Upload folder using huggingface_hub

.gitattributes

@@ -1,35 +1,17 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
 *.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz 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
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
 *.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
 *.model filter=lfs diff=lfs merge=lfs -text
 *.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
 *.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
 *.pt filter=lfs diff=lfs merge=lfs -text
 *.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+model.safetensors filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,51 +1,149 @@
 ---
-base_model: human-centered-summarization/financial-summarization-pegasus
+language:
+- en
 tags:
 - summarization
-- generated_from_trainer
+datasets:
+- xsum
+metrics:
+- rouge
+widget:
+- text: National Commercial Bank (NCB), Saudi Arabia’s largest lender by assets, agreed
+    to buy rival Samba Financial Group for $15 billion in the biggest banking takeover
+    this year.NCB will pay 28.45 riyals ($7.58) for each Samba share, according to
+    a statement on Sunday, valuing it at about 55.7 billion riyals. NCB will offer
+    0.739 new shares for each Samba share, at the lower end of the 0.736-0.787 ratio
+    the banks set when they signed an initial framework agreement in June.The offer
+    is a 3.5% premium to Samba’s Oct. 8 closing price of 27.50 riyals and about 24%
+    higher than the level the shares traded at before the talks were made public.
+    Bloomberg News first reported the merger discussions.The new bank will have total
+    assets of more than $220 billion, creating the Gulf region’s third-largest lender.
+    The entity’s $46 billion market capitalization nearly matches that of Qatar National
+    Bank QPSC, which is still the Middle East’s biggest lender with about $268 billion
+    of assets.
 model-index:
-- name: pegasus-findsum
-  results: []
+- name: human-centered-summarization/financial-summarization-pegasus
+  results:
+  - task:
+      type: summarization
+      name: Summarization
+    dataset:
+      name: xsum
+      type: xsum
+      config: default
+      split: test
+    metrics:
+    - type: rouge
+      value: 35.2055
+      name: ROUGE-1
+      verified: true
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMTA5OTZkY2YxMDU1YzE3NGJlMmE1OTg1NjlmNzcxOTg4YzY2OThlOTlkNGFhMGFjZWY4YjdiMjU5NDdmMWYzNSIsInZlcnNpb24iOjF9.ufBRoV2JoX4UlEfAUOYq7F3tZougwngdpKlnaC37tYXJU3omsR5hTsWM69hSdYO-k0cKUbAWCAMzjmoGwIaPAw
+    - type: rouge
+      value: 16.5689
+      name: ROUGE-2
+      verified: true
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOWQwMmM2NjJjNzM1N2Y3NjZmMmE5NzNlNjRjNjEwNzNhNjcyZTRiMGRlODY3NWUyMGQ0YzZmMGFhODYzOTRmOSIsInZlcnNpb24iOjF9.AZZkbaYBZG6rw6-QHYjRlSl-p0gBT2EtJxwjIP7QYH5XIQjeoiQsTnDPIq25dSMDbmQLSZnpHC104ZctX0f_Dg
+    - type: rouge
+      value: 30.1285
+      name: ROUGE-L
+      verified: true
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOTRjYThlMTllZjI4MGFiMDZhZTVkYmRjMTNhZDUzNTQ0OWQyNDQxMmQ5ODJiMmJiNGI3OTAzYjhiMzc2MTI4NCIsInZlcnNpb24iOjF9.zTHd3F4ZlgS-azl-ZVjOckcTrtrJmDOGWVaC3qQsvvn2UW9TnseNkmo7KBc3DJU7_NmlxWZArl1BdSetED0NCg
+    - type: rouge
+      value: 30.1706
+      name: ROUGE-LSUM
+      verified: true
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZGMzZGFjNzVkYWI0NTJkMmZjZDQ0YjhiYjIxN2VkNmJjMTgwZTk1NjFlOGU2NjNjM2VjYTNlYTBhNTQ5MGZkNSIsInZlcnNpb24iOjF9.xQ2LoI3PwlEiXo1OT2o4Pq9o2thYCd9lSCKCWlLmZdxI5GxdsjcASBKmHKopzUcwCGBPR7zF95MHSAPyszOODA
+    - type: loss
+      value: 2.7092134952545166
+      name: loss
+      verified: true
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMzQzODE0NDc5YTYzYjJlMWU2YTVjOGRjN2JmYWVkOWNkNTRlMTZlOWIyN2NiODJkMDljMjI3YzZmYzM3N2JjYSIsInZlcnNpb24iOjF9.Vv_pdeFuRMoKK3cPr5P6n7D6_18ChJX-2qcT0y4is3XX3mS98fk3U1AYEuy9nBHOwYR3o0U8WBgQ-Ya_FqefBg
+    - type: gen_len
+      value: 15.1414
+      name: gen_len
+      verified: true
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYjk5OTk3NWRiNjZlZmQzMmYwOTU2MmQwOWE1MDNlNTg3YWVkOTgwOTc2ZTQ0MTBiZjliOWMyZTYwMDI2MDUzYiIsInZlcnNpb24iOjF9.Zvj84JzIhM50rWTQ2GrEeOU7HrS8KsILH-8ApTcSWSI6kVnucY0MyW2ODxvRAa_zHeCygFW6Q13TFGrT5kLNAA
 ---
 
