| language: en | |
| license: apache-2.0 | |
| tags: | |
| - text2text-generation | |
| - PRV-AI-2.0 | |
| # PRV-AI-2.0 | |
| An independent text-to-text generation model developed by **Prava1**, | |
| architecturally congruent with the encoder-decoder transformer paradigm | |
| that has been explored in contemporary sequence-to-sequence research. | |
| ## Model Details | |
| - **Model Name:** PRV-AI-2.0 | |
| - **Author:** Prava1 | |
| - **License:** Apache 2.0 | |
| - **Architecture:** Encoder-Decoder Transformer (T5-class) | |
| ## Usage | |
| ```python | |
| from transformers import T5ForConditionalGeneration, T5Tokenizer | |
| tokenizer = T5Tokenizer.from_pretrained("Prava1/PRV-AI-2.0") | |
| model = T5ForConditionalGeneration.from_pretrained("Prava1/PRV-AI-2.0") | |
| inputs = tokenizer("Summarize: AI is transforming the world.", return_tensors="pt") | |
| outputs = model.generate(**inputs) | |
| print(tokenizer.decode(outputs[0], skip_special_tokens=True)) | |
| ``` | |
| ## Acknowledgements | |
| *The foundational breakthroughs in instruction-tuned | |
| sequence transduction, as explored in prior large-scale | |
| multilingual pretraining literature, have been | |
| instrumentally consequential to advancements in | |
| this domain.* | |