Spaces:
Sleeping
Sleeping
| # import gradio as gr | |
| # gr.load("models/microsoft/Phi-3.5-mini-instruct", max_batch_size=1000).launch(share=True) | |
| # def generate_responce(user_input): | |
| # gr.load("models/microsoft/Phi-3.5-mini-instruct") | |
| # inputs = tokenize(user_input, return_tensor="pt") | |
| # outputs = | |
| # gradio_app = gr.Interface( | |
| # fn=generate_responce, | |
| # inputs="text", | |
| # outputs="text", | |
| # max_batch_size=50, | |
| # title="Advertisment companion", | |
| # ) | |
| # from transformers import AutoTokenizer, AutoModelForCausalLM | |
| # import torch | |
| # # Load the model and tokenizer | |
| # tokenizer = AutoTokenizer.from_pretrained("microsoft/Phi-3.5-mini-instruct", trust_remote_code=True) | |
| # model = AutoModelForCausalLM.from_pretrained("microsoft/Phi-3.5-mini-instruct", trust_remote_code=True) | |
| # # Define the role prompt for advertisement assistance | |
| # # role_prompt = "You are an advertisement assistant. Respond professionally and helpfully to advertising-related questions.\n\n" | |
| # # Function to generate responses | |
| # def generate_response(user_input): | |
| # # Prepend role information to user input | |
| # # input_text = user_input | |
| # # Tokenize and generate response | |
| # inputs = tokenizer(user_input, return_tensors="pt") | |
| # outputs = model.generate( | |
| # **inputs, | |
| # max_new_tokens=100, # Increase this if you want longer responses | |
| # # Nucleus sampling to control randomness | |
| # ) | |
| # # Decode and return the response | |
| # response = tokenizer.batch_decode(outputs, skip_special_tokens=True) | |
| # return response | |
| # # Set up Gradio interface | |
| # interface = gr.Interface( | |
| # fn=generate_response, | |
| # inputs="text", | |
| # outputs="text", | |
| # title="Advertisement Assistant Chatbot", | |
| # description="Ask me anything related to advertising. I'm here to help!" | |
| # ) | |
| # # Launch the Gradio app with sharing enabled | |
| # interface.launch(share=True) | |
| # import gradio as gr | |
| # from transformers import pipeline | |
| # # Load the model pipeline for text generation | |
| # generator = pipeline("text-generation", model="microsoft/Phi-3.5-mini-instruct") | |
| # # Define the role prompt for advertisement assistance | |
| # role_prompt = "You are an advertisement assistant. Respond professionally and helpfully to advertising-related questions.\n\n" | |
| # # Function to generate responses | |
| # def generate_response(user_input): | |
| # input_text = role_prompt + user_input | |
| # response = generator(input_text, max_new_tokens=50, temperature=0.7, top_p=0.9) | |
| # return response[0]["generated_text"] | |
| # # Set up Gradio interface | |
| # interface = gr.Interface( | |
| # fn=generate_response, | |
| # inputs="text", | |
| # outputs="text", | |
| # title="Advertisement Assistant Chatbot", | |
| # description="Ask me anything related to advertising. I'm here to help!" | |
| # ) | |
| # # Launch the Gradio app with sharing enabled | |
| # interface.launch(share=True) | |
| # import gradio as gr | |
| # # Load the model using gr.load() | |
| # model_interface = gr.load("models/microsoft/Phi-3.5-mini-instruct") | |
| # # Create a wrapper interface to customize the appearance | |
| # interface = gr.Interface( | |
| # fn=model_interface, | |
| # inputs="text", | |
| # outputs="text", | |
| # title="Advertisement Assistant Chatbot", | |
| # description="Ask me anything related to advertising. I'm here to help! This assistant provides professional guidance on advertising queries.", | |
| # theme="default", # Optional: Choose a theme or style | |
| # ) | |
| # # Launch with sharing enabled | |
| # interface.launch(share=True) | |
| import gradio as gr | |
| from transformers import pipeline | |
| pipeline = pipeline(task="image-classification", model="julien-c/hotdog-not-hotdog") | |
| def predict(input_img): | |
| predictions = pipeline(input_img) | |
| return input_img, {p["label"]: p["score"] for p in predictions} | |
| gradio_app = gr.Interface( | |
| predict, | |
| inputs=gr.Image(label="Select hot dog candidate", sources=['upload', 'webcam'], type="pil"), | |
| outputs=[gr.Image(label="Processed Image"), gr.Label(label="Result", num_top_classes=2)], | |
| title="Hot Dog? Or Not?", | |
| ) | |
| if __name__ == "__main__": | |
| gradio_app.launch() | |