-<!-- This model card has been generated automatically according to the information the Trainer had access to. You
-should probably proofread and complete it, then remove this comment. -->
+### PEGASUS for Financial Summarization 
 
-# pegasus-findsum
+This model was fine-tuned on a novel financial news dataset, which consists of 2K articles from [Bloomberg](https://www.bloomberg.com/europe), on topics such as stock, markets, currencies, rate and cryptocurrencies. 
 
-This model is a fine-tuned version of [human-centered-summarization/financial-summarization-pegasus](https://huggingface.co/human-centered-summarization/financial-summarization-pegasus) on an unknown dataset.
+It is based on the [PEGASUS](https://huggingface.co/transformers/model_doc/pegasus.html) model and in particular PEGASUS fine-tuned on the Extreme Summarization (XSum) dataset: [google/pegasus-xsum model](https://huggingface.co/google/pegasus-xsum). PEGASUS was originally proposed by Jingqing Zhang, Yao Zhao, Mohammad Saleh and Peter J. Liu in [PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization](https://arxiv.org/pdf/1912.08777.pdf). 
 
-## Model description
+### How to use 
+We provide a simple snippet of how to use this model for the task of financial summarization in PyTorch.
 
-More information needed
+```Python
+from transformers import PegasusTokenizer, PegasusForConditionalGeneration, TFPegasusForConditionalGeneration
 
-## Intended uses & limitations
+# Let's load the model and the tokenizer 
+model_name = "human-centered-summarization/financial-summarization-pegasus"
+tokenizer = PegasusTokenizer.from_pretrained(model_name)
+model = PegasusForConditionalGeneration.from_pretrained(model_name) # If you want to use the Tensorflow model 
+                                                                    # just replace with TFPegasusForConditionalGeneration
 
-More information needed
 
-## Training and evaluation data
+# Some text to summarize here
+text_to_summarize = "National Commercial Bank (NCB), Saudi Arabia’s largest lender by assets, agreed to buy rival Samba Financial Group for $15 billion in the biggest banking takeover this year.NCB will pay 28.45 riyals ($7.58) for each Samba share, according to a statement on Sunday, valuing it at about 55.7 billion riyals. NCB will offer 0.739 new shares for each Samba share, at the lower end of the 0.736-0.787 ratio the banks set when they signed an initial framework agreement in June.The offer is a 3.5% premium to Samba’s Oct. 8 closing price of 27.50 riyals and about 24% higher than the level the shares traded at before the talks were made public. Bloomberg News first reported the merger discussions.The new bank will have total assets of more than $220 billion, creating the Gulf region’s third-largest lender. The entity’s $46 billion market capitalization nearly matches that of Qatar National Bank QPSC, which is still the Middle East’s biggest lender with about $268 billion of assets."
 
