chore: updating md files and credits

README.md

@@ -9,34 +9,43 @@ app_file: main.py
 pinned: true
 license: mit
 app_port: 8080
+models: microsoft/GODEL-v1_1-large-seq2seq
+tags: ["CHAT", "XAI", "SHAP", "GODEL", "Gradio"]
+disable_embedding: true
 ---
 
-# Bachelor Thesis
-## Webapp
-#### This is the ui showcase for my thesis about interpretability in a LLM based chatbot application and applications of XAI.
+# Bachelor Thesis Webapp
 
-## 🔗 Links:
+## 📜 Info:
+This is the ui showcase for my thesis about interpretability in a LLM based chatbot application and applications of XAI.
+
+### 🔗 Links:
 
 **[Github Repository](https://github.com/LennardZuendorf/thesis-webapp)**
-**[Huggingface Spaces Showcase](https://huggingface.co/spaces/lennardzuendorf/thesis-webapp-docker**
 
-## 🏗️ Tech Stack:
+**[Huggingface Spaces Showcase](https://huggingface.co/spaces/lennardzuendorf/thesis-webapp-docker)**
+
+### 🏗️ Tech Stack:
 
 **Language and Framework:** Python
 
 **Noteable Packages:** 🤗 Transformers, FastAPI, Gradio, SHAP, BERTViz
 
-## 👨‍💻 Author and Credits:</h2>
+## 👨‍💻 Author and Credits:
 
-**Author:** [@LennardZuendorf](https://github.com/LennardZuendorf)
+**Author: [@LennardZuendorf](https://github.com/LennardZuendorf)**
 
-**Thesis Supervisor**: [Prof. Dr. Simbeck](https://www.htw-berlin.de/hochschule/personen/person/?eid=9862)
+**Thesis Supervisor: [Prof. Dr. Simbeck](https://www.htw-berlin.de/hochschule/personen/person/?eid=9862)**
 <br> Second Corrector: [Prof. Dr. Hochstein](https://www.htw-berlin.de/hochschule/personen/person/?eid=10628)
 
-See code for in detailed credits, work is based on
+See code for in detailed credits, work is strongly based on:
+#### GODEL
+- [HGF Model Page](https://huggingface.co/microsoft/GODEL-v1_1-large-seq2seq?text=Hey+my+name+is+Mariama%21+How+are+you%3F)
+- [Paper on HGF](https://huggingface.co/papers/2206.11309)
+- [Paper Print](https://arxiv.org/abs/2206.11309)
 
-- GODEL:
-- SHAP:
-- BERTViz:
+#### SHAP
+- [Github](https://github.com/shap/shap)
+- [Inital Paper](https://arxiv.org/abs/1705.07874)
 
 This Project was part of my studies of Business Computing at University of Applied Science for Technology and Business Berlin (HTW Berlin).

main.py

@@ -60,7 +60,7 @@ with gr.Blocks(
         # markdown component to display the header
         gr.Markdown("""
             # Thesis Demo - AI Chat Application with GODEL
-            ## Interpretability powered by SHAP and BERTVIZ
+            Interpretability powered by shap and attention visualization,
             ### Select between tabs below for the different views.
             """)
     # ChatBot tab used to chat with the AI chatbot

public/about.md

@@ -8,14 +8,13 @@ This research tackles the rise of LLM based applications such a chatbots and exp
 
 - [GitHub Repository](https://github.com/LennardZuendorf/thesis-webapp) - The GitHub repository of this project.
 - [HTW Berlin](https://www.htw-berlin.de/) - The University I have built this project for, as part of my thesis.
-- [Thesis Print]() - Link to the thesis pdf (in English), containing more information about the project. And a full list of sources for this work as well as additional evaluations and fundamental information for the project.
 
 
 ## Implementation
 
-This project is an implementation of PartitionSHAP and BERTViz into GODEL by Microsoft - [GODEL Model](https://huggingface.co/microsoft/GODEL-v1_1-large-seq2seq) which is a generative seq2seq transformer fine-tuned for goal directed dialog. It supports context and knowledge base inputs.
+This project is an implementation of PartitionSHAP into GODEL by Microsoft - [GODEL Model](https://huggingface.co/microsoft/GODEL-v1_1-large-seq2seq) which is a generative seq2seq transformer fine-tuned for goal directed dialog. It supports context and knowledge base inputs.
 
