sagawa commited on
Commit
223ef97
·
verified ·
1 Parent(s): 5c12863

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -3
README.md CHANGED
@@ -12,7 +12,7 @@ metrics:
12
  - accuracy
13
  ---
14
 
15
- # Model Card for ReactionT5-forward-v2
16
 
17
  This is a ReactionT5 pre-trained to predict the products of reactions. You can use the demo [here](https://huggingface.co/spaces/sagawa/ReactionT5_task_forward).
18
 
@@ -38,8 +38,8 @@ Use the code below to get started with the model.
38
  ```python
39
  from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
40
 
41
- tokenizer = AutoTokenizer.from_pretrained("sagawa/ReactionT5-forward-v2", return_tensors="pt")
42
- model = AutoModelForSeq2SeqLM.from_pretrained("sagawa/ReactionT5-forward-v2")
43
 
44
  inp = tokenizer('REACTANT:COC(=O)C1=CCCN(C)C1.O.[Al+3].[H-].[Li+].[Na+].[OH-]REAGENT:C1CCOC1', return_tensors='pt')
45
  output = model.generate(**inp, num_beams=1, num_return_sequences=1, return_dict_in_generate=True, output_scores=True)
 
12
  - accuracy
13
  ---
14
 
15
+ # Model Card for ReactionT5v2-forward
16
 
17
  This is a ReactionT5 pre-trained to predict the products of reactions. You can use the demo [here](https://huggingface.co/spaces/sagawa/ReactionT5_task_forward).
18
 
 
38
  ```python
39
  from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
40
 
41
+ tokenizer = AutoTokenizer.from_pretrained("sagawa/ReactionT5v2-forward", return_tensors="pt")
42
+ model = AutoModelForSeq2SeqLM.from_pretrained("sagawa/ReactionT5v2-forward")
43
 
44
  inp = tokenizer('REACTANT:COC(=O)C1=CCCN(C)C1.O.[Al+3].[H-].[Li+].[Na+].[OH-]REAGENT:C1CCOC1', return_tensors='pt')
45
  output = model.generate(**inp, num_beams=1, num_return_sequences=1, return_dict_in_generate=True, output_scores=True)