import gradio as gr from transformers import ( AutoModelForSeq2SeqLM, AutoModelForTableQuestionAnswering, AutoTokenizer, pipeline, TapexTokenizer, BartForConditionalGeneration ) import pandas as pd # model_tapex = "microsoft/tapex-large-finetuned-wtq" # tokenizer_tapex = AutoTokenizer.from_pretrained(model_tapex) # model_tapex = AutoModelForSeq2SeqLM.from_pretrained(model_tapex) # pipe_tapex = pipeline( # "table-question-answering", model=model_tapex, tokenizer=tokenizer_tapex # ) #new tokenizer = TapexTokenizer.from_pretrained("microsoft/tapex-large-finetuned-wtq") model = BartForConditionalGeneration.from_pretrained("microsoft/tapex-large-finetuned-wtq") # model_tapas = "google/tapas-large-finetuned-wtq" # tokenizer_tapas = AutoTokenizer.from_pretrained(model_tapas) # model_tapas = AutoModelForTableQuestionAnswering.from_pretrained(model_tapas) # pipe_tapas = pipeline( # "table-question-answering", model=model_tapas, tokenizer=tokenizer_tapas # ) #new pipe_tapas = pipeline(task="table-question-answering", model="google/tapas-large-finetuned-wtq") def process2(query, csv_data): csv_data={"Actors": ["Brad Pitt", "Leonardo Di Caprio", "George Clooney"], "Number of movies": ["87", "53", "69"]} table = pd.DataFrame.from_dict(csv_data) #microsoft encoding = tokenizer(table=table, query=query, return_tensors="pt") outputs = model.generate(**encoding) result_tapex=tokenizer.batch_decode(outputs, skip_special_tokens=True) #google result_tapas = pipe_tapas(table=table, query=query)['cells'][0] return result_tapex, result_tapas # Inputs query_text = gr.Text(label="Enter a question") # input_file = gr.File(label="Upload a CSV file", type="file") input_data = gr.Text(label="Input table json data") # rows_slider = gr.Slider(label="Number of rows") # Output answer_text_tapex = gr.Text(label="TAPEX answer") answer_text_tapas = gr.Text(label="TAPAS answer") description = "This Space lets you ask questions on CSV documents with Microsoft [TAPEX-Large](https://huggingface.co/microsoft/tapex-large-finetuned-wtq) and Google [TAPAS-Large](https://huggingface.co/google/tapas-large-finetuned-wtq). \ Both have been fine-tuned on the [WikiTableQuestions](https://huggingface.co/datasets/wikitablequestions) dataset. \n\n\ A sample file with football statistics is available in the repository: \n\n\ * Which team has the most wins? Answer: Manchester City FC\n\ * Which team has the most wins: Chelsea, Liverpool or Everton? Answer: Liverpool\n\ * Which teams have scored less than 40 goals? Answer: Cardiff City FC, Fulham FC, Brighton & Hove Albion FC, Huddersfield Town FC\n\ * What is the average number of wins? Answer: 16 (rounded)\n\n\ You can also upload your own CSV file. Please note that maximum sequence length for both models is 1024 tokens, \ so you may need to limit the number of rows in your CSV file. Chunking is not implemented yet." iface = gr.Interface( theme="huggingface", description=description, layout="vertical", fn=process2, inputs=[query_text, input_data], outputs=[answer_text_tapex, answer_text_tapas], examples=[ ], allow_flagging="never", ) iface.launch()