Hugging Face's logo

leukas
/
byt5-large-wmt14-deen

Translation
Transformers
PyTorch
German
English
t5
text2text-generation
Eval Results
text-generation-inference
Inference Endpoints
Model card Files Community
1
byt5-large-wmt14-deen / README.md
leukas's picture
leukas
Add evaluation results on the de-en config and test split of wmt14 (#1)
0eee8df verified
preview code
|
raw
history blame contribute delete
No virus
1.96 kB
metadata
language:
  - de
  - en
datasets:
  - wmt14
pipeline_tag: translation
model-index:
  - name: leukas/byt5-large-wmt14-deen
    results:
      - task:
          type: translation
          name: Translation
        dataset:
          name: wmt14
          type: wmt14
          config: de-en
          split: test
        metrics:
          - type: bleu
            value: 0.236
            name: BLEU
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZTI1MzQ4NzYxMGExODRhYTk0NzY5MDcxOWZjOTJhY2ZkMWU3ZTM0NmNlMzI4ZDAyYTEwYzdjMzI3MmY1NzYzZCIsInZlcnNpb24iOjF9.0kBCKKpU8CUzcUWi9y9gFZn__j6bbsiukUBiKFmMbwtwaZSAsc25_hGsHLe3bnwQWJxov7_lGDXX9DK6XNiIAQ
          - type: loss
            value: 0.3008817732334137
            name: loss
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMzIyM2I2Yjg1NWQ2NjEzOTAwN2NlNDc3NWU4NmI3ZDFhYzZlMTQyNjZlMWM0Njg5YWIzMmI5MzBjN2Y3NmMzYSIsInZlcnNpb24iOjF9.2totcDoHCyf7N9xaqAFVqlyuaoHM3hRIH5jmP4kPoD0crEcPZ0re6pg10_2Uoud4YunWMRvOpUTt8lk2cCM1BA
          - type: gen_len
            value: 20
            name: gen_len
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNzdjODYyY2UxZGZjNmFmZGFlY2IzNzQxNzA3YjQ3MDg1OWY3YjdkMzM2NGI2Njk2ZDczODNlOWM4YjZjZDQ2MCIsInZlcnNpb24iOjF9.hRVI7QHiBlX3Yp0cFOdezmoxV6CTq20vzp8IzugYc0uTUVD5OAvcBVRLZERGoNR1b1Oi2FV3trQvDWXUQZnsAQ

byt5-large-wmt14-deen

This model is released as part of the work from Are Character-level Translations Worth the Wait? Comparing Character- and Subword-level Models for Machine Translation. It is a ByT5 model finetuned on German-->English translation the WMT14 dataset.

To use the model correctly, you must prepend the prompt with "translate X to Y: ", where X and Y are your source and target languages (e.g. German, English).

NOTE: The decoder_start_token_id is 259 for byt5 models and 250099 for mt5 models, which is different from the default token from google's byt5 and mt5 models (which is 0).