Files
transformers/docs/source/ja/model_doc/blenderbot.md
陈赣 06f1fd69a6
Some checks failed
Self-hosted runner (nightly-past-ci-caller) / Get number (push) Has been cancelled
Self-hosted runner (nightly-past-ci-caller) / TensorFlow 2.11 (push) Has been cancelled
Self-hosted runner (nightly-past-ci-caller) / TensorFlow 2.10 (push) Has been cancelled
Self-hosted runner (nightly-past-ci-caller) / TensorFlow 2.9 (push) Has been cancelled
Self-hosted runner (nightly-past-ci-caller) / TensorFlow 2.8 (push) Has been cancelled
Self-hosted runner (nightly-past-ci-caller) / TensorFlow 2.7 (push) Has been cancelled
Self-hosted runner (nightly-past-ci-caller) / TensorFlow 2.6 (push) Has been cancelled
Self-hosted runner (nightly-past-ci-caller) / TensorFlow 2.5 (push) Has been cancelled
Self-hosted runner (benchmark) / Benchmark (aws-g5-4xlarge-cache) (push) Has been cancelled
Build documentation / build (push) Has been cancelled
Build documentation / build_other_lang (push) Has been cancelled
CodeQL Security Analysis / CodeQL Analysis (push) Has been cancelled
New model PR merged notification / Notify new model (push) Has been cancelled
PR CI / pr-ci (push) Has been cancelled
Slow tests on important models (on Push - A10) / Get all modified files (push) Has been cancelled
Secret Leaks / trufflehog (push) Has been cancelled
Update Transformers metadata / build_and_package (push) Has been cancelled
Slow tests on important models (on Push - A10) / Model CI (push) Has been cancelled
Check Tiny Models / Check tiny models (push) Has been cancelled
Self-hosted runner (Intel Gaudi3 scheduled CI caller) / Model CI (push) Has been cancelled
Self-hosted runner (Intel Gaudi3 scheduled CI caller) / Pipeline CI (push) Has been cancelled
Self-hosted runner (Intel Gaudi3 scheduled CI caller) / Example CI (push) Has been cancelled
Self-hosted runner (Intel Gaudi3 scheduled CI caller) / DeepSpeed CI (push) Has been cancelled
Self-hosted runner (Intel Gaudi3 scheduled CI caller) / Trainer/FSDP CI (push) Has been cancelled
Nvidia CI - Flash Attn / Setup (push) Has been cancelled
Nvidia CI - Flash Attn / Model CI (push) Has been cancelled
Nvidia CI / Setup (push) Has been cancelled
Nvidia CI / Model CI (push) Has been cancelled
Nvidia CI / Torch pipeline CI (push) Has been cancelled
Nvidia CI / Example CI (push) Has been cancelled
Nvidia CI / Trainer/FSDP CI (push) Has been cancelled
Nvidia CI / DeepSpeed CI (push) Has been cancelled
Nvidia CI / Quantization CI (push) Has been cancelled
Nvidia CI / Kernels CI (push) Has been cancelled
Doctests / Setup (push) Has been cancelled
Doctests / Call doctest jobs (push) Has been cancelled
Doctests / Send results to webhook (push) Has been cancelled
Extras Smoke Test / Get supported Python versions (push) Has been cancelled
Extras Smoke Test / Test extras on Python ${{ matrix.python-version }} (push) Has been cancelled
Extras Smoke Test / Check Slack token availability (push) Has been cancelled
Extras Smoke Test / Notify failures to Slack (push) Has been cancelled
Self-hosted runner (AMD scheduled CI caller) / Trigger Scheduled AMD CI (push) Has been cancelled
Stale Bot / Close Stale Issues (push) Has been cancelled
first commit
2026-06-05 16:53:03 +08:00

5.3 KiB

Blenderbot

免責事項: 何か奇妙なものを見つけた場合は、 Github Issue を報告してください。

Overview

Blender チャットボット モデルは、Recipes for building an open-domain chatbot Stephen Roller、Emily Dinan、Naman Goyal、Da Ju、Mary Williamson、yinghan Liu、で提案されました。 ジン・シュー、マイル・オット、カート・シャスター、エリック・M・スミス、Y-ラン・ブーロー、ジェイソン・ウェストン、2020年4月30日。

論文の要旨は次のとおりです。

オープンドメインのチャットボットの構築は、機械学習研究にとって難しい分野です。これまでの研究では次のことが示されていますが、 ニューラル モデルをパラメーターの数とトレーニング対象のデータのサイズでスケーリングすると、結果が向上します。 高性能のチャットボットには他の要素も重要であることを示します。良い会話には多くのことが必要です 会話の専門家がシームレスに融合するスキル: 魅力的な話のポイントを提供し、話を聞く 一貫した態度を維持しながら、知識、共感、個性を適切に表現する ペルソナ。適切なトレーニング データと選択が与えられた場合、大規模モデルがこれらのスキルを学習できることを示します。 世代戦略。 90M、2.7B、9.4B パラメーター モデルを使用してこれらのレシピのバリアントを構築し、モデルを作成します。 コードは公開されています。人間による評価では、当社の最良のモデルが既存のアプローチよりも優れていることがマルチターンで示されています 魅力と人間性の測定という観点からの対話。次に、分析によってこの作業の限界について説明します。 弊社機種の故障事例

チップ:

  • Blenderbot は絶対位置埋め込みを備えたモデルであるため、通常は入力を右側にパディングすることをお勧めします。 左。

このモデルは sshleifer によって提供されました。著者のコードは ここ にあります。

Implementation Notes

  • Blenderbot は、標準の seq2seq モデル トランスフォーマー ベースのアーキテクチャを使用します。
  • 利用可能なチェックポイントは、モデル ハブ で見つけることができます。
  • これは デフォルト Blenderbot モデル クラスです。ただし、次のような小さなチェックポイントもいくつかあります。 facebook/blenderbot_small_90M はアーキテクチャが異なるため、一緒に使用する必要があります。 BlenderbotSmall

Usage

モデルの使用例を次に示します。

>>> from transformers import BlenderbotTokenizer, BlenderbotForConditionalGeneration

>>> mname = "facebook/blenderbot-400M-distill"
>>> model = BlenderbotForConditionalGeneration.from_pretrained(mname)
>>> tokenizer = BlenderbotTokenizer.from_pretrained(mname)
>>> UTTERANCE = "My friends are cool but they eat too many carbs."
>>> inputs = tokenizer([UTTERANCE], return_tensors="pt")
>>> reply_ids = model.generate(**inputs)
>>> print(tokenizer.batch_decode(reply_ids))
["<s> That's unfortunate. Are they trying to lose weight or are they just trying to be healthier?</s>"]

Documentation resources

BlenderbotConfig

autodoc BlenderbotConfig

BlenderbotTokenizer

autodoc BlenderbotTokenizer

BlenderbotTokenizerFast

autodoc BlenderbotTokenizerFast

BlenderbotModel

forward および generate の引数については、transformers.BartModelを参照してください。

autodoc BlenderbotModel - forward

BlenderbotForConditionalGeneration

forwardgenerate の引数については、[~transformers.BartForConditionalGeneration] を参照してください。

autodoc BlenderbotForConditionalGeneration - forward

BlenderbotForCausalLM

autodoc BlenderbotForCausalLM - forward