Downloads · 30 days
74
2% of all-time downloads
bloom-6b4-clp-german-oasst-v0.1
malteos/bloom-6b4-clp-german-oasst-v0.1
bloom-6b4-clp-german-oasst-v0.1 is a text generation model from malteos. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as bigscience-bloom-rail-1.0.
Base model: malteos/bloom-6b4-clp-german (Ostendorff and Rehm, 2023)
All-time downloads
3.6K
Public
Parameters
6.5B
25.8 GB on disk
Likes
8
Public
Repo makeup
Click a slice to open those files.
.bin12.9 GB · 50%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- bigscience-bloom-rail-1.0
- Model type
- bloom
- Access
- Public
- Created
- May 11, 2023
- Updated
- Nov 4, 2024
- SHA
- d10bdd31
Model card
From the Hugging Face model README
Instruction-fine-tuned German language model (6B parameters; early alpha version)
Base model: malteos/bloom-6b4-clp-german (Ostendorff and Rehm, 2023)
Trained on:
- 20B additional German tokens (Wikimedia dumps and OSCAR 2023)
- OpenAssistant/oasst1 (German subset)
- LEL-A/translated_german_alpaca_validation
- LEL-A's version of deepset/germandpr
Chat demo
https://opengptx.dfki.de/chat/
Please note that this a research prototype and may not be suitable for extensive use.
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}
}
License
Acknowledgements
This model was trained during the Helmholtz GPU Hackathon 2023. We gratefully thank the organizers for hosting this event and the provided computing resources.
- Task
- Text Generation
- Library
- transformers
- Type
- bloom
- License
- bigscience-bloom-rail-1.0
- Languages
- de
- Created
- May 11, 2023
- Updated
- Nov 4, 2024