Upload distilbart-cnn-12-6 ONNX model

README.md

@@ -0,0 +1,48 @@
+---
+library_name: onnx
+tags:
+  - text2text-generation
+  - bart
+  - summarization
+  - encoder-decoder
+  - onnx
+  - inference4j
+license: apache-2.0
+pipeline_tag: summarization
+---
+
+# DistilBART CNN 12-6 — ONNX
+
+ONNX export of [DistilBART CNN 12-6](https://huggingface.co/sshleifer/distilbart-cnn-12-6) (306M parameters) with encoder-decoder architecture and KV cache support.
+
+A distilled version of BART Large CNN, 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:** [sshleifer/distilbart-cnn-12-6](https://huggingface.co/sshleifer/distilbart-cnn-12-6)
+- **License:** Apache 2.0
+
+## Usage with inference4j
+
+```java
+try (var summarizer = BartSummarizer.distilBartCnn().build()) {
+    System.out.println(summarizer.summarize("Long article text..."));
+}
+```
+
+## Model Details
+
+| Property | Value |
+|----------|-------|
+| Architecture | BART encoder-decoder (306M parameters, 12 encoder + 6 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 [Sam Shleifer](https://huggingface.co/sshleifer).

config.json

@@ -0,0 +1,75 @@
+{
+  "_num_labels": 3,
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "BartForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classif_dropout": 0.0,
+  "classifier_dropout": 0.0,
+  "d_model": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "dtype": "float32",
+  "early_stopping": null,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "eos_token_id": 2,
+  "extra_pos_embeddings": 2,
+  "force_bos_token_to_be_generated": true,
+  "forced_eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "length_penalty": null,
+  "max_length": null,
+  "max_position_embeddings": 1024,
+  "min_length": null,
+  "model_type": "bart",
+  "no_repeat_ngram_size": null,
+  "normalize_before": false,
+  "normalize_embedding": true,
+  "num_beams": null,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "prefix": " ",
+  "replacing_rate": 0,
+  "scale_embedding": false,
+  "static_position_embeddings": false,
+  "student_decoder_layers": null,
+  "student_encoder_layers": null,
+  "task_specific_params": {
+    "summarization": {
+      "early_stopping": true,
+      "length_penalty": 2.0,
+      "max_length": 142,
+      "min_length": 56,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 4
+    }
+  },
+  "transformers_version": "4.57.6",
+  "use_cache": true,
+  "vocab_size": 50264
+}

decoder_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d07573868c03d0dc938ca54eee38a3c7855b4d7063c9c277b0f6d3fb761ca98
+size 819503824

decoder_with_past_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a62480780bafb8b29a6a38d3bc6b5ec5cf444985e0a09d906dafe335e1af7014
+size 769100877

encoder_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d4be719088e992b5f18e25a5b10800a6934ae0fc5c67cd5e236e1f4bca61204
+size 814868677