Instructions to use RAAZIM/RT-AI with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ESPnet
How to use RAAZIM/RT-AI with ESPnet:
unknown model type (must be text-to-speech or automatic-speech-recognition)
- Notebooks
- Google Colab
- Kaggle
| # Install the Hugging Face CLI | |
| powershell -ExecutionPolicy ByPass -c "irm https://hf.co/cli/install.ps1 | iex" | |
| # (optional) Login with your Hugging Face credentials | |
| hf auth login | |
| # Push your model files | |
| hf upload RAAZIM/RT-AI . | |
| import gradio as gr | |
| from transformers import pipeline | |
| # 1. Load the GPT-Neo model (free to use) | |
| generator = pipeline("text-generation", model="EleutherAI/gpt-neo-1.3B") | |
| # 2. Create multi-turn chat memory | |
| history = [] | |
| def chat(input_text): | |
| global history | |
| # Add user input to history | |
| history.append(f"User: {input_text}") | |
| # Prepare prompt with conversation history | |
| prompt = "\n".join(history) + "\nAI:" | |
| # Generate response | |
| response = generator(prompt, max_length=200, do_sample=True, temperature=0.7) | |
| ai_text = response[0]["generated_text"] | |
| # Add AI response to history | |
| history.append(f"AI: {ai_text}") | |
| return ai_text | |
| # 3. Gradio interface | |
| iface = gr.Interface( | |
| fn=chat, | |
| inputs=gr.Textbox(lines=2, placeholder="Type your message here..."), | |
| outputs="text", | |
| title="AltisBot", # <-- Your chatbot name here | |
| description="Your free AI assistant chatbot" | |
| ) | |
| # 4. Launch the interface | |
| iface.launch() | |
| unknown model type (must be text-to-speech or automatic-speech-recognition) | |