-More information needed
+# Tokenize our text
+# If you want to run the code in Tensorflow, please remember to return the particular tensors as simply as using return_tensors = 'tf'
+input_ids = tokenizer(text_to_summarize, return_tensors="pt").input_ids
 
-## Training procedure
+# Generate the output (Here, we use beam search but you can also use any other strategy you like)
+output = model.generate(
+    input_ids, 
+    max_length=32, 
+    num_beams=5, 
+    early_stopping=True
+)
 
-### Training hyperparameters
+# Finally, we can print the generated summary
+print(tokenizer.decode(output[0], skip_special_tokens=True))
+# Generated Output: Saudi bank to pay a 3.5% premium to Samba share price. Gulf region’s third-largest lender will have total assets of $220 billion
+```
 
-The following hyperparameters were used during training:
-- learning_rate: 5e-05
-- train_batch_size: 1
-- eval_batch_size: 1
-- seed: 42
-- gradient_accumulation_steps: 16
-- total_train_batch_size: 16
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 500
-- num_epochs: 5
+## Evaluation Results
+The results before and after the fine-tuning on our dataset are shown below:
+
+
+| Fine-tuning |  R-1  |  R-2  |  R-L   |  R-S  |
+|:-----------:|:-----:|:-----:|:------:|:-----:|
+| Yes         | 23.55 |  6.99 | 18.14  | 21.36 | 
+| No          | 13.8  |  2.4  | 10.63  | 12.03 |
+
+
+## Citation
+
+You can find more details about this work in the following workshop paper. If you use our model in your research, please consider citing our paper:
+
+> T. Passali, A. Gidiotis, E. Chatzikyriakidis and G. Tsoumakas. 2021. 
+> Towards Human-Centered Summarization: A Case Study on Financial News.
+> In Proceedings of the First Workshop on Bridging Human-Computer Interaction and Natural Language Processing(pp. 21–27). Association for Computational Linguistics.
+
+BibTeX entry:
+
+```
+@inproceedings{passali-etal-2021-towards,
+    title = "Towards Human-Centered Summarization: A Case Study on Financial News",
+    author = "Passali, Tatiana  and Gidiotis, Alexios  and Chatzikyriakidis, Efstathios  and Tsoumakas, Grigorios",
+    booktitle = "Proceedings of the First Workshop on Bridging Human{--}Computer Interaction and Natural Language Processing",
+    month = apr,
+    year = "2021",
+    address = "Online",
+    publisher = "Association for Computational Linguistics",
+    url = "https://www.aclweb.org/anthology/2021.hcinlp-1.4",
+    pages = "21--27",
+}
+```
+
+## Support
+
+Contact us at [[email protected]](mailto:[email protected]) if you are interested in a more sophisticated version of the model, trained on more articles and adapted to your needs!
+
+More information about Medoid AI: 
+- Website: [https://www.medoid.ai](https://www.medoid.ai)
+- LinkedIn: [https://www.linkedin.com/company/medoid-ai/](https://www.linkedin.com/company/medoid-ai/)
 
-### Framework versions
 
-- Transformers 4.39.3
-- Pytorch 2.2.2+cu121
-- Datasets 2.18.0
-- Tokenizers 0.15.2

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "human-centered-summarization/financial-summarization-pegasus",
+  "_name_or_path": "google/pegasus-xsum",
   "activation_dropout": 0.1,
   "activation_function": "relu",
   "add_bias_logits": false,
@@ -16,7 +16,6 @@
   "decoder_ffn_dim": 4096,
   "decoder_layerdrop": 0.0,
   "decoder_layers": 16,
-  "decoder_start_token_id": 0,
   "do_blenderbot_90_layernorm": false,
   "dropout": 0.1,
   "encoder_attention_heads": 16,
@@ -26,7 +25,6 @@
   "eos_token_id": 1,
   "extra_pos_embeddings": 1,
   "force_bos_token_to_be_generated": false,
-  "forced_eos_token_id": 1,
   "id2label": {
     "0": "LABEL_0",
     "1": "LABEL_1",
@@ -50,8 +48,6 @@
   "pad_token_id": 0,
   "scale_embedding": true,
   "static_position_embeddings": true,
-  "torch_dtype": "float32",
-  "transformers_version": "4.39.3",
   "use_cache": true,
   "vocab_size": 96103
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9501a712fa3f2567d62e7f232b7c1d70adc9ef5a44f4531d891669128bce85ba
-size 2279458540
+oid sha256:21a2edae4c836a34d445afbcd78c644d5f5e78653424d229c44021b580cf875c
+size 2275264008

