first commit

README.md

@@ -0,0 +1,69 @@
+---
+language: id
+tags:
+- pipeline:summarization
+- summarization
+- bert2gpt
+datasets:
+- id_liputan6
+license: apache-2.0
+---
+
+# Indonesian BERT2BERT Summarization Model
+
+Finetuned EncoderDecoder model using BERT-base and GPT2-small for Indonesian text summarization.
+
+## Finetuning Corpus
+
+`bert2gpt-indonesian-summarization` model is based on `cahya/bert-base-indonesian-1.5G` and `cahya/gpt2-small-indonesian-522M`by [cahya](https://huggingface.co/cahya), finetuned using [id_liputan6](https://huggingface.co/datasets/id_liputan6) dataset.
+
+## Load Finetuned Model
+
+```python
+from transformers import BertTokenizer, EncoderDecoderModel
+
+tokenizer = BertTokenizer.from_pretrained("cahya/bert2gpt-indonesian-summarization")
+tokenizer.bos_token = tokenizer.cls_token
+tokenizer.eos_token = tokenizer.sep_token
+model = EncoderDecoderModel.from_pretrained("cahya/bert2gpt-indonesian-summarization")
+```
+
+## Code Sample
+
+```python
+from transformers import BertTokenizer, EncoderDecoderModel
+
+tokenizer = BertTokenizer.from_pretrained("cahya/bert2gpt-indonesian-summarization")
+tokenizer.bos_token = tokenizer.cls_token
+tokenizer.eos_token = tokenizer.sep_token
+model = EncoderDecoderModel.from_pretrained("cahya/bert2gpt-indonesian-summarization")
+
+# 
+ARTICLE_TO_SUMMARIZE = ""
+
+# generate summary
+input_ids = tokenizer.encode(ARTICLE_TO_SUMMARIZE, return_tensors='pt')
+summary_ids = model.generate(input_ids,
+            min_length=20,
+            max_length=80, 
+            num_beams=10,
+            repetition_penalty=2.5, 
+            length_penalty=1.0, 
+            early_stopping=True,
+            no_repeat_ngram_size=2,
+            use_cache=True,
+            do_sample = True,
+            temperature = 0.8,
+            top_k = 50,
+            top_p = 0.95)
+
+summary_text = tokenizer.decode(summary_ids[0], skip_special_tokens=True)
+print(summary_text)
+```
+
+Output:
+
+```
+
+```
+

config.json

@@ -0,0 +1,164 @@
+{
+  "architectures": [
+    "EncoderDecoderModel"
+  ],
+  "decoder": {
+    "_name_or_path": "cahya/gpt2-small-indonesian-522M",
+    "activation_function": "gelu_new",
+    "add_cross_attention": true,
+    "architectures": [
+      "GPT2LMHeadModel"
+    ],
+    "attn_pdrop": 0.1,
+    "bad_words_ids": null,
+    "bos_token_id": 50256,
+    "chunk_size_feed_forward": 0,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "embd_pdrop": 0.1,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 50256,
+    "finetuning_task": null,
+    "gradient_checkpointing": false,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "is_decoder": true,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_epsilon": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "gpt2",
+    "n_ctx": 1024,
+    "n_embd": 768,
+    "n_head": 12,
+    "n_inner": null,
+    "n_layer": 12,
+    "n_positions": 1024,
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "prefix": null,
+    "pruned_heads": {},
+    "repetition_penalty": 1.0,
+    "resid_pdrop": 0.1,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "summary_activation": null,
+    "summary_first_dropout": 0.1,
+    "summary_proj_to_labels": true,
+    "summary_type": "cls_index",
+    "summary_use_proj": true,
+    "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,
+    "transformers_version": "4.4.0.dev0",
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 50257,
+    "xla_device": null
+  },
+  "decoder_start_token_id": 3,
+  "early_stopping": true,
+  "encoder": {
+    "_name_or_path": "cahya/bert-base-indonesian-1.5G",
+    "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,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "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_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 0,
+    "position_embedding_type": "absolute",
+    "prefix": null,
+    "pruned_heads": {},
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": 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,
+    "transformers_version": "4.4.0.dev0",
+    "type_vocab_size": 2,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 32000,
+    "xla_device": null
+  },
+  "eos_token_id": 1,
+  "is_encoder_decoder": true,
+  "length_penalty": 2.0,
+  "max_length": 40,
+  "min_length": 20,
+  "model_type": "encoder-decoder",
+  "no_repeat_ngram_size": 3,
+  "num_beams": 10,
+  "pad_token_id": 2,
+  "vocab_size": 50257
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a8a5e8b8a4539592118c54b98a45e63e47dc9578915f9873dd36ef457922774
+size 1079069947

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 @@
+{"special_tokens_map_file": null, "full_tokenizer_file": null}