Spaces:
Runtime error
Runtime error
| import spaces | |
| from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer | |
| import gradio as gr | |
| from threading import Thread | |
| import os | |
| from gradio_modal import Modal | |
| checkpoint = "WillHeld/soft-raccoon" | |
| device = "cuda" | |
| tokenizer = AutoTokenizer.from_pretrained(checkpoint) | |
| model = AutoModelForCausalLM.from_pretrained(checkpoint).to(device) | |
| def predict(message, history, temperature, top_p): | |
| history.append({"role": "user", "content": message}) | |
| input_text = tokenizer.apply_chat_template(history, tokenize=False, add_generation_prompt=True) | |
| inputs = tokenizer.encode(input_text, return_tensors="pt").to(device) | |
| # Create a streamer | |
| streamer = TextIteratorStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True) | |
| # Set up generation parameters | |
| generation_kwargs = { | |
| "input_ids": inputs, | |
| "max_new_tokens": 1024, | |
| "temperature": float(temperature), | |
| "top_p": float(top_p), | |
| "do_sample": True, | |
| "streamer": streamer, | |
| "eos_token_id": 128009, | |
| } | |
| # Run generation in a separate thread | |
| thread = Thread(target=model.generate, kwargs=generation_kwargs) | |
| thread.start() | |
| # Yield from the streamer as tokens are generated | |
| partial_text = "" | |
| for new_text in streamer: | |
| partial_text += new_text | |
| yield partial_text | |
| # Function to handle the report submission | |
| def submit_report(satisfaction, feedback_text): | |
| # In a real application, you might save this to a database or file | |
| print(f"Report submitted - Satisfaction: {satisfaction}, Feedback: {feedback_text}") | |
| return "Thank you for your feedback! Your report has been submitted." | |
| with gr.Blocks() as demo: | |
| with gr.Row(): | |
| with gr.Column(scale=3): | |
| chatbot = gr.ChatInterface( | |
| predict, | |
| additional_inputs=[ | |
| gr.Slider(0.1, 2.0, value=0.7, step=0.1, label="Temperature"), | |
| gr.Slider(0.1, 1.0, value=0.9, step=0.05, label="Top-P") | |
| ], | |
| type="messages" | |
| ) | |
| with gr.Column(scale=1): | |
| report_button = gr.Button("File a Report", variant="primary") | |
| # Create the modal with feedback form components | |
| with Modal(visible=False) as feedback_modal: | |
| with gr.Column(): | |
| gr.Markdown("## We value your feedback!") | |
| gr.Markdown("Please tell us about your experience with the model.") | |
| satisfaction = gr.Radio( | |
| ["Very satisfied", "Satisfied", "Neutral", "Unsatisfied", "Very unsatisfied"], | |
| label="How satisfied are you with the model's responses?", | |
| value="Neutral" | |
| ) | |
| feedback_text = gr.Textbox( | |
| lines=5, | |
| label="Please provide any additional feedback or describe issues you encountered:", | |
| placeholder="Enter your detailed feedback here..." | |
| ) | |
| submit_button = gr.Button("Submit Feedback", variant="primary") | |
| response_text = gr.Textbox(label="Status", interactive=False) | |
| # Connect the "File a Report" button to show the modal | |
| report_button.click( | |
| lambda: Modal(visible=True), | |
| None, | |
| feedback_modal | |
| ) | |
| # Connect the submit button to the submit_report function | |
| submit_button.click( | |
| submit_report, | |
| inputs=[satisfaction, feedback_text], | |
| outputs=response_text | |
| ) | |
| demo.launch() |