-The UI is build with Gradio.
+The UI is build with Gradio, utilizing some custom components and FastAPI.
 
 ### Usage
 
@@ -39,13 +38,13 @@ Please credit the original authors of this project (Lennard Zündorf) and the cr
 ### Author
 
 - Lennard Zündorf
-- lennard.zuendorf@student.htw-berlin.de
-- [GitHub](https://github.com/LennardZuendorf)
-- [LinkedIn](https://www.zuendorf.me/linkd)
+- [lennard.zuendorf@student.htw-berlin.de](mailto:lennard.zuendorf@student.htw-berlin.de) or [lennard@zuendorf.me](mailto:lennard@zuendorf.me)
+- [GitHub](https://zuendorf.me/github)
+- [LinkedIn](https://zuendorf.me/github)
 
 
 ### University
 Hochschule für Technik und Wirtschaft Berlin (HTW Berlin) - University of Applied Sciences for Engineering and Economics Berlin
 
-1. Supervisor: Prof. Dr. Katarina Simbeck
-2. Supervisor: Prof. Dr. Axel Hochstein
+Supervisor: Prof. Dr. Katarina Simbeck
+2. Corrector : Prof. Dr. Axel Hochstein

public/credits_dataprotection_license.md

@@ -1,7 +1,4 @@
-
-
 # Credits
-For full credits, please refer to the [thesis print]()
 
 ### Models
 This implementation is build on GODEL by Microsoft, Inc.
@@ -10,7 +7,7 @@ This implementation is build on GODEL by Microsoft, Inc.
 GODEL is an open source model by Microsoft. See [offical paper](https://arxiv.org/abs/2206.11309) for more information.
 
 - the version used in this project is GODEL Large, see [huggingface model hub](https://huggingface.co/microsoft/GODEL-v1_1-large-seq2seq?text=Hey+my+name+is+Thomas%21+How+are+you%3F)
-- the model as is a generative seq2seq transformer fine tuned for goal directed dialog
+- the model as is a generative seq2seq transformer fine-tuned for goal directed dialog
 - it supports context and knowledge base inputs
 
 ### Libraries
@@ -19,14 +16,14 @@ This project uses a number of open source libraries, only the most important one
 ##### Shap
 This application uses a custom version of the shap library, which is available at [GitHub](https://github.com/shap/shap).
 
-- please refer to the [thesis-custom-shap](https://github.com/LennardZuendorf/thesis-custom-shap) repository for more information about the changes made to the library, specifically the README and CHANGES files
-- the shap library and the used partition SHAP explainer are based on work by Lundberg et al. (2017), see [offical paper](https://arxiv.org/pdf/1705.07874.pdf) for more information
+- Please refer to the [thesis-shap](https://github.com/LennardZuendorf/thesis-custom-shap) repository for more information about the changes made to the library, specifically the README file.
+- The shap library and the used partition SHAP explainer are based on work by Lundberg et al. (2017), see [offical paper](https://arxiv.org/pdf/1705.07874.pdf) for more information.
 
-##### BertViz
-This application uses a slightly customized version of the bertviz library, which is available at [GitHub](https://github.com/jessevig/bertviz)
+##### Visualizations
+This application uses attention visualization inspired by the bertviz library, which is available at[GitHub](https://github.com/jessevig/bertviz). It doesn't actually use BERTViz.
 
-- the bertviz was introduced by Vig et al. (2019), see [offical paper](https://arxiv.org/pdf/1906.05714.pdf) for more information
-- there are no changes to the library itself, only to the way it is used in this project (adapted to use Mistral/LlaMa 2 instead of BERT)
+- The bertviz was introduced by Vig et al. (2019), see [offical paper](https://arxiv.org/pdf/1906.05714.pdf) for more information.
+- This project only uses cross attention visualization with gradio and matplotlib.
 
 
 # Data Protection