commit files to HF hub

README.md

@@ -0,0 +1,138 @@
+
+---
+license: cc-by-4.0
+metrics:
+- bleu4
+- meteor
+- rouge-l
+- bertscore
+- moverscore
+language: ru
+datasets:
+- lmqg/qg_ruquad
+pipeline_tag: text2text-generation
+tags:
+- question generation
+widget:
+- text: "Нелишним будет отметить, что, развивая это направление, Д. И. Менделеев, поначалу априорно выдвинув идею о температуре, при которой высота мениска будет нулевой, <hl> в мае 1860 года <hl> провёл серию опытов."
+  example_title: "Question Generation Example 1" 
+- text: "Однако, франкоязычный <hl> Квебек <hl> практически никогда не включается в состав Латинской Америки."
+  example_title: "Question Generation Example 2" 
+- text: "Классическим примером международного синдиката XX века была группа компаний <hl> Де Бирс <hl> , которая в 1980-е годы контролировала до 90 % мировой торговли алмазами."
+  example_title: "Question Generation Example 3" 
+model-index:
+- name: vocabtrimmer/mbart-large-cc25-trimmed-ru-ruquad-qg
+  results:
+  - task:
+      name: Text2text Generation
+      type: text2text-generation
+    dataset:
+      name: lmqg/qg_ruquad
+      type: default
+      args: default
+    metrics:
+    - name: BLEU4 (Question Generation)
+      type: bleu4_question_generation
+      value: 18.15
+    - name: ROUGE-L (Question Generation)
+      type: rouge_l_question_generation
+      value: 33.27
+    - name: METEOR (Question Generation)
+      type: meteor_question_generation
+      value: 28.27
+    - name: BERTScore (Question Generation)
+      type: bertscore_question_generation
+      value: 86.7
+    - name: MoverScore (Question Generation)
+      type: moverscore_question_generation
+      value: 65.05
+---
+
+# Model Card of `vocabtrimmer/mbart-large-cc25-trimmed-ru-ruquad-qg`
+This model is fine-tuned version of [ckpts/mbart-large-cc25-trimmed-ru](https://huggingface.co/ckpts/mbart-large-cc25-trimmed-ru) for question generation task on the [lmqg/qg_ruquad](https://huggingface.co/datasets/lmqg/qg_ruquad) (dataset_name: default) via [`lmqg`](https://github.com/asahi417/lm-question-generation).
+
+
+### Overview
+- **Language model:** [ckpts/mbart-large-cc25-trimmed-ru](https://huggingface.co/ckpts/mbart-large-cc25-trimmed-ru)   
+- **Language:** ru  
+- **Training data:** [lmqg/qg_ruquad](https://huggingface.co/datasets/lmqg/qg_ruquad) (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="ru", model="vocabtrimmer/mbart-large-cc25-trimmed-ru-ruquad-qg")
+
+# model prediction
+questions = model.generate_q(list_context="Нелишним будет отметить, что, развивая это направление, Д. И. Менделеев, поначалу априорно выдвинув идею о температуре, при которой высота мениска будет нулевой, в мае 1860 года провёл серию опытов.", list_answer="в мае 1860 года")
+
+```
+
+- With `transformers`
+```python
+from transformers import pipeline
+
+pipe = pipeline("text2text-generation", "vocabtrimmer/mbart-large-cc25-trimmed-ru-ruquad-qg")
+output = pipe("Нелишним будет отметить, что, развивая это направление, Д. И. Менделеев, поначалу априорно выдвинув идею о температуре, при которой высота мениска будет нулевой, <hl> в мае 1860 года <hl> провёл серию опытов.")
+
+```
+
+## Evaluation
+
+
+- ***Metric (Question Generation)***: [raw metric file](https://huggingface.co/vocabtrimmer/mbart-large-cc25-trimmed-ru-ruquad-qg/raw/main/eval/metric.first.sentence.paragraph_answer.question.lmqg_qg_ruquad.default.json) 
+
+|            |   Score | Type    | Dataset                                                          |
+|:-----------|--------:|:--------|:-----------------------------------------------------------------|
+| BERTScore  |   86.7  | default | [lmqg/qg_ruquad](https://huggingface.co/datasets/lmqg/qg_ruquad) |
+| Bleu_1     |   34.19 | default | [lmqg/qg_ruquad](https://huggingface.co/datasets/lmqg/qg_ruquad) |
+| Bleu_2     |   27.16 | default | [lmqg/qg_ruquad](https://huggingface.co/datasets/lmqg/qg_ruquad) |
+| Bleu_3     |   22.07 | default | [lmqg/qg_ruquad](https://huggingface.co/datasets/lmqg/qg_ruquad) |
+| Bleu_4     |   18.15 | default | [lmqg/qg_ruquad](https://huggingface.co/datasets/lmqg/qg_ruquad) |
+| METEOR     |   28.27 | default | [lmqg/qg_ruquad](https://huggingface.co/datasets/lmqg/qg_ruquad) |
+| MoverScore |   65.05 | default | [lmqg/qg_ruquad](https://huggingface.co/datasets/lmqg/qg_ruquad) |
+| ROUGE_L    |   33.27 | default | [lmqg/qg_ruquad](https://huggingface.co/datasets/lmqg/qg_ruquad) |
+
+
+
+## Training hyperparameters
+
+The following hyperparameters were used during fine-tuning:
+ - dataset_path: lmqg/qg_ruquad
+ - dataset_name: default
+ - input_types: paragraph_answer
+ - output_types: question
+ - prefix_types: None
+ - model: ckpts/mbart-large-cc25-trimmed-ru
+ - max_length: 512
+ - max_length_output: 32
+ - epoch: 18
+ - batch: 8
+ - lr: 0.0001
+ - fp16: False
+ - random_seed: 1
+ - gradient_accumulation_steps: 8
+ - label_smoothing: 0.15
+
+The full configuration can be found at [fine-tuning config file](https://huggingface.co/vocabtrimmer/mbart-large-cc25-trimmed-ru-ruquad-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",
+}
+
+```

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

@@ -0,0 +1 @@
+{"validation": {"Bleu_1": 0.3407487565812678, "Bleu_2": 0.27026268753605714, "Bleu_3": 0.21821281486997016, "Bleu_4": 0.17829367532749277}, "test": {"Bleu_1": 0.3403867277362057, "Bleu_2": 0.27044776074821764, "Bleu_3": 0.21981389955438682, "Bleu_4": 0.1808349875396973}}

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

@@ -0,0 +1 @@
+{"validation": {"Bleu_1": 0.3422137646685624, "Bleu_2": 0.2712134203505215, "Bleu_3": 0.2188621590292899, "Bleu_4": 0.17875405442300535, "METEOR": 0.2844079484666794, "ROUGE_L": 0.3354123041931337, "BERTScore": 0.868464763261079, "MoverScore": 0.6521697563253485}, "test": {"Bleu_1": 0.34190334041076453, "Bleu_2": 0.27160107951923074, "Bleu_3": 0.2207393045357022, "Bleu_4": 0.18154640827831353, "METEOR": 0.28267607251288623, "ROUGE_L": 0.3327112212070974, "BERTScore": 0.8669884641364982, "MoverScore": 0.6505327148591051}}