Update README.md
Browse files
README.md
CHANGED
@@ -4,6 +4,7 @@ datasets:
|
|
4 |
- OpenAssistant/oasst1
|
5 |
- LEL-A/translated_german_alpaca_validation
|
6 |
- deepset/germandpr
|
|
|
7 |
language:
|
8 |
- de
|
9 |
pipeline_tag: conversational
|
@@ -14,13 +15,15 @@ pipeline_tag: conversational
|
|
14 |
Base model: [malteos/bloom-6b4-clp-german](https://huggingface.co/malteos/bloom-6b4-clp-german) [(Ostendorff and Rehm, 2023)](https://arxiv.org/abs/2301.09626)
|
15 |
|
16 |
Trained on:
|
17 |
-
- 20B additional German tokens
|
18 |
- [OpenAssistant/oasst1](https://huggingface.co/datasets/OpenAssistant/oasst1) (German subset)
|
19 |
- [LEL-A/translated_german_alpaca_validation](https://huggingface.co/datasets/LEL-A/translated_german_alpaca_validation)
|
20 |
- [LEL-A's version of deepset/germandpr](https://github.com/LEL-A/EuroInstructProject#instruct-germandpr-dataset-v1-german)
|
21 |
|
22 |
## Chat demo
|
23 |
|
|
|
|
|
24 |
[https://opengptx.dfki.de/chat/](https://opengptx.dfki.de/chat/)
|
25 |
|
26 |
Please note that this a research prototype and may not be suitable for extensive use.
|
@@ -44,3 +47,9 @@ If you are using our code or models, please cite [our paper](https://arxiv.org/a
|
|
44 |
## License
|
45 |
|
46 |
[BigScience BLOOM RAIL 1.0](https://bigscience.huggingface.co/blog/the-bigscience-rail-license)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
4 |
- OpenAssistant/oasst1
|
5 |
- LEL-A/translated_german_alpaca_validation
|
6 |
- deepset/germandpr
|
7 |
+
- oscar-corpus/OSCAR-2301
|
8 |
language:
|
9 |
- de
|
10 |
pipeline_tag: conversational
|
|
|
15 |
Base model: [malteos/bloom-6b4-clp-german](https://huggingface.co/malteos/bloom-6b4-clp-german) [(Ostendorff and Rehm, 2023)](https://arxiv.org/abs/2301.09626)
|
16 |
|
17 |
Trained on:
|
18 |
+
- 20B additional German tokens (Wikimedia dumps and OSCAR 2023)
|
19 |
- [OpenAssistant/oasst1](https://huggingface.co/datasets/OpenAssistant/oasst1) (German subset)
|
20 |
- [LEL-A/translated_german_alpaca_validation](https://huggingface.co/datasets/LEL-A/translated_german_alpaca_validation)
|
21 |
- [LEL-A's version of deepset/germandpr](https://github.com/LEL-A/EuroInstructProject#instruct-germandpr-dataset-v1-german)
|
22 |
|
23 |
## Chat demo
|
24 |
|
25 |
+
[![Try out the chat demo](https://huggingface.co/malteos/bloom-6b4-clp-german-oasst-v0.1/resolve/main/chat-demo.png)](https://opengptx.dfki.de/chat/)
|
26 |
+
|
27 |
[https://opengptx.dfki.de/chat/](https://opengptx.dfki.de/chat/)
|
28 |
|
29 |
Please note that this a research prototype and may not be suitable for extensive use.
|
|
|
47 |
## License
|
48 |
|
49 |
[BigScience BLOOM RAIL 1.0](https://bigscience.huggingface.co/blog/the-bigscience-rail-license)
|
50 |
+
|
51 |
+
|
52 |
+
## Acknowledgements
|
53 |
+
|
54 |
+
This model was trained during the [Helmholtz GPU Hackathon 2023](https://www.fz-juelich.de/de/ias/jsc/aktuelles/termine/2023/helmholtz-gpu-hackathon-2023).
|
55 |
+
We gratefully thank the organizers for hosting this event and the provided computing resources.
|