screemix commited on
Commit
d1deae6
1 Parent(s): 4b747b7

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -5
README.md CHANGED
@@ -28,9 +28,8 @@ To evaluate the model, we sample 50 times from the decoder for each input and th
28
  One can load this model for their personal use of fine-tuning as follows:
29
 
30
  ```python
31
- # Load model directly
32
- from transformers import AutoModel, AutoTokenizer
33
- tokenizer = AutoTokenizer.from_pretrained("t5-small")
34
- tokenizer.add_special_tokens({'sep_token': '[SEP]'})
35
- model = AutoModel.from_pretrained("DeepPavlov/t5-wikidata5M-with-neighbors")
36
  ```
 
28
  One can load this model for their personal use of fine-tuning as follows:
29
 
30
  ```python
31
+ from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
32
+
33
+ tokenizer = AutoTokenizer.from_pretrained("DeepPavlov/t5-wikidata5M-with-neighbors")
34
+ model = AutoModelForSeq2SeqLM.from_pretrained("DeepPavlov/t5-wikidata5M-with-neighbors")
 
35
  ```