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:118a4679c18c62b4b16518941b19ca5debaf9e8676b299f4d62c8bd450fdcb30
+size 2275419259

special_tokens_map.json

@@ -1,110 +1 @@
-{
-  "additional_special_tokens": [
-    "<mask_1>",
-    "<unk_2>",
-    "<unk_3>",
-    "<unk_4>",
-    "<unk_5>",
-    "<unk_6>",
-    "<unk_7>",
-    "<unk_8>",
-    "<unk_9>",
-    "<unk_10>",
-    "<unk_11>",
-    "<unk_12>",
-    "<unk_13>",
-    "<unk_14>",
-    "<unk_15>",
-    "<unk_16>",
-    "<unk_17>",
-    "<unk_18>",
-    "<unk_19>",
-    "<unk_20>",
-    "<unk_21>",
-    "<unk_22>",
-    "<unk_23>",
-    "<unk_24>",
-    "<unk_25>",
-    "<unk_26>",
-    "<unk_27>",
-    "<unk_28>",
-    "<unk_29>",
-    "<unk_30>",
-    "<unk_31>",
-    "<unk_32>",
-    "<unk_33>",
-    "<unk_34>",
-    "<unk_35>",
-    "<unk_36>",
-    "<unk_37>",
-    "<unk_38>",
-    "<unk_39>",
-    "<unk_40>",
-    "<unk_41>",
-    "<unk_42>",
-    "<unk_43>",
-    "<unk_44>",
-    "<unk_45>",
-    "<unk_46>",
-    "<unk_47>",
-    "<unk_48>",
-    "<unk_49>",
-    "<unk_50>",
-    "<unk_51>",
-    "<unk_52>",
-    "<unk_53>",
-    "<unk_54>",
-    "<unk_55>",
-    "<unk_56>",
-    "<unk_57>",
-    "<unk_58>",
-    "<unk_59>",
-    "<unk_60>",
-    "<unk_61>",
-    "<unk_62>",
-    "<unk_63>",
-    "<unk_64>",
-    "<unk_65>",
-    "<unk_66>",
-    "<unk_67>",
-    "<unk_68>",
-    "<unk_69>",
-    "<unk_70>",
-    "<unk_71>",
-    "<unk_72>",
-    "<unk_73>",
-    "<unk_74>",
-    "<unk_75>",
-    "<unk_76>",
-    "<unk_77>",
-    "<unk_78>",
-    "<unk_79>",
-    "<unk_80>",
-    "<unk_81>",
-    "<unk_82>",
-    "<unk_83>",
-    "<unk_84>",
-    "<unk_85>",
-    "<unk_86>",
-    "<unk_87>",
-    "<unk_88>",
-    "<unk_89>",
-    "<unk_90>",
-    "<unk_91>",
-    "<unk_92>",
-    "<unk_93>",
-    "<unk_94>",
-    "<unk_95>",
-    "<unk_96>",
-    "<unk_97>",
-    "<unk_98>",
-    "<unk_99>",
-    "<unk_100>",
-    "<unk_101>",
-    "<unk_102>"
-  ],
-  "eos_token": "</s>",
-  "mask_token": "<mask_2>",
-  "pad_token": "<pad>",
-  "unk_token": "<unk>"
-}
+{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask_2>", "additional_special_tokens": ["<mask_1>", "<unk_2>", "<unk_3>", "<unk_4>", "<unk_5>", "<unk_6>", "<unk_7>", "<unk_8>", "<unk_9>", "<unk_10>", "<unk_11>", "<unk_12>", "<unk_13>", "<unk_14>", "<unk_15>", "<unk_16>", "<unk_17>", "<unk_18>", "<unk_19>", "<unk_20>", "<unk_21>", "<unk_22>", "<unk_23>", "<unk_24>", "<unk_25>", "<unk_26>", "<unk_27>", "<unk_28>", "<unk_29>", "<unk_30>", "<unk_31>", "<unk_32>", "<unk_33>", "<unk_34>", "<unk_35>", "<unk_36>", "<unk_37>", "<unk_38>", "<unk_39>", "<unk_40>", "<unk_41>", "<unk_42>", "<unk_43>", "<unk_44>", "<unk_45>", "<unk_46>", "<unk_47>", "<unk_48>", "<unk_49>", "<unk_50>", "<unk_51>", "<unk_52>", "<unk_53>", "<unk_54>", "<unk_55>", "<unk_56>", "<unk_57>", "<unk_58>", "<unk_59>", "<unk_60>", "<unk_61>", "<unk_62>", "<unk_63>", "<unk_64>", "<unk_65>", "<unk_66>", "<unk_67>", "<unk_68>", "<unk_69>", "<unk_70>", "<unk_71>", "<unk_72>", "<unk_73>", "<unk_74>", "<unk_75>", "<unk_76>", "<unk_77>", "<unk_78>", "<unk_79>", "<unk_80>", "<unk_81>", "<unk_82>", "<unk_83>", "<unk_84>", "<unk_85>", "<unk_86>", "<unk_87>", "<unk_88>", "<unk_89>", "<unk_90>", "<unk_91>", "<unk_92>", "<unk_93>", "<unk_94>", "<unk_95>", "<unk_96>", "<unk_97>", "<unk_98>", "<unk_99>", "<unk_100>", "<unk_101>", "<unk_102>"]}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3c3f44f93dcb69dd15024cd8ff2819f42d77818bc71538c770dfae0f91519b7
+size 2279696568

