metadata
language:
- de
license: bigscience-bloom-rail-1.0
library_name: transformers
tags:
- ggml
- bloom
datasets:
- oscar
pipeline_tag: text-generation
BLOOM-CLP German (6.4B parameters)
This is a monolingual German language model trained using the CLP-Transfer method based on BLOOM-7b1.
You can try out the model at European Language Grid.
How to use
You can use this model directly with a pipeline for text generation. Since the generation relies on some randomness, we set a seed for reproducibility:
>>> from transformers import pipeline, set_seed
>>> generator = pipeline('text-generation', model='malteos/bloom-6b4-clp-german')
>>> set_seed(42)
>>> generator("Hello, I'm a language model,", max_length=30, num_return_sequences=3)
[{'generated_text': "Hello, I'm a language model, a language for thinking, a language for expressing thoughts."},
{'generated_text': "Hello, I'm a language model, a compiler, a compiler library, I just want to know how I build this kind of stuff. I don"},
{'generated_text': "Hello, I'm a language model, and also have more than a few of your own, but I understand that they're going to need some help"},]
Training dataset
- ca. 50B German tokens
- Web-crawled content from the German subset OSCAR v22.01 (excluding content tagged as header, footer, noisy, or adult)
- Web-crawled content from the GC4 Corpus (including only the head and middle parts)
- Both Web-crawled datasets are deduplicated with Google's suffix array implementation
- German court decisions from Open Legal Data
Code
Hardware
- 32xA100-40GB GPUs
- 12.5 days
- Tensorboard logs
Evaluation
Validation PPL compared to from-scratch training (the lower the better):
Additional evaluations can be found in our paper.
How to cite
If you are using our code or models, please cite our paper:
@misc{Ostendorff2023clp,
doi = {10.48550/ARXIV.2301.09626},
author = {Ostendorff, Malte and Rehm, Georg},
title = {Efficient Language Model Training through Cross-Lingual and Progressive Transfer Learning},
publisher = {arXiv},
year = {2023}
}