| language: en | |
| tags: | |
| - question-answering | |
| - science | |
| - flan-t5 | |
| - transformers | |
| license: mit | |
| # Science Q&A Base Model | |
| This is a base model model fine-tuned for science question answering. | |
| ## Model Details | |
| - **Base Model**: google/flan-t5-small | |
| - **Task**: Question Answering | |
| - **Domain**: Science | |
| - **Training Data**: Science content from PDF documents | |
| - **Model Type**: Base Model | |
| ## Usage | |
| ```python | |
| from transformers import AutoTokenizer, AutoModelForSeq2SeqLM | |
| tokenizer = AutoTokenizer.from_pretrained("alexputhiyadom/science-qa-base") | |
| model = AutoModelForSeq2SeqLM.from_pretrained("alexputhiyadom/science-qa-base") | |
| # Example usage | |
| question = "What is science?" | |
| inputs = tokenizer(f"Question: {question}\nAnswer:", return_tensors="pt") | |
| outputs = model.generate(**inputs, max_length=128) | |
| answer = tokenizer.decode(outputs[0], skip_special_tokens=True) | |
| print(answer) | |
| ``` | |
| ## Training | |
| This model was trained on science content using the flan-t5-small base model. | |
| The training focused on generating concise, accurate answers to science-related questions. | |
| ## License | |
| MIT License | |