Streamlit App for Chatbot creation using EMGerman LLama 2 model
This repo is designed for the Streamlit Web application for EMGerman LLama 2 model. Using Streamlit, one can easily create a prototype to test different ideas/approaches and also use it for the showcase of these ideas to bigger audience.
Most of contemporary custom LLMs were trained using mostly textual information in English and EMGerman is one of the few current custom models that was trained on German text corpus and therefore achieves really good results in different tasks such as Text Generation and named entity recognition (NER).
Streamlit: https://streamlit.io/
EMGerman: https://github.com/jphme/EM_German
LLama2 Paper: https://arxiv.org/abs/2307.09288
To run the app all you need is:
git clone https://github.com/ds-muzalevskiy/EMGerman-LLama-Streamlit-Chatbot.git
cd EMGerman-LLama-Streamlit-Chatbot-main
python -m venv venv
source venv/bin/activate
pip install -r requirements.txt
streamlit run app.py
If everything went fine, you should be able to see similar screen and have a chance to interact with the app :)
7 commits
Python
91.2%
Dockerfile
8.8%
Streamlit App for Chatbot creation using EMGerman LLama 2 model
This repo is designed for the Streamlit Web application for EMGerman LLama 2 model. Using Streamlit, one can easily create a prototype to test different ideas/approaches and also use it for the showcase of these ideas to bigger audience.
Most of contemporary custom LLMs were trained using mostly textual information in English and EMGerman is one of the few current custom models that was trained on German text corpus and therefore achieves really good results in different tasks such as Text Generation and named entity recognition (NER).
Streamlit: https://streamlit.io/
EMGerman: https://github.com/jphme/EM_German
LLama2 Paper: https://arxiv.org/abs/2307.09288
To run the app all you need is:
git clone https://github.com/ds-muzalevskiy/EMGerman-LLama-Streamlit-Chatbot.git
cd EMGerman-LLama-Streamlit-Chatbot-main
python -m venv venv
source venv/bin/activate
pip install -r requirements.txt
streamlit run app.py
If everything went fine, you should be able to see similar screen and have a chance to interact with the app :)
7 commits
Python
91.2%
Dockerfile
8.8%