initial commit

README.md

@@ -0,0 +1,46 @@
+---
+language: ko
+tags:
+- bart
+license: MIT
+---
+
+# Korean News Summarization Model
+
+## How to use
+
+```python
+from transformers import PreTrainedTokenizerFast
+from transformers import BartForConditionalGeneration
+
+tokenizer = PreTrainedTokenizerFast(
+    'gogamza/kobart-summarization',
+    bos_token='<s>', eos_token='</s>', unk_token='<unk>', pad_token='<pad>', mask_token='<mask>')
+
+model = BartForConditionalGeneration.from_pretrained('gogamza/kobart-summarization')
+
+text = "과거를 떠올려보자. 방송을 보던 우리의 모습을..."
+
+raw_input_ids = tokenizer.encode(text)
+input_ids = [tokenizer.bos_token_id] + \
+    raw_input_ids + [tokenizer.eos_token_id]
+summary_ids = model.generate(torch.tensor([input_ids]),
+                                max_length=150,
+                                early_stopping=False,
+                                num_beams=5,
+                                repetition_penalty=1.0,
+                                eos_token_id=tokenizer.eos_token_id)
+summ_text = tokenizer.batch_decode(summary_ids.tolist(), skip_special_tokens=True)[0]
+```
+
+## Demo
+
+- <a href="http://52.231.69.211:8081/" target="_blank">요약 데모</a>
+
+<table><tr><td>
+  <center><img src="summ.png" width="600"/></center>
+</td></tr></table>
+
+
+
+

config.json

@@ -0,0 +1,48 @@
+{
+  "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": 0.1,
+  "classifier_dropout": 0.1,
+  "d_model": 768,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "do_blenderbot_90_layernorm": false,
+  "dropout": 0.1,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 1,
+  "extra_pos_embeddings": 2,
+  "force_bos_token_to_be_generated": false,
+  "id2label": {
+    "0": "NEGATIVE",
+    "1": "POSITIVE"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "NEGATIVE": 0,
+    "POSITIVE": 1
+  },
+  "max_position_embeddings": 1026,
+  "model_type": "bart",
+  "normalize_before": false,
+  "normalize_embedding": true,
+  "num_hidden_layers": 6,
+  "pad_token_id": 3,
+  "scale_embedding": false,
+  "static_position_embeddings": false,
+  "use_cache": true,
+  "vocab_size": 30000,
+  "author": "Heewon Jeon(madjakarta@gmail.com)"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f59dd27e0e73b4b5cf45a6c70513cc5af667df248be097874be71bc51fd5f53
+size 495659091