model update

.gitattributes

@@ -32,3 +32,4 @@ saved_model/**/* 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,138 @@
+
+---
+license: cc-by-4.0
+metrics:
+- bleu4
+- meteor
+- rouge-l
+- bertscore
+- moverscore
+language: ko
+datasets:
+- lmqg/qg_koquad
+pipeline_tag: text2text-generation
+tags:
+- question generation
+widget:
+- text: "1990년 영화 《 <hl> 남부군 <hl> 》에서 단역으로 영화배우 첫 데뷔에 이어 같은 해 KBS 드라마 《지구인》에서 단역으로 출연하였고 이듬해 MBC 《여명의 눈동자》를 통해 단역으로 출연하였다."
+  example_title: "Question Generation Example 1" 
+- text: "백신이 없기때문에 예방책은 <hl> 살충제 <hl> 를 사용하면서 서식 장소(찻찬 받침, 배수로, 고인 물의 열린 저장소, 버려진 타이어 등)의 수를 줄임으로써 매개체를 통제할 수 있다."
+  example_title: "Question Generation Example 2" 
+- text: "<hl> 원테이크 촬영 <hl> 이기 때문에 한 사람이 실수를 하면 처음부터 다시 찍어야 하는 상황이 발생한다."
+  example_title: "Question Generation Example 3" 
+model-index:
+- name: vocabtrimmer/mt5-small-trimmed-ko-koquad-qg
+  results:
+  - task:
+      name: Text2text Generation
+      type: text2text-generation
+    dataset:
+      name: lmqg/qg_koquad
+      type: default
+      args: default
+    metrics:
+    - name: BLEU4 (Question Generation)
+      type: bleu4_question_generation
+      value: 11.22
+    - name: ROUGE-L (Question Generation)
+      type: rouge_l_question_generation
+      value: 26.36
+    - name: METEOR (Question Generation)
+      type: meteor_question_generation
+      value: 27.98
+    - name: BERTScore (Question Generation)
+      type: bertscore_question_generation
+      value: 83.69
+    - name: MoverScore (Question Generation)
+      type: moverscore_question_generation
+      value: 82.62
+---
+
+# Model Card of `vocabtrimmer/mt5-small-trimmed-ko-koquad-qg`
+This model is fine-tuned version of [vocabtrimmer/mt5-small-trimmed-ko](https://huggingface.co/vocabtrimmer/mt5-small-trimmed-ko) for question generation task on the [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) (dataset_name: default) via [`lmqg`](https://github.com/asahi417/lm-question-generation).
+
+
+### Overview
+- **Language model:** [vocabtrimmer/mt5-small-trimmed-ko](https://huggingface.co/vocabtrimmer/mt5-small-trimmed-ko)   
+- **Language:** ko  
+- **Training data:** [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) (default)
+- **Online Demo:** [https://autoqg.net/](https://autoqg.net/)
+- **Repository:** [https://github.com/asahi417/lm-question-generation](https://github.com/asahi417/lm-question-generation)
+- **Paper:** [https://arxiv.org/abs/2210.03992](https://arxiv.org/abs/2210.03992)
+
+### Usage
+- With [`lmqg`](https://github.com/asahi417/lm-question-generation#lmqg-language-model-for-question-generation-)
+```python
+from lmqg import TransformersQG
+
+# initialize model
+model = TransformersQG(language="ko", model="vocabtrimmer/mt5-small-trimmed-ko-koquad-qg")
+
+# model prediction
+questions = model.generate_q(list_context="1990년 영화 《 남부군 》에서 단역으로 영화배우 첫 데뷔에 이어 같은 해 KBS 드라마 《지구인》에서 단역으로 출연하였고 이듬해 MBC 《여명의 눈동자》를 통해 단역으로 출연하였다.", list_answer="남부군")
+
+```
+
+- With `transformers`
+```python
+from transformers import pipeline
+
+pipe = pipeline("text2text-generation", "vocabtrimmer/mt5-small-trimmed-ko-koquad-qg")
+output = pipe("1990년 영화 《 <hl> 남부군 <hl> 》에서 단역으로 영화배우 첫 데뷔에 이어 같은 해 KBS 드라마 《지구인》에서 단역으로 출연하였고 이듬해 MBC 《여명의 눈동자》를 통해 단역으로 출연하였다.")
+
+```
+
+## Evaluation
+
+
+- ***Metric (Question Generation)***: [raw metric file](https://huggingface.co/vocabtrimmer/mt5-small-trimmed-ko-koquad-qg/raw/main/eval/metric.first.sentence.paragraph_answer.question.lmqg_qg_koquad.default.json) 
+
+|            |   Score | Type    | Dataset                                                          |
+|:-----------|--------:|:--------|:-----------------------------------------------------------------|
+| BERTScore  |   83.69 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
+| Bleu_1     |   26.6  | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
+| Bleu_2     |   19.55 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
+| Bleu_3     |   14.72 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
+| Bleu_4     |   11.22 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
+| METEOR     |   27.98 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
+| MoverScore |   82.62 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
+| ROUGE_L    |   26.36 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
+
+
+
+## Training hyperparameters
+
+The following hyperparameters were used during fine-tuning:
+ - dataset_path: lmqg/qg_koquad
+ - dataset_name: default
+ - input_types: paragraph_answer
+ - output_types: question
+ - prefix_types: None
+ - model: vocabtrimmer/mt5-small-trimmed-ko
+ - max_length: 512
+ - max_length_output: 32
+ - epoch: 12
+ - batch: 32
+ - lr: 0.001
+ - fp16: False
+ - random_seed: 1
+ - gradient_accumulation_steps: 2
+ - label_smoothing: 0.15
+
+The full configuration can be found at [fine-tuning config file](https://huggingface.co/vocabtrimmer/mt5-small-trimmed-ko-koquad-qg/raw/main/trainer_config.json).
+
+## Citation
+```
+@inproceedings{ushio-etal-2022-generative,
+    title = "{G}enerative {L}anguage {M}odels for {P}aragraph-{L}evel {Q}uestion {G}eneration",
+    author = "Ushio, Asahi  and
+        Alva-Manchego, Fernando  and
+        Camacho-Collados, Jose",
+    booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
+    month = dec,
+    year = "2022",
+    address = "Abu Dhabi, U.A.E.",
+    publisher = "Association for Computational Linguistics",
+}
+
+```

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<hl>": 73356
+}

config.json

@@ -0,0 +1,53 @@
+{
+  "_name_or_path": "lmqg_output/trimmed_qg/mt5-small-trimmed-ko-koquad-qg/model_wmcoba/epoch_5",
+  "add_prefix": false,
+  "architectures": [
+    "MT5ForConditionalGeneration"
+  ],
+  "d_ff": 1024,
+  "d_kv": 64,
+  "d_model": 512,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "mt5",
+  "num_decoder_layers": 8,
+  "num_heads": 6,
+  "num_layers": 8,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "tokenizer_class": "T5Tokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.1",
+  "use_cache": true,
+  "vocab_size": 73357,
+  "vocabtrimmer": {
+    "mining_config": {
+      "dataset": "vocabtrimmer/mc4_validation",
+      "dataset_column": "text",
+      "dataset_name": "ko",
+      "dataset_split": "validation",
+      "language": "ko",
+      "min_frequency": 2,
+      "target_vocab_size": null
+    },
+    "stats": {
+      "compression_rate_embedding": 29.329260491299898,
+      "compression_rate_full": 39.70281404322403,
+      "parameter_size_embedding/raw": 256114688,
+      "parameter_size_embedding/trimmed": 75116544,
+      "parameter_size_full/raw": 300176768,
+      "parameter_size_full/trimmed": 119178624,
+      "vocab_size/raw": 250112,
+      "vocab_size/trimmed": 73356
+    }
+  }
+}

eval/metric.first.answer.paragraph_answer.question.lmqg_qg_koquad.default.json

@@ -0,0 +1 @@
+{"validation": {"Bleu_1": 0.25025182573658505, "Bleu_2": 0.18240754238793663, "Bleu_3": 0.13668169507998976, "Bleu_4": 0.10415574106904937}, "test": {"Bleu_1": 0.26318239526025683, "Bleu_2": 0.1930858983779023, "Bleu_3": 0.14523885616258092, "Bleu_4": 0.11061169834018082}}

eval/metric.first.sentence.paragraph_answer.question.lmqg_qg_koquad.default.json

@@ -0,0 +1 @@
+{"validation": {"Bleu_1": 0.284231036882386, "Bleu_2": 0.21154803685569284, "Bleu_3": 0.1611403376680883, "Bleu_4": 0.12414307684332021, "METEOR": 0.28327675523071516, "ROUGE_L": 0.2720815157984448, "BERTScore": 0.8304896071803468, "MoverScore": 0.8293865560624111}, "test": {"Bleu_1": 0.2660048226272399, "Bleu_2": 0.19547467003031915, "Bleu_3": 0.14721260000365624, "Bleu_4": 0.112159203165296, "METEOR": 0.2798399275673203, "ROUGE_L": 0.26359342086196064, "BERTScore": 0.8368670031890183, "MoverScore": 0.8262387498353335}}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.26.1"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:922af8d82d61c3ac19948d88f228a0e80258ff13526e38a0db0e3ce72f7d7c4c
+size 476784005

special_tokens_map.json

@@ -0,0 +1,8 @@
+{
+  "additional_special_tokens": [
+    "<hl>"
+  ],
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
+size 4309802

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51ead6033dd871b60241a6d8fd95d8d60bb730f54fe7fa208efe1699329b2a70
+size 4885417

tokenizer_config.json

@@ -0,0 +1,12 @@
+{
+  "additional_special_tokens": null,
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "model_max_length": 1000000000000000019884624838656,
+  "name_or_path": "lmqg_output/trimmed_qg/mt5-small-trimmed-ko-koquad-qg/model_wmcoba/epoch_5",
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": "/home/asahiushio/.cache/huggingface/hub/models--google--mt5-small/snapshots/38f23af8ec210eb6c376d40e9c56bd25a80f195d/special_tokens_map.json",
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}

trainer_config.json

@@ -0,0 +1 @@
+{"dataset_path": "lmqg/qg_koquad", "dataset_name": "default", "input_types": "paragraph_answer", "output_types": "question", "prefix_types": null, "model": "vocabtrimmer/mt5-small-trimmed-ko", "max_length": 512, "max_length_output": 32, "epoch": 12, "batch": 32, "lr": 0.001, "fp16": false, "random_seed": 1, "gradient_accumulation_steps": 2, "label_smoothing": 0.15}