Korventenn commited on
Commit
c5d7feb
1 Parent(s): 6bd39cf

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -16,7 +16,7 @@ language:
16
  This model has been optimized for French and English language processing while minimizing overall size. To achieve this, I only retained relevant parameters and tokens specific to these two languages, ensuring that performance remains as good as the original mt5.
17
 
18
  ## Model Details
19
- I used a method outlined in a [blog post](https://towardsdatascience.com/how-to-adapt-a-multilingual-t5-model-for-a-single-language-b9f94f3d9c90) by David Dale to downsize the multilingual T5 model for French and English use cases specifically. By utilizing the giga_fren dataset, I was able to successfully reduce the total number of tokens and decrease both the model and tokenizer sizes by 38% and 80% respectively.
20
 
21
  ### Model Description
22
 
@@ -24,7 +24,7 @@ I used a method outlined in a [blog post](https://towardsdatascience.com/how-to-
24
  - **Model type:** mt5
25
  - **Language(s) (NLP):** French and English
26
  - **License:** Apache 2.0
27
- - **Generated from model:** mt5-large
28
 
29
  ### Model Sources [optional]
30
 
 
16
  This model has been optimized for French and English language processing while minimizing overall size. To achieve this, I only retained relevant parameters and tokens specific to these two languages, ensuring that performance remains as good as the original mt5.
17
 
18
  ## Model Details
19
+ I used a method outlined in a [blog post](https://towardsdatascience.com/how-to-adapt-a-multilingual-t5-model-for-a-single-language-b9f94f3d9c90) by David Dale to downsize the multilingual T5 model for French and English use cases specifically. By utilizing the giga_fren dataset, I was able to successfully reduce the total number of tokens and decrease both the model and tokenizer sizes by 67% and 80% respectively.
20
 
21
  ### Model Description
22
 
 
24
  - **Model type:** mt5
25
  - **Language(s) (NLP):** French and English
26
  - **License:** Apache 2.0
27
+ - **Generated from model:** mt5-small
28
 
29
  ### Model Sources [optional]
30