|
--- |
|
language: |
|
- de |
|
pipeline_tag: text-generation |
|
library_name: transformers |
|
tags: |
|
- bloom |
|
- LLM |
|
inference: false |
|
widget: |
|
- text: "TODO" |
|
--- |
|
|
|
<div style="text-align:center;width:250px;height:250px;"> |
|
<img src="https://huggingface.co/philschmid/instruct-igel-001/resolve/main/assets/igel_removedbg.png" alt="IGEL logo""> |
|
</div> |
|
|
|
|
|
|
|
# IGEL: Instruction-tuned German large Language Model for Text |
|
|
|
IGEL is a LLM model family developed for German. The first version of IGEL is built on top [BigScience BLOOM](https://bigscience.huggingface.co/blog/bloom) adapted to [German from Malte Ostendorff](https://huggingface.co/malteos/bloom-6b4-clp-german). IGEL designed to provide accurate and reliable language understanding capabilities for a wide range of natural language understanding tasks, including sentiment analysis, language translation, and question answering. |
|
|
|
### You can try out the model at [igel-playground](). |
|
|
|
The IGEL family includes instruction `instruct-igel-001` and `chat-igel-001` _coming soon_. |
|
|
|
|
|
## Model Description |
|
|
|
LoRA tuned [BLOOM-CLP German (6.4B parameters)](https://huggingface.co/malteos/bloom-6b4-clp-german) with merged weights. |
|
|
|
## Training data |
|
|
|
`instruct-igel-001` is trained on naive translated instruction datasets, without much post-processing. |
|
|
|
### Known limitations |
|
|
|
`instruct-igel-001` also exhibits several common deficiencies of language models, including hallucination, toxicity, and stereotypes. |
|
|
|
For example, in the following figure, `instruct-igel-001` wrongly says that the cancelor of Germany is Angela Merkel. |
|
|
|
 |
|
|
|
|
|
### Training procedure |
|
|
|
_coming soon_ |
|
|
|
## How to use |
|
|
|
You can test the model in this LLM playground. |
|
|
|
_coming soon_ |
|
|
