sshleifer / bb3b-tok

huggingface.co
Total runs: 4
24-hour runs: 0
7-day runs: 2
30-day runs: 0
Model's Last Updated: September 25 2020
translation

Introduction of bb3b-tok

Model Details of bb3b-tok

Blenderbot-3B

Model description

The abbreviation FSMT stands for FairSeqMachineTranslation

All four models are available:

Intended uses & limitations
How to use
from transformers.tokenization_fsmt import FSMTTokenizer
from transformers.modeling_fsmt import FSMTForConditionalGeneration
mname = "facebook/wmt19-en-ru"
tokenizer = FSMTTokenizer.from_pretrained(mname)
model = FSMTForConditionalGeneration.from_pretrained(mname)

input = "Machine learning is great, isn't it?"
input_ids = tokenizer.encode(input, return_tensors="pt")
outputs = model.generate(input_ids)
decoded = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(decoded) # Машинное обучение - это здорово, не так ли?
Limitations and bias
  • The original (and this ported model) doesn't seem to handle well inputs with repeated sub-phrases, content gets truncated
Training data

Pretrained weights were left identical to the original model released by fairseq. For more details, please, see the paper .

Eval results
pair fairseq transformers
en-ru 36.4 33.47

The score is slightly below the score reported by fairseq , since `transformers`` currently doesn't support:

  • model ensemble, therefore the best performing checkpoint was ported ( model4.pt ).
  • re-ranking

The score was calculated using this code:

git clone https://github.com/huggingface/transformers
cd transformers
export PAIR=en-ru
export DATA_DIR=data/$PAIR
export SAVE_DIR=data/$PAIR
export BS=8
export NUM_BEAMS=15
mkdir -p $DATA_DIR
sacrebleu -t wmt19 -l $PAIR --echo src > $DATA_DIR/val.source
sacrebleu -t wmt19 -l $PAIR --echo ref > $DATA_DIR/val.target
echo $PAIR
PYTHONPATH="src:examples/seq2seq" python examples/seq2seq/run_eval.py facebook/wmt19-$PAIR $DATA_DIR/val.source $SAVE_DIR/test_translations.txt --reference_path $DATA_DIR/val.target --score_path $SAVE_DIR/test_bleu.json --bs $BS --task translation --num_beams $NUM_BEAMS

note: fairseq reports using a beam of 50, so you should get a slightly higher score if re-run with --num_beams 50 .

Data Sources
BibTeX entry and citation info
@inproceedings{...,
  year={2020},
  title={Facebook FAIR's WMT19 News Translation Task Submission},
  author={Ng, Nathan and Yee, Kyra and Baevski, Alexei and Ott, Myle and Auli, Michael and Edunov, Sergey},
  booktitle={Proc. of WMT},
}
TODO
  • port model ensemble (fairseq uses 4 model checkpoints)

Runs of sshleifer bb3b-tok on huggingface.co

4
Total runs
0
24-hour runs
1
3-day runs
2
7-day runs
0
30-day runs

More Information About bb3b-tok huggingface.co Model

More bb3b-tok license Visit here:

https://choosealicense.com/licenses/apache-2.0

bb3b-tok huggingface.co

bb3b-tok huggingface.co is an AI model on huggingface.co that provides bb3b-tok's model effect (), which can be used instantly with this sshleifer bb3b-tok model. huggingface.co supports a free trial of the bb3b-tok model, and also provides paid use of the bb3b-tok. Support call bb3b-tok model through api, including Node.js, Python, http.

sshleifer bb3b-tok online free

bb3b-tok huggingface.co is an online trial and call api platform, which integrates bb3b-tok's modeling effects, including api services, and provides a free online trial of bb3b-tok, you can try bb3b-tok online for free by clicking the link below.

sshleifer bb3b-tok online free url in huggingface.co:

https://huggingface.co/sshleifer/bb3b-tok

bb3b-tok install

bb3b-tok is an open source model from GitHub that offers a free installation service, and any user can find bb3b-tok on GitHub to install. At the same time, huggingface.co provides the effect of bb3b-tok install, users can directly use bb3b-tok installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

bb3b-tok install url in huggingface.co:

https://huggingface.co/sshleifer/bb3b-tok

Url of bb3b-tok

Provider of bb3b-tok huggingface.co

sshleifer
ORGANIZATIONS

Other API from sshleifer

huggingface.co

Total runs: 39.6K
Run Growth: 4.5K
Growth Rate: 11.24%
Updated: May 23 2021
huggingface.co

Total runs: 39.2K
Run Growth: 27.1K
Growth Rate: 69.87%
Updated: August 26 2021
huggingface.co

Total runs: 9.6K
Run Growth: 2.1K
Growth Rate: 21.76%
Updated: May 13 2020
huggingface.co

Total runs: 3.1K
Run Growth: -777
Growth Rate: -23.42%
Updated: June 14 2021
huggingface.co

Total runs: 3
Run Growth: -1
Growth Rate: -33.33%
Updated: September 19 2020