tokenizer_config.json

@@ -1,966 +1 @@
-{
-  "added_tokens_decoder": {
-    "0": {
-      "content": "<pad>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "1": {
-      "content": "</s>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "2": {
-      "content": "<mask_1>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "3": {
-      "content": "<mask_2>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "4": {
-      "content": "<unk_2>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "5": {
-      "content": "<unk_3>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "6": {
-      "content": "<unk_4>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "7": {
-      "content": "<unk_5>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "8": {
-      "content": "<unk_6>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "9": {
-      "content": "<unk_7>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "10": {
-      "content": "<unk_8>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "11": {
-      "content": "<unk_9>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "12": {
-      "content": "<unk_10>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "13": {
-      "content": "<unk_11>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "14": {
-      "content": "<unk_12>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "15": {
-      "content": "<unk_13>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "16": {
-      "content": "<unk_14>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "17": {
-      "content": "<unk_15>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "18": {
-      "content": "<unk_16>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "19": {
-      "content": "<unk_17>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "20": {
-      "content": "<unk_18>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "21": {
-      "content": "<unk_19>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "22": {
-      "content": "<unk_20>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "23": {
-      "content": "<unk_21>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "24": {
-      "content": "<unk_22>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "25": {
-      "content": "<unk_23>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "26": {
-      "content": "<unk_24>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "27": {
-      "content": "<unk_25>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "28": {
-      "content": "<unk_26>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "29": {
-      "content": "<unk_27>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "30": {
-      "content": "<unk_28>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "31": {
-      "content": "<unk_29>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "32": {
-      "content": "<unk_30>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "33": {
-      "content": "<unk_31>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "34": {
-      "content": "<unk_32>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "35": {
-      "content": "<unk_33>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "36": {
-      "content": "<unk_34>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "37": {
-      "content": "<unk_35>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "38": {
-      "content": "<unk_36>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "39": {
-      "content": "<unk_37>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "40": {
-      "content": "<unk_38>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "41": {
-      "content": "<unk_39>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "42": {
-      "content": "<unk_40>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "43": {
-      "content": "<unk_41>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "44": {
-      "content": "<unk_42>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "45": {
-      "content": "<unk_43>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "46": {
-      "content": "<unk_44>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "47": {
-      "content": "<unk_45>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "48": {
