Add model files and model card

README.md

@@ -0,0 +1,52 @@
+---
+language: 
+- nl
+tags:
+- mbart
+- bart
+- summarization
+datasets:
+- ml6team/cnn_dailymail_nl
+- ml6team/xsum_nl
+---
+
+# mbart-large-cc25-cnn-dailymail-xsum-nl
+
+## Model description
+Finetuned version of [mbart](https://huggingface.co/facebook/mbart-large-cc25). We also wrote a **blog post** about this model [here](https://blog.ml6.eu/)
+
+## Intended uses & limitations
+It's meant for summarizing Dutch news articles.
+
+#### How to use
+
+```python
+import transformers
+
+undisputed_best_model = transformers.MBartForConditionalGeneration.from_pretrained(
+    "ml6team/mbart-large-cc25-cnn-dailymail-xsum-nl"
+)
+tokenizer = transformers.MBartTokenizer.from_pretrained("facebook/mbart-large-cc25")
+summarization_pipeline = transformers.pipeline(
+    task="summarization",
+    model=undisputed_best_model,
+    tokenizer=tokenizer,
+)
+summarization_pipeline.model.config.decoder_start_token_id = tokenizer.lang_code_to_id[
+    "nl_XX"
+]
+
+article = "Kan je dit even samenvatten alsjeblief."  # Dutch
+summarization_pipeline(
+    article,
+    do_sample=True,
+    top_p=0.75,
+    top_k=50,
+    min_length=50,
+    early_stopping=True,
+    truncation=True,
+)[0]["summary_text"]
+```
+
+## Training data
+Finetuned [mbart](https://huggingface.co/facebook/mbart-large-cc25) with [this dataset](https://huggingface.co/datasets/ml6team/cnn_dailymail_nl) and [this dataset](https://huggingface.co/datasets/ml6team/xsum_nl)

config.json

@@ -0,0 +1,59 @@
+{
+  "_name_or_path": "facebook/mbart-large-cc25",
+  "_num_labels": 3,
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "add_bias_logits": false,
+  "add_final_layer_norm": true,
+  "architectures": [
+    "MBartForConditionalGeneration"
+  ],
+  "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": 12,
+  "dropout": 0.1,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 2,
+  "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
+  },
+  "max_length": 1024,
+  "max_position_embeddings": 1024,
+  "model_type": "mbart",
+  "normalize_before": true,
+  "normalize_embedding": true,
+  "num_beams": 5,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "scale_embedding": true,
+  "static_position_embeddings": false,
+  "task_specific_params": {
+    "translation_en_to_ro": {
+      "decoder_start_token_id": 250020
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.15.0",
+  "use_cache": true,
+  "vocab_size": 250027
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce5e2ef6d04dd5b1817d40d199270db3253e4864424c71a714823fb15b9ca101
+size 2444611475

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}, "additional_special_tokens": ["ar_AR", "cs_CZ", "de_DE", "en_XX", "es_XX", "et_EE", "fi_FI", "fr_XX", "gu_IN", "hi_IN", "it_IT", "ja_XX", "kk_KZ", "ko_KR", "lt_LT", "lv_LV", "my_MM", "ne_NP", "nl_XX", "ro_RO", "ru_RU", "si_LK", "tr_TR", "vi_VN", "zh_CN"]}

tokenizer_config.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "src_lang": null, "tgt_lang": null, "additional_special_tokens": null, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "facebook/mbart-large-cc25", "tokenizer_class": "MBartTokenizer"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23cf25a736fe0696f000b513b05a69b830f46b38121e3387e82516b2a6540907
+size 3119