added uv

README.md

@@ -12,3 +12,62 @@ short_description: Interactive Marketing Text Generator
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+
+## Configuration
+
+The project is configured to use `uv` with the following `uv.yml` file:
+
+```yaml
+name: marketing-text-generator
+dependencies:
+  - python=3.10
+  - pip:
+      - streamlit
+      - transformers
+scripts:
+  start: streamlit run app.py
+```
+
+## Setup and Usage with `uv`
+
+To manage this project with `uv`, follow these steps:
+
+### Prerequisites
+
+Ensure you have `uv` installed. If not, you can install it using pip:
+
+```sh
+pip install uv
+```
+
+### Initializing the `uv` Environment
+
+1. **Initialize the `uv` environment**: Run the following command to set up the environment based on the `uv.yml` configuration:
+
+   ```sh
+   uv start
+   ```
+
+2. **Activate the `uv` environment**: Use the following command to activate the environment:
+
+   ```sh
+   uv activate
+   ```
+
+### Running the Streamlit App
+
+Once the environment is set up and activated, you can start the Streamlit app using the defined script:
+
+```sh
+uv run start
+```
+
+This command will launch the Streamlit app, and you can access it in your web browser.
+
+### Notes
+
+- The first time you run the app, it may take a while to load as it downloads and sets up the necessary dependencies.
+- Ensure all required fields in the form are filled out before generating the marketing text.
+- Review and edit the generated texts as needed before using them.
+
+For more information on `uv`, refer to the [official documentation](https://github.com/iterative/uv).

app.py

@@ -9,7 +9,8 @@ def load_gpt2():
     try:
         # Wir verwenden das deutsche GPT-2 Modell für bessere deutsche Texte
         return pipeline('text-generation', 
-                       model='benjamin/german-gpt2', 
+                       model='dbmdz/german-gpt2',
+                       tokenizer="dbmdz/german-gpt2", 
                        device=-1)
     except Exception as e:
         st.error(f"Modell konnte nicht geladen werden: {str(e)}")

uv.yml

@@ -0,0 +1,8 @@
+name: marketing-text-generator
+dependencies:
+  - python=3.11
+  - pip:
+      - streamlit
+      - transformers
+scripts:
+  start: streamlit run app.py