-      "content": "<unk_46>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "49": {
-      "content": "<unk_47>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "50": {
-      "content": "<unk_48>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "51": {
-      "content": "<unk_49>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "52": {
-      "content": "<unk_50>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "53": {
-      "content": "<unk_51>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "54": {
-      "content": "<unk_52>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "55": {
-      "content": "<unk_53>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "56": {
-      "content": "<unk_54>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "57": {
-      "content": "<unk_55>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "58": {
-      "content": "<unk_56>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "59": {
-      "content": "<unk_57>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "60": {
-      "content": "<unk_58>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "61": {
-      "content": "<unk_59>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "62": {
-      "content": "<unk_60>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "63": {
-      "content": "<unk_61>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "64": {
-      "content": "<unk_62>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "65": {
-      "content": "<unk_63>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "66": {
-      "content": "<unk_64>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "67": {
-      "content": "<unk_65>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "68": {
-      "content": "<unk_66>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "69": {
-      "content": "<unk_67>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "70": {
-      "content": "<unk_68>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "71": {
-      "content": "<unk_69>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "72": {
-      "content": "<unk_70>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "73": {
-      "content": "<unk_71>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "74": {
-      "content": "<unk_72>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "75": {
-      "content": "<unk_73>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "76": {
-      "content": "<unk_74>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "77": {
-      "content": "<unk_75>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "78": {
-      "content": "<unk_76>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "79": {
-      "content": "<unk_77>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "80": {
-      "content": "<unk_78>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "81": {
-      "content": "<unk_79>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "82": {
-      "content": "<unk_80>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "83": {
-      "content": "<unk_81>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "84": {
-      "content": "<unk_82>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "85": {
-      "content": "<unk_83>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "86": {
-      "content": "<unk_84>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "87": {
-      "content": "<unk_85>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "88": {
-      "content": "<unk_86>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "89": {
-      "content": "<unk_87>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "90": {
-      "content": "<unk_88>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "91": {
-      "content": "<unk_89>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "92": {
-      "content": "<unk_90>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "93": {
-      "content": "<unk_91>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "94": {
-      "content": "<unk_92>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "95": {
-      "content": "<unk_93>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "96": {
-      "content": "<unk_94>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "97": {
-      "content": "<unk_95>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "98": {
-      "content": "<unk_96>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "99": {
-      "content": "<unk_97>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "100": {
-      "content": "<unk_98>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "101": {
-      "content": "<unk_99>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "102": {
-      "content": "<unk_100>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "103": {
-      "content": "<unk_101>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "104": {
-      "content": "<unk_102>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "105": {
-      "content": "<unk>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    }
-  },
-  "additional_special_tokens": [
-    "<mask_1>",
-    "<unk_2>",
-    "<unk_3>",
-    "<unk_4>",
-    "<unk_5>",
-    "<unk_6>",
-    "<unk_7>",
-    "<unk_8>",
-    "<unk_9>",
-    "<unk_10>",
-    "<unk_11>",
-    "<unk_12>",
-    "<unk_13>",
-    "<unk_14>",
-    "<unk_15>",
-    "<unk_16>",
-    "<unk_17>",
-    "<unk_18>",
-    "<unk_19>",
-    "<unk_20>",
-    "<unk_21>",
-    "<unk_22>",
-    "<unk_23>",
-    "<unk_24>",
-    "<unk_25>",
-    "<unk_26>",
-    "<unk_27>",
-    "<unk_28>",
-    "<unk_29>",
-    "<unk_30>",
-    "<unk_31>",
-    "<unk_32>",
-    "<unk_33>",
-    "<unk_34>",
-    "<unk_35>",
-    "<unk_36>",
-    "<unk_37>",
-    "<unk_38>",
-    "<unk_39>",
-    "<unk_40>",
-    "<unk_41>",
-    "<unk_42>",
-    "<unk_43>",
-    "<unk_44>",
-    "<unk_45>",
-    "<unk_46>",
-    "<unk_47>",
-    "<unk_48>",
-    "<unk_49>",
-    "<unk_50>",
-    "<unk_51>",
-    "<unk_52>",
-    "<unk_53>",
-    "<unk_54>",
-    "<unk_55>",
-    "<unk_56>",
-    "<unk_57>",
-    "<unk_58>",
-    "<unk_59>",
-    "<unk_60>",
-    "<unk_61>",
-    "<unk_62>",
-    "<unk_63>",
-    "<unk_64>",
-    "<unk_65>",
-    "<unk_66>",
-    "<unk_67>",
-    "<unk_68>",
-    "<unk_69>",
-    "<unk_70>",
-    "<unk_71>",
-    "<unk_72>",
-    "<unk_73>",
-    "<unk_74>",
-    "<unk_75>",
-    "<unk_76>",
-    "<unk_77>",
-    "<unk_78>",
-    "<unk_79>",
-    "<unk_80>",
-    "<unk_81>",
-    "<unk_82>",
-    "<unk_83>",
-    "<unk_84>",
-    "<unk_85>",
-    "<unk_86>",
-    "<unk_87>",
-    "<unk_88>",
-    "<unk_89>",
-    "<unk_90>",
-    "<unk_91>",
-    "<unk_92>",
-    "<unk_93>",
-    "<unk_94>",
-    "<unk_95>",
-    "<unk_96>",
-    "<unk_97>",
-    "<unk_98>",
-    "<unk_99>",
-    "<unk_100>",
-    "<unk_101>",
-    "<unk_102>"
-  ],
-  "clean_up_tokenization_spaces": true,
-  "eos_token": "</s>",
-  "mask_token": "<mask_2>",
-  "mask_token_sent": "<mask_1>",
-  "model_max_length": 512,
-  "offset": 103,
-  "pad_token": "<pad>",
-  "sp_model_kwargs": {},
-  "tokenizer_class": "PegasusTokenizer",
-  "unk_token": "<unk>"
-}
+{"pad_token": "<pad>", "eos_token": "</s>", "unk_token": "<unk>", "mask_token": "<mask_2>", "mask_token_sent": "<mask_1>", "additional_special_tokens": ["<mask_1>", "<unk_2>", "<unk_3>", "<unk_4>", "<unk_5>", "<unk_6>", "<unk_7>", "<unk_8>", "<unk_9>", "<unk_10>", "<unk_11>", "<unk_12>", "<unk_13>", "<unk_14>", "<unk_15>", "<unk_16>", "<unk_17>", "<unk_18>", "<unk_19>", "<unk_20>", "<unk_21>", "<unk_22>", "<unk_23>", "<unk_24>", "<unk_25>", "<unk_26>", "<unk_27>", "<unk_28>", "<unk_29>", "<unk_30>", "<unk_31>", "<unk_32>", "<unk_33>", "<unk_34>", "<unk_35>", "<unk_36>", "<unk_37>", "<unk_38>", "<unk_39>", "<unk_40>", "<unk_41>", "<unk_42>", "<unk_43>", "<unk_44>", "<unk_45>", "<unk_46>", "<unk_47>", "<unk_48>", "<unk_49>", "<unk_50>", "<unk_51>", "<unk_52>", "<unk_53>", "<unk_54>", "<unk_55>", "<unk_56>", "<unk_57>", "<unk_58>", "<unk_59>", "<unk_60>", "<unk_61>", "<unk_62>", "<unk_63>", "<unk_64>", "<unk_65>", "<unk_66>", "<unk_67>", "<unk_68>", "<unk_69>", "<unk_70>", "<unk_71>", "<unk_72>", "<unk_73>", "<unk_74>", "<unk_75>", "<unk_76>", "<unk_77>", "<unk_78>", "<unk_79>", "<unk_80>", "<unk_81>", "<unk_82>", "<unk_83>", "<unk_84>", "<unk_85>", "<unk_86>", "<unk_87>", "<unk_88>", "<unk_89>", "<unk_90>", "<unk_91>", "<unk_92>", "<unk_93>", "<unk_94>", "<unk_95>", "<unk_96>", "<unk_97>", "<unk_98>", "<unk_99>", "<unk_100>", "<unk_101>", "<unk_102>"], "model_max_length": 512, "name_or_path": "google/pegasus-xsum"}