license: apache-2.0
datasets:
- oscar-corpus/OSCAR-2109
language:
- en
- pl
pipeline_tag: text-generation
library_name: transformers
B-GPT_en_pl_simultaneous
This is a bilingual GPT-2 style model. For the first half of training, this model was trained only on English data. In the second half of training, the model was trained on a 50%-50% mix of English and Polish data. At the end of training, 75% of training data seen by the model is English and 25% is Polish. The tokenizer was trained on the same overall proportions of data as the language model at the final step.
Model details:
All models are trained with a [CLS] (same as [BOS]) token prepended, and a [SEP] (same as [EOS]) token separating sequences. For best results, make sure that [CLS] is prepended to your input sequence (see sample usage linked above)! Details for this model specifically:
- Architecture: gpt2
- Parameters: 124770816
- Maximum sequence length: 512 tokens
- Training tokens: 12B
- Vocabulary size: 50000
- Compute cost: ~9 NVIDIA A6000 GPU hours
- CO2 Emission: 1.17 kg
Training dataset: OSCAR 2021/09
Checkpoints are taken at training steps: 0, 10000, 20000, 30000, 40000, 50000, 64000, 64010, 64020, 64030, 64040, 64050, 64060, 64070, 64080, 64090, 64100, 64110, 64120, 64130, 64140, 64150, 64160, 64170, 64180, 64190, 64200, 64300, 64400, 64500, 64600, 64700, 64800, 64900, 65000, 66000, 67000, 68000, 69000, 70000, 80000, 90000, 100000, 110000, 120000, 128000.
Use This Model
Load the model:
Note: if you do not specify a revision, it will load the final checkpoint of the model. See above for the list of checkpoints. The checkpoint step is the name of the revision.
from transformers import AutoTokenizer, AutoModel
tokenizer = AutoTokenizer.from_pretrained("catherinearnett/B-GPT_en_pl_simultaneous")
model = AutoModel.from_pretrained("catherinearnett/B-GPT_en_pl_simultaneous", revision = "128000")
Text Generation:
from transformers import pipeline
pipe = pipeline("text-generation", model="catherinearnett/B-GPT_en_pl_simultaneous")
pipe("I am a")
Citation
If you use this model, please cite: