Upload 8 files

README.md

@@ -0,0 +1,52 @@
+---
+language: en
+license: apache-2.0
+datasets:
+- cnn_dailymail
+tags:
+- summarization
+---
+
+# Bert-mini2Bert-mini Summarization with 🤗EncoderDecoder Framework
+
+This model is a warm-started *BERT2BERT* ([mini](https://huggingface.co/google/bert_uncased_L-4_H-256_A-4)) model fine-tuned on the *CNN/Dailymail* summarization dataset.
+
+The model achieves a **16.51** 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.
+
+## Results on test set 📝
+
+| Metric | # Value   |
+| ------ | --------- |
+| **ROUGE-2** | **16.51** |
+
+
+
+## Model in Action 🚀
+
+```python
+from transformers import BertTokenizerFast, EncoderDecoderModel
+import torch
+device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
+tokenizer = BertTokenizerFast.from_pretrained('mrm8488/bert-mini2bert-mini-finetuned-cnn_daily_mail-summarization')
+model = EncoderDecoderModel.from_pretrained('mrm8488/bert-mini2bert-mini-finetuned-cnn_daily_mail-summarization').to(device)
+
+def generate_summary(text):
+    # cut off at BERT max length 512
+    inputs = tokenizer([text], padding="max_length", truncation=True, max_length=512, return_tensors="pt")
+    input_ids = inputs.input_ids.to(device)
+    attention_mask = inputs.attention_mask.to(device)
+
+    output = model.generate(input_ids, attention_mask=attention_mask)
+
+    return tokenizer.decode(output[0], skip_special_tokens=True)
+  
+text = "your text to be summarized here..."
+generate_summary(text)
+```
+
+> Created by [Manuel Romero/@mrm8488](https://twitter.com/mrm8488) | [LinkedIn](https://www.linkedin.com/in/manuel-romero-cs/)
+
+> Made with <span style="color: #e25555;">&hearts;</span> in Spain

config.json

@@ -0,0 +1,141 @@
+{
+  "architectures": [
+    "EncoderDecoderModel"
+  ],
+  "decoder": {
+    "_name_or_path": "google/bert_uncased_L-4_H-256_A-4",
+    "add_cross_attention": true,
+    "architectures": null,
+    "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": 256,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 1024,
+    "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": 4,
+    "num_beams": 1,
+    "num_hidden_layers": 4,
+    "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": true,
+    "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": "google/bert_uncased_L-4_H-256_A-4",
+    "add_cross_attention": false,
+    "architectures": null,
+    "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": 256,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 1024,
+    "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": 4,
+    "num_beams": 1,
+    "num_hidden_layers": 4,
+    "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": true,
+    "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 sha256:0db6945137885092d5c2eb915204187933a460c9baffc21481e56dc7b4fad8ae
+size 93795803

special_tokens_map.json

@@ -0,0 +1 @@
+{"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, "do_basic_tokenize": true, "never_split": null, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "google/bert_uncased_L-4_H-256_A-4"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73fadf0a9554678334ac7069bdb38f38f6851c277253aeabbf0f54c6dd8f97d4
+size 1967