YAML Metadata
Warning:
The pipeline tag "text2text-generation" is not in the official list: text-classification, token-classification, table-question-answering, question-answering, zero-shot-classification, translation, summarization, feature-extraction, text-generation, fill-mask, sentence-similarity, text-to-speech, text-to-audio, automatic-speech-recognition, audio-to-audio, