1
1

Delete article

Deleted articles cannot be recovered.

Draft of this article would be also deleted.

Are you sure you want to delete this article?

introduction

Hugging Face って何ですか
https://qiita.com/tadokuno/items/c4536dea7f629d37549c

Hugging Face transformersドキュメントのまとめページ
https://qiita.com/taka_yayoi/items/155f97efbff594df4386

AIプラットフォーム「Hugging Face」の使い方を解説
https://qiita.com/SAKUBUN/items/d02dd7288fbda01995ed

初心者でもわかる!Hugging Faceを使いこなして、RAG風プロンプトエンジニアリングで精度UPする方法
https://qiita.com/ryo18/items/251f5a7baa745e982526

Llama 2向けのDatasetsを作成してHugging Faceに登録するまで
https://qiita.com/yn01/items/54f7ceb4edfaba119d34

Hugging Face Spacesで、plumberで作成したWeb APIをホストする方法
https://qiita.com/Yuuki-Osada/items/72644b62d5a7d1e19eda

Hugging Faceのssh鍵の作り方
https://qiita.com/mae616/items/bbf35f97396301ac2e6d

Otehrs

Hugging Faceで独自データセットを使う
https://qiita.com/izaki_shin/items/70d4c51618c068fbb7a7

Hugging Face CI/CDにおけるエラー解消: Git LFS設定と画像ファイルの履歴削除
https://qiita.com/Maki-HamarukiLab/items/9c2e7da8e4b153307ea4

Hugging Face からのモデルのダウンロード
https://qiita.com/mizutan/items/e79f3ef6b8b833891ee3

Hugging Faceのライブラリを使ってTokenize
https://qiita.com/ishikawa-takumi/items/5fc45ddd121b23db5de9

Hugging Face 画像生成
https://qiita.com/miketorii/items/b559b56b85ab443772fc

Hugging Face🤗の拡散モデル入門
https://qiita.com/hotekagi/items/5afabf5945f125020eb1

Databricks ❤️ Hugging Face
https://qiita.com/taka_yayoi/items/665da50ddf7920d33677

Hugging Faceトランスフォーマーパイプラインを用いてNLPをスタートする
https://qiita.com/taka_yayoi/items/f0540a29b3cfa9868585

Hugging Faceのdbrx-instructを動かしてみる
https://qiita.com/taka_yayoi/items/c67b3f5fb168342a4b90

Hugging FaceとDeepSpeedによる大規模言語モデルのファインチューニング
https://qiita.com/taka_yayoi/items/fadf3ce5b3d4e954ef83

サクッと API を作ろう|FastAPI, Hugging Face,Docker,Python
https://qiita.com/tregu148/items/73045efce0a6216e1cd9

Reference

[翻訳] Hugging Face transformersのクイックスタート
https://qiita.com/taka_yayoi/items/f3c74c8a242368412615

[翻訳] Hugging Face transformersの推論パイプライン
https://qiita.com/taka_yayoi/items/fe841afc78c27b153b44

[翻訳] Hugging Face transformersにおけるAutoClassを用いた事前学習済みインスタンスのロード
https://qiita.com/taka_yayoi/items/af736dd515c0d12faaf7

[翻訳] Hugging Face transformersにおける前処理
https://qiita.com/taka_yayoi/items/d6300140765b9b1406c5

[翻訳] Hugging Face transformersにおける事前学習済みモデルのファインチューン
https://qiita.com/taka_yayoi/items/597c6b1c36abaf9c1b3c

[翻訳] Hugging Face transformersにおける質問応答
https://qiita.com/taka_yayoi/items/044caf839e83b210042b

[翻訳] Hugging faceのPEFTのクイックツアー
https://qiita.com/taka_yayoi/items/9196444274d6a63cda76

model.save_pretrained("output_dir")
# if pushing to Hub
from huggingface_hub import notebook_login
notebook_login()
model.push_to_hub("my_awesome_peft_model")
  from transformers import AutoModelForSeq2SeqLM
+ from peft import PeftModel, PeftConfig

+ peft_model_id = "smangrul/twitter_complaints_bigscience_T0_3B_LORA_SEQ_2_SEQ_LM"
+ config = PeftConfig.from_pretrained(peft_model_id)
  model = AutoModelForSeq2SeqLM.from_pretrained(config.base_model_name_or_path)
+ model = PeftModel.from_pretrained(model, peft_model_id)
  tokenizer = AutoTokenizer.from_pretrained(config.base_model_name_or_path)

  model = model.to(device)
  model.eval()
  inputs = tokenizer("Tweet text : @HondaCustSvc Your customer service has been horrible during the recall process. I will never purchase a Honda again. Label :", return_tensors="pt")

  with torch.no_grad():
      outputs = model.generate(input_ids=inputs["input_ids"].to("cuda"), max_new_tokens=10)
      print(tokenizer.batch_decode(outputs.detach().cpu().numpy(), skip_special_tokens=True)[0])
  'complaint'

[翻訳] Hugging FaceのマルチGPUにおける効率的なトレーニング
https://qiita.com/taka_yayoi/items/ecf3564d62b3c1d1e1cb

[翻訳] Hugging faceのPEFT
https://qiita.com/taka_yayoi/items/67950183d32b112246ba

Related document

DatabricksとHugging Faceを用いた保険Q&Aにおける意図分類
https://qiita.com/taka_yayoi/items/ad1d8970606048e0a0fb

Hugging Face、Databricksモデルサービング、Databricks Appsによるインペイントアプリの構築
https://qiita.com/taka_yayoi/items/9a7be741b08bfec41d5e

DatabricksにおけるHugging Faceモデルの分散ファインチューニング
https://qiita.com/taka_yayoi/items/fdf409f2cf6e7e1f7f22

DatabricksにおけるシングルGPUにおけるHugging Faceモデルのファインチューニング
https://qiita.com/taka_yayoi/items/755d1e52b6b07b760ebe

atabricksモデルサービングによるHugging Face transformersモデルのデプロイ
https://qiita.com/taka_yayoi/items/aebac893b1c2f73245eb

MLflow 2.3のHugging Faceトランスフォーマーのサポートを試す
https://qiita.com/taka_yayoi/items/ad370a7f57c4eae58800

Hugging Face Diffusers、Databricks Appsとモデルサービングで構築する顔ハメ看板アプリ
https://qiita.com/taka_yayoi/items/9ef95cb2f39fddd047af

LoRAによる効率的なファインチューニング:大規模言語モデルにおける最適パラメータ選択のガイド
https://qiita.com/taka_yayoi/items/7f50d3ebbe4bebd6877c

1
1
0

Register as a new user and use Qiita more conveniently

  1. You get articles that match your needs
  2. You can efficiently read back useful information
  3. You can use dark theme
What you can do with signing up
1
1

Delete article

Deleted articles cannot be recovered.

Draft of this article would be also deleted.

Are you sure you want to delete this article?