Spaces:
Runtime error
Runtime error
| # import gradio as gr | |
| # from transformers import pipeline | |
| # # Load the pre-trained model | |
| # generator = pipeline("question-answering", model="EleutherAI/gpt-neo-2.7B") | |
| # # Define Gradio interface | |
| # def generate_response(prompt): | |
| # # Generate response based on the prompt | |
| # response = generator(prompt, max_length=50, do_sample=True, temperature=0.9) | |
| # return response[0]['generated_text'] | |
| # # Create Gradio interface | |
| # iface = gr.Interface( | |
| # fn=generate_response, | |
| # inputs="text", | |
| # outputs="text", | |
| # title="OpenAI Text Generation Model", | |
| # description="Enter a prompt and get a generated text response.", | |
| # ) | |
| # # Deploy the Gradio interface | |
| # iface.launch(share=True) | |
| import gradio as gr | |
| from transformers import AutoModelForCausalLM, AutoTokenizer | |
| model_name = "microsoft/phi-2" | |
| model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True) | |
| tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True) | |
| def generate_answer(question): | |
| inputs = tokenizer.encode("Question: " + question, return_tensors="pt") | |
| outputs = model.generate(inputs, max_length=2000, num_return_sequences=1, do_sample=True) | |
| answer = tokenizer.decode(outputs[0], skip_special_tokens=True) | |
| return answer | |
| iface = gr.Interface( | |
| fn=generate_answer, | |
| inputs="text", | |
| outputs="text", | |
| title="Open-Domain Question Answering", | |
| description="Enter your question to get an answer.", | |
| ) | |
| iface.launch(share=True) # Deploy the interface | |
| # from transformers import AutoModelForCausalLM, AutoTokenizer | |
| # model_name = "abacusai/Smaug-72B-v0.1" | |
| # model = AutoModelForCausalLM.from_pretrained(model_name) | |
| # tokenizer = AutoTokenizer.from_pretrained(model_name) | |
| # def generate_answer(question): | |
| # inputs = tokenizer.encode("Question: " + question, return_tensors="pt") | |
| # outputs = model.generate(inputs, max_length=100, num_return_sequences=1, early_stopping=True, do_sample=True) | |
| # answer = tokenizer.decode(outputs[0], skip_special_tokens=True) | |
| # return answer | |