ybracke commited on
Commit
f309b85
·
verified ·
1 Parent(s): f580828

Update README.md

Browse files

Update code section

Files changed (1) hide show
  1. README.md +7 -9
README.md CHANGED
@@ -34,26 +34,24 @@ We fine-tuned [google/byt5-small](https://huggingface.co/google/byt5-small) on a
34
 
35
  ```python
36
  from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
37
- from transformers.generation import GenerationConfig
38
  tokenizer = AutoTokenizer.from_pretrained("ybracke/transnormer-19c-beta-v02")
39
  model = AutoModelForSeq2SeqLM.from_pretrained("ybracke/transnormer-19c-beta-v02")
40
- gen_cfg = GenerationConfig.from_model_config(model.config)
41
- gen_cfg.max_new_tokens = 512
42
- sentence = ""
43
  inputs = tokenizer(sentence, return_tensors="pt",)
44
- outputs = model.generate(**inputs, generation_config=gen_cfg)
45
  print(tokenizer.batch_decode(outputs, skip_special_tokens=True))
46
- # >>> ['']
47
  ```
48
 
49
- Here is how to use this model with the [pipeline API](https://huggingface.co/transformers/main_classes/pipelines.html):
50
 
51
  ```python
52
  from transformers import pipeline
53
  transnormer = pipeline('text2text-generation', model='ybracke/transnormer-19c-beta-v02')
54
- sentence = ""
55
  print(transnormer(sentence))
56
- # >>> [{'generated_text': ''}]
57
  ```
58
 
59
  ## Intended uses & limitations
 
34
 
35
  ```python
36
  from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
37
+
38
  tokenizer = AutoTokenizer.from_pretrained("ybracke/transnormer-19c-beta-v02")
39
  model = AutoModelForSeq2SeqLM.from_pretrained("ybracke/transnormer-19c-beta-v02")
40
+ sentence = "Die Königinn ſaß auf des Pallaſtes mittlerer Tribune."
 
 
41
  inputs = tokenizer(sentence, return_tensors="pt",)
42
+ outputs = model.generate(**inputs, max_length=128)
43
  print(tokenizer.batch_decode(outputs, skip_special_tokens=True))
44
+ # >>> ['Die Königin saß auf des Palastes mittlerer Tribüne.']
45
  ```
46
 
47
+ Or use this model with the [pipeline API](https://huggingface.co/transformers/main_classes/pipelines.html) like this:
48
 
49
  ```python
50
  from transformers import pipeline
51
  transnormer = pipeline('text2text-generation', model='ybracke/transnormer-19c-beta-v02')
52
+ sentence = "Die Königinn ſaß auf des Pallaſtes mittlerer Tribune."
53
  print(transnormer(sentence))
54
+ # >>> [{'generated_text': 'Die Königin saß auf des Palastes mittlerer Tribüne.'}]
55
  ```
56
 
57
  ## Intended uses & limitations