pilota_scud2query / README.md
shirayu's picture
Updated tags
a35fb64
---
language: ja
tags:
- t5
- text2text-generation
- pilota
license: apache-2.0
---
# Pilota model for scud2query
A model for [Pilota](https://github.com/megagonlabs/pilota) trained with <https://github.com/megagonlabs/scud2query>.
- ``scud``
- Fine tuned model of [t5-base-japanese-web (with Byte-fallback, 8K)](https://huggingface.co/megagonlabs/t5-base-japanese-web-8k)
- The original model is distributed in [the Apache License 2.0](https://www.apache.org/licenses/LICENSE-2.0)
- ``scorer``
- Fine tuned model of [LINE DistilBERT Japanese](https://huggingface.co/line-corporation/line-distilbert-base-japanese)
- The original model is distributed in [the Apache License 2.0](https://www.apache.org/licenses/LICENSE-2.0)
## Usage
1. Install [Pilota](https://github.com/megagonlabs/pilota)
2. Prepare inputs
- Command
```bash
echo -e 'ιƒ¨ε±‹γ«ε†·θ”΅εΊ«γŒγ‚γ‚‹γ¨θ‰―γ„γ€‚γƒ¬γƒ³γ‚Ώγ‚«γƒΌγ‚΅γƒΌγƒ“γ‚ΉγŒγ‚γ‚‹γƒ›γƒ†γƒ«γ‚’γ€customerγ€‘γŒεΈŒζœ›γ™γ‚‹γ€‚' | python -m pilota.convert.plain2request | tee input.jsonl
```
- Output
```json
{"context":null,"utterance":"ιƒ¨ε±‹γ«ε†·θ”΅εΊ«γŒγ‚γ‚‹γ¨θ‰―γ„γ€‚γƒ¬γƒ³γ‚Ώγ‚«γƒΌγ‚΅γƒΌγƒ“γ‚ΉγŒγ‚γ‚‹γƒ›γƒ†γƒ«γ‚’γ€customerγ€‘γŒεΈŒζœ›γ™γ‚‹γ€‚","sentences":null,"meta":{}}
```
3. Feed it to Pilota
- Command
```console
pilota -m megagonlabs/pilota_scud2query --batch_size 1 --outlen 60 --nbest 1 --beam 5 < input.jsonl
```
- Output (Formatted by ``jq .``)
```json
[
{
"scuds_nbest": [
[
"ιƒ¨ε±‹γ«ε†·θ”΅εΊ«γŒγ‚γ‚‹γ€‚"
]
],
"original_ranks": [
0
],
"scores": [
0.9769772589206696
],
"scores_detail": [
{
"OK": 0.9232575297355652,
"incorrect_none": 0.0034886503126472235,
"lack": 0.023772092536091805,
"limited": 0.013821585103869438,
"untruth": 0.04332486167550087
}
],
"sentence": "ιƒ¨ε±‹γ«ε†·θ”΅εΊ«γŒγ‚γ‚‹γ¨θ‰―γ„γ€‚"
},
{
"scuds_nbest": [
[
"γƒ¬γƒ³γ‚Ώγ‚«γƒΌγ‚΅γƒΌγƒ“γ‚ΉγŒγ‚γ‚‹γƒ›γƒ†γƒ«γ γ€‚"
]
],
"original_ranks": [
0
],
"scores": [
0.9876023113727569
],
"scores_detail": [
{
"OK": 0.9586743712425232,
"incorrect_none": 0.004059707745909691,
"lack": 0.0024317132774740458,
"limited": 0.007630097679793835,
"untruth": 0.04025880992412567
}
],
"sentence": "γƒ¬γƒ³γ‚Ώγ‚«γƒΌγ‚΅γƒΌγƒ“γ‚ΉγŒγ‚γ‚‹γƒ›γƒ†γƒ«γ‚’γ€customerγ€‘γŒεΈŒζœ›γ™γ‚‹γ€‚"
}
]
```
## License
Apache License 2.0