mdm-code commited on
Commit
50b114e
1 Parent(s): 4471561

Update readme

Browse files
Files changed (1) hide show
  1. README.md +8 -7
README.md CHANGED
@@ -3,6 +3,7 @@ license: gpl-3.0
3
  ---
4
 
5
  [MANX](https://github.com/mdm-code/manx)
 
6
 
7
  This is a ByT5-small model fine-tuned for early Middle English lemmatization.
8
  This is a PoC. The model has been fed series of 11-grams extracted from eLAEME
@@ -11,14 +12,14 @@ lemmatizer for all sorts of Middle English texts because eLAEME employes bespoke
11
  transcription rules that diverge from your regular transcript rules.
12
 
13
  The `manx` package that you can use the model with can be found here:
14
- `https://github.com/mdm-code/manx`. The package will give a more in-depth look
15
  at the data used to fine-tune the model. It lets you download corpus files, parse
16
  them and get them ready for fine-tuning the base model checkpoint.
17
- It has links to Colab notebooks and ready-made API that lets you feed
18
  texts to have them lemmatized.
19
 
20
- Make sure to reference this Huggingface repository (`https://huggingface.co/mdm-code/me-lemmatize-byt5-small`)
21
- and the Github repository (`https://github.com/mdm-code/manx`) for
22
- `manx` whenever you use this model for your own research. The model and package
23
- are published under the GPL-3 license, so make sure any research output and codebase
24
- are made publicly available. Do not violate this license.
 
3
  ---
4
 
5
  [MANX](https://github.com/mdm-code/manx)
6
+ [Colab Notebook](https://colab.research.google.com/drive/1qpd4F8BoHMGzZnSqrGxZe-1YyX9IhVHc?usp=sharing)
7
 
8
  This is a ByT5-small model fine-tuned for early Middle English lemmatization.
9
  This is a PoC. The model has been fed series of 11-grams extracted from eLAEME
 
12
  transcription rules that diverge from your regular transcript rules.
13
 
14
  The `manx` package that you can use the model with can be found here:
15
+ `https://github.com/mdm-code/manx`. The package will give a more general look
16
  at the data used to fine-tune the model. It lets you download corpus files, parse
17
  them and get them ready for fine-tuning the base model checkpoint.
18
+ It has links to Colab notebook and ready-made API that lets you feed
19
  texts to have them lemmatized.
20
 
21
+ Make sure to reference this Huggingface repository
22
+ (`https://huggingface.co/mdm-code/me-lemmatize-byt5-small`) and the Github
23
+ repository (`https://github.com/mdm-code/manx`) for `manx` whenever you use
24
+ this model for your own research. The model and package are published under the
25
+ GPL-3 license.