commit files to HF hub

README.md

@@ -0,0 +1,114 @@
+
+---
+license: cc-by-4.0
+metrics:
+- bleu4
+- meteor
+- rouge-l
+- bertscore
+- moverscore
+language: en
+datasets:
+- StellarMilk/squad_newsqa
+pipeline_tag: text2text-generation
+tags:
+- questions and answers generation
+widget:
+- text: "generate question and answer: Beyonce further expanded her acting career, starring as blues singer Etta James in the 2008 musical biopic, Cadillac Records."
+  example_title: "Questions & Answers Generation Example 1" 
+model-index:
+- name: StellarMilk/t5-small-squad-newsqa-qag-trained
+  results:
+  - task:
+      name: Text2text Generation
+      type: text2text-generation
+    dataset:
+      name: StellarMilk/squad_newsqa
+      type: default
+      args: default
+    metrics:
+    - name: BLEU4 (Question & Answer Generation)
+      type: bleu4_question_answer_generation
+      value: 5.67
+---
+
+# Model Card of `StellarMilk/t5-small-squad-newsqa-qag-trained`
+This model is fine-tuned version of [t5-small](https://huggingface.co/t5-small) for question & answer pair generation task on the [StellarMilk/squad_newsqa](https://huggingface.co/datasets/StellarMilk/squad_newsqa) (dataset_name: default) via [`lmqg`](https://github.com/asahi417/lm-question-generation).
+
+
+### Overview
+- **Language model:** [t5-small](https://huggingface.co/t5-small)   
+- **Language:** en  
+- **Training data:** [StellarMilk/squad_newsqa](https://huggingface.co/datasets/StellarMilk/squad_newsqa) (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="en", model="StellarMilk/t5-small-squad-newsqa-qag-trained")
+
+# model prediction
+question_answer_pairs = model.generate_qa("William Turner was an English painter who specialised in watercolour landscapes")
+
+```
+
+- With `transformers`
+```python
+from transformers import pipeline
+
+pipe = pipeline("text2text-generation", "StellarMilk/t5-small-squad-newsqa-qag-trained")
+output = pipe("generate question and answer: Beyonce further expanded her acting career, starring as blues singer Etta James in the 2008 musical biopic, Cadillac Records.")
+
+```
+
+## Evaluation
+
+
+- ***Metric (Question & Answer Generation)***: [raw metric file](https://huggingface.co/StellarMilk/t5-small-squad-newsqa-qag-trained/raw/main/eval/metric.first.answer.paragraph.questions_answers.StellarMilk_squad_newsqa.default.json) 
+
+| Score   | Type   | Dataset   |
+|---------|--------|-----------|
+
+
+
+## Training hyperparameters
+
+The following hyperparameters were used during fine-tuning:
+ - dataset_path: StellarMilk/squad_newsqa
+ - dataset_name: default
+ - input_types: ['paragraph']
+ - output_types: ['questions_answers']
+ - prefix_types: ['qag']
+ - model: t5-small
+ - max_length: 512
+ - max_length_output: 512
+ - epoch: 3
+ - batch: 2
+ - lr: 1e-05
+ - 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/StellarMilk/t5-small-squad-newsqa-qag-trained/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.questions_answers.StellarMilk_squad_newsqa.default.json

@@ -0,0 +1 @@
+{"validation": {"Bleu_1": 0.2931779573819033, "Bleu_2": 0.1679642439217249, "Bleu_3": 0.09900018031960674, "Bleu_4": 0.0658890416713825}, "test": {"Bleu_1": 0.27017063100588157, "Bleu_2": 0.15127545074771495, "Bleu_3": 0.08683136335169285, "Bleu_4": 0.05672527099123468}}

trainer_config.json

@@ -0,0 +1 @@
+{"dataset_path": "StellarMilk/squad_newsqa", "dataset_name": "default", "input_types": ["paragraph"], "output_types": ["questions_answers"], "prefix_types": ["qag"], "model": "t5-small", "max_length": 512, "max_length_output": 512, "epoch": 3, "batch": 2, "lr": 1e-05, "fp16": false, "random_seed": 1, "gradient_accumulation_steps": 2, "label_smoothing": 0.15}