Colab: [link](https://colab.research.google.com
31
 
32
  To access all Goldfish model details programmatically, see https://github.com/tylerachang/goldfish/blob/main/model_details.json.
33
  All models are trained with a [CLS] (same as [BOS]) token prepended, and a [SEP] (same as [EOS]) token separating sequences.
 
34
  Details for this model specifically:
35
 
36
  * Architecture: gpt2
@@ -57,5 +58,6 @@ If you use this model, please cite:
57
  author={Chang, Tyler A. and Arnett, Catherine and Tu, Zhuowen and Bergen, Benjamin K.},
58
  journal={Preprint},
59
  year={2024},
 
60
  }
61
  ```
 
2
  ---
3
  license: apache-2.0
4
  language:
 
5
  - ekk
6
+ - est
7
  datasets:
8
  - cis-lmu/Glot500
9
  library_name: transformers
10
  pipeline_tag: text-generation
11
  tags:
12
  - goldfish
13
+ - arxiv:2408.10441
14
  ---
15
 
16
  # ekk_latn_full
 
21
 
22
  Note: ekk_latn is an [individual language](https://iso639-3.sil.org/code_tables/639/data) code. Macrolanguage code est_latn (Estonian) is included in Goldfish. Consider using that model depending on your use case.
23
 
24
+ 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).
25
 
26
  Training code and sample usage: https://github.com/tylerachang/goldfish
27
 
 
31
 
32
  To access all Goldfish model details programmatically, see https://github.com/tylerachang/goldfish/blob/main/model_details.json.
33
  All models are trained with a [CLS] (same as [BOS]) token prepended, and a [SEP] (same as [EOS]) token separating sequences.
34
+ For best results, make sure that [CLS] is prepended to your input sequence (see sample usage linked above)!
35
  Details for this model specifically:
36
 
37
  * Architecture: gpt2
 
58
  author={Chang, Tyler A. and Arnett, Catherine and Tu, Zhuowen and Bergen, Benjamin K.},
59
  journal={Preprint},
60
  year={2024},
61
+ url={https://www.arxiv.org/abs/2408.10441},
62
  }
63
  ```