gardari commited on
Commit
255b90a
·
verified ·
1 Parent(s): 7163f3d

Update README.md to reflect easier fix for tokenizer bug

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -16,7 +16,7 @@ To run the model you will need a python3 environment. Install the required depen
16
 
17
  > pip install -r requirements.txt
18
 
19
- The current version of transformers includes a bug which has to be fixed in the user's environment before the model can be run. To fix it, change "gpt-sw3-7b" in line no. 138 in transformers/models/gpt_sw3/tokenization_gpt_sw3.py to "gpt-sw3-6.7b".
20
 
21
  The model is fine-tuned on the following three tasks. Output examples for each task are shown in ./example_outputs.
22
  - Task 1: The model evaluates one text with regards to e.g. grammar and spelling, and returns all errors in the input text as a list, with their position in the text and their corrections.
 
16
 
17
  > pip install -r requirements.txt
18
 
19
+ The current version of transformers includes a bug in the GPTSw3Tokenizer class which causes it to use the wrong BOS and PAD tokens if the tokenizer is loaded through `AI-Sweden-Models/gpt-sw3-6.7b`. Load the tokenizer through `mideind/icelandic-gpt-sw3-6.7b` instead to avoid this bug.
20
 
21
  The model is fine-tuned on the following three tasks. Output examples for each task are shown in ./example_outputs.
22
  - Task 1: The model evaluates one text with regards to e.g. grammar and spelling, and returns all errors in the input text as a list, with their position in the text and their corrections.