Upload 8 files

README.md

@@ -0,0 +1,52 @@
+---
+language: en
+license: apache-2.0
+datasets:
+- cnn_dailymail
+tags:
+- summarization
+model-index:
+- name: patrickvonplaten/bert2bert_cnn_daily_mail
+  results:
+  - task:
+      type: summarization
+      name: Summarization
+    dataset:
+      name: cnn_dailymail
+      type: cnn_dailymail
+      config: 3.0.0
+      split: test
+    metrics:
+    - name: ROUGE-1
+      type: rouge
+      value: 41.2808
+      verified: true
+    - name: ROUGE-2
+      type: rouge
+      value: 18.6853
+      verified: true
+    - name: ROUGE-L
+      type: rouge
+      value: 28.191
+      verified: true
+    - name: ROUGE-LSUM
+      type: rouge
+      value: 38.0871
+      verified: true
+    - name: loss
+      type: loss
+      value: 2.3451855182647705
+      verified: true
+    - name: gen_len
+      type: gen_len
+      value: 73.8332
+      verified: true
+---
+
+Bert2Bert Summarization with 🤗EncoderDecoder Framework
+This model is a warm-started *BERT2BERT* model fine-tuned on the *CNN/Dailymail* summarization dataset.
+
+The model achieves a **18.22** ROUGE-2 score on *CNN/Dailymail*'s test dataset.
+
+For more details on how the model was fine-tuned, please refer to 
+[this](https://colab.research.google.com/drive/1Ekd5pUeCX7VOrMx94_czTkwNtLN32Uyu?usp=sharing) notebook.

config.json

@@ -0,0 +1,145 @@
+{
+  "architectures": [
+    "EncoderDecoderModel"
+  ],
+  "decoder": {
+    "_name_or_path": "bert-base-uncased",
+    "add_cross_attention": true,
+    "architectures": [
+      "BertForMaskedLM"
+    ],
+    "attention_probs_dropout_prob": 0.1,
+    "bad_words_ids": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "decoder_start_token_id": null,
+    "do_sample": false,
+    "early_stopping": false,
+    "eos_token_id": null,
+    "finetuning_task": null,
+    "gradient_checkpointing": false,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.1,
+    "hidden_size": 768,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_decoder": true,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-12,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 512,
+    "min_length": 0,
+    "model_type": "bert",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 12,
+    "num_beams": 1,
+    "num_hidden_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "pad_token_id": 0,
+    "prefix": null,
+    "pruned_heads": {},
+    "repetition_penalty": 1.0,
+    "return_dict": false,
+    "sep_token_id": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torchscript": false,
+    "type_vocab_size": 2,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 30522,
+    "xla_device": null
+  },
+  "decoder_start_token_id": 101,
+  "early_stopping": true,
+  "encoder": {
+    "_name_or_path": "bert-base-uncased",
+    "add_cross_attention": false,
+    "architectures": [
+      "BertForMaskedLM"
+    ],
+    "attention_probs_dropout_prob": 0.1,
+    "bad_words_ids": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "decoder_start_token_id": null,
+    "do_sample": false,
+    "early_stopping": false,
+    "eos_token_id": null,
+    "finetuning_task": null,
+    "gradient_checkpointing": false,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.1,
+    "hidden_size": 768,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-12,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 512,
+    "min_length": 0,
+    "model_type": "bert",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 12,
+    "num_beams": 1,
+    "num_hidden_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "pad_token_id": 0,
+    "prefix": null,
+    "pruned_heads": {},
+    "repetition_penalty": 1.0,
+    "return_dict": false,
+    "sep_token_id": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torchscript": false,
+    "type_vocab_size": 2,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 30522,
+    "xla_device": null
+  },
+  "eos_token_id": 102,
+  "is_encoder_decoder": true,
+  "length_penalty": 2.0,
+  "max_length": 142,
+  "min_length": 56,
+  "model_type": "encoder-decoder",
+  "no_repeat_ngram_size": 3,
+  "num_beams": 4,
+  "pad_token_id": 0,
+  "vocab_size": 30522
+}

index.gitattributes

@@ -0,0 +1,8 @@
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tar.gz filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c42e5122d8eaf2192d3da7cd4fa360d1cfad98ca07ffe6a9a3aeb8ea1e525dd9
+size 989691346

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "name_or_path": "bert-base-uncased"}