| library_name: onnx | |
| tags: | |
| - text2text-generation | |
| - bart | |
| - summarization | |
| - encoder-decoder | |
| - onnx | |
| - inference4j | |
| license: apache-2.0 | |
| pipeline_tag: summarization | |
| # BART Large CNN — ONNX | |
| ONNX export of [BART Large CNN](https://huggingface.co/facebook/bart-large-cnn) (406M parameters) with encoder-decoder architecture and KV cache support. | |
| Fine-tuned for text summarization on the CNN/DailyMail dataset. | |
| Converted for use with [inference4j](https://github.com/inference4j/inference4j), an inference-only AI library for Java. | |
| ## Original Source | |
| - **Repository:** [facebook/bart-large-cnn](https://huggingface.co/facebook/bart-large-cnn) | |
| - **License:** Apache 2.0 | |
| ## Usage with inference4j | |
| ```java | |
| try (var summarizer = BartSummarizer.bartLargeCnn().build()) { | |
| System.out.println(summarizer.summarize("Long article text...")); | |
| } | |
| ``` | |
| ## Model Details | |
| | Property | Value | | |
| |----------|-------| | |
| | Architecture | BART encoder-decoder (406M parameters, 12 encoder + 12 decoder layers) | | |
| | Task | Text summarization | | |
| | Training data | CNN/DailyMail | | |
| | Tokenizer | BPE (50,265 tokens) | | |
| | Original framework | PyTorch (transformers) | | |
| | Export method | Hugging Face Optimum (encoder-decoder with KV cache) | | |
| ## License | |
| This model is licensed under the [Apache License 2.0](https://www.apache.org/licenses/LICENSE-2.0). Original model by [Facebook AI](https://huggingface.co/facebook). | |