IGEL: Instruction-tuned German large Language Model for Text
IGEL is an LLM model family developed for German. The first version of IGEL is built on top
BigScience BLOOM
,
adapted to
German from Malte Ostendorff
. IGEL is 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.
The IGEL family currently includes
instruct-igel-001
and
chat-igel-001
(coming soon)
.
Model Description
LoRA tuned
BLOOM-CLP German (6.4B parameters)
with merged weights. The
001
was designed as a naive test to determine whether it is possible to create an german instruction-tuned model using a small, undertrained LLM and a naive translated dataset. The goal of this test was to explore the potential of the BLOOM architecture for language modeling tasks that require instruction-based responses.
To achieve this goal, we used a pre-trained LLM model with limited training, and fine-tuned it using a dataset of naive translations of instruction-based content. The dataset was created by taking instructions in English and translating them into German using an automated translation tool. While this approach may introduce errors in the translated content, we wanted to test whether the model could still learn to generate instruction-based responses in a variety of languages.
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
Runs of philschmid instruct-igel-001 on huggingface.co
34
Total runs
0
24-hour runs
2
3-day runs
2
7-day runs
26
30-day runs
More Information About instruct-igel-001 huggingface.co Model
instruct-igel-001 huggingface.co is an AI model on huggingface.co that provides instruct-igel-001's model effect (), which can be used instantly with this philschmid instruct-igel-001 model. huggingface.co supports a free trial of the instruct-igel-001 model, and also provides paid use of the instruct-igel-001. Support call instruct-igel-001 model through api, including Node.js, Python, http.
instruct-igel-001 huggingface.co is an online trial and call api platform, which integrates instruct-igel-001's modeling effects, including api services, and provides a free online trial of instruct-igel-001, you can try instruct-igel-001 online for free by clicking the link below.
philschmid instruct-igel-001 online free url in huggingface.co:
instruct-igel-001 is an open source model from GitHub that offers a free installation service, and any user can find instruct-igel-001 on GitHub to install. At the same time, huggingface.co provides the effect of instruct-igel-001 install, users can directly use instruct-igel-001 installed effect in huggingface.co for debugging and trial. It also supports api for free installation.