goldfish-models commited on
Commit
e6a0049
1 Parent(s): b55eb49

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +4 -2
README.md CHANGED
@@ -9,7 +9,7 @@ library_name: transformers
9
  pipeline_tag: text-generation
10
  tags:
11
  - goldfish
12
-
13
  ---
14
 
15
  # eng_latn_1000mb
@@ -20,7 +20,7 @@ The Goldfish models are trained primarily for comparability across languages and
20
 
21
  Note: eng_latn is an [individual language](https://iso639-3.sil.org/code_tables/639/data) code. It is not contained in any macrolanguage codes contained in Goldfish (for script latn).
22
 
23
- 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).
24
 
25
  Training code and sample usage: https://github.com/tylerachang/goldfish
26
 
@@ -30,6 +30,7 @@ Sample usage also in this Google Colab: [link](https://colab.research.google.com
30
 
31
  To access all Goldfish model details programmatically, see https://github.com/tylerachang/goldfish/blob/main/model_details.json.
32
  All models are trained with a [CLS] (same as [BOS]) token prepended, and a [SEP] (same as [EOS]) token separating sequences.
 
33
  Details for this model specifically:
34
 
35
  * Architecture: gpt2
@@ -55,5 +56,6 @@ If you use this model, please cite:
55
  author={Chang, Tyler A. and Arnett, Catherine and Tu, Zhuowen and Bergen, Benjamin K.},
56
  journal={Preprint},
57
  year={2024},
 
58
  }
59
  ```
 
9
  pipeline_tag: text-generation
10
  tags:
11
  - goldfish
12
+ - arxiv:2408.10441
13
  ---
14
 
15
  # eng_latn_1000mb
 
20
 
21
  Note: eng_latn is an [individual language](https://iso639-3.sil.org/code_tables/639/data) code. It is not contained in any macrolanguage codes contained in Goldfish (for script latn).
22
 
23
+ 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).
24
 
25
  Training code and sample usage: https://github.com/tylerachang/goldfish
26
 
 
30
 
31
  To access all Goldfish model details programmatically, see https://github.com/tylerachang/goldfish/blob/main/model_details.json.
32
  All models are trained with a [CLS] (same as [BOS]) token prepended, and a [SEP] (same as [EOS]) token separating sequences.
33
+ For best results, make sure that [CLS] is prepended to your input sequence (see sample usage linked above)!
34
  Details for this model specifically:
35
 
36
  * Architecture: gpt2
 
56
  author={Chang, Tyler A. and Arnett, Catherine and Tu, Zhuowen and Bergen, Benjamin K.},
57
  journal={Preprint},
58
  year={2024},
59
+ url={https://www.arxiv.org/abs/2408.10441},
60
  }
61
  ```