Harsh Trivedi commited on
Commit
8e97603
1 Parent(s): a161ee5
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -30,7 +30,7 @@ Please checkout the details in our [github repository](https://github.com/stonyb
30
  from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
31
  from digit_tokenization import enable_digit_tokenization # digit_tokenization.py from https://github.com/stonybrooknlp/teabreac
32
 
33
- model_name = "poet-large-iirc-retrieved"
34
  tokenizer = AutoTokenizer.from_pretrained(model_name, use_fast=False) # Fast doesn't work with digit tokenization
35
  model = AutoModelForSeq2SeqLM.from_pretrained(model_name)
36
  enable_digit_tokenization(tokenizer)
@@ -43,7 +43,7 @@ input_ids = tokenizer(
43
  input_texts, return_tensors="pt",
44
  truncation=True, max_length=800,
45
  add_special_tokens=True, padding=True,
46
- )
47
  generated_ids = model.generate(input_ids, min_length=1, max_length=50)
48
  generated_predictions = tokenizer.batch_decode(generated_ids, skip_special_tokens=False)
49
  generated_predictions = [
 
30
  from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
31
  from digit_tokenization import enable_digit_tokenization # digit_tokenization.py from https://github.com/stonybrooknlp/teabreac
32
 
33
+ model_name = "StonyBrookNLP/poet-large-iirc-retrieved"
34
  tokenizer = AutoTokenizer.from_pretrained(model_name, use_fast=False) # Fast doesn't work with digit tokenization
35
  model = AutoModelForSeq2SeqLM.from_pretrained(model_name)
36
  enable_digit_tokenization(tokenizer)
 
43
  input_texts, return_tensors="pt",
44
  truncation=True, max_length=800,
45
  add_special_tokens=True, padding=True,
46
+ )["input_ids"]
47
  generated_ids = model.generate(input_ids, min_length=1, max_length=50)
48
  generated_predictions = tokenizer.batch_decode(generated_ids, skip_special_tokens=False)
49
  generated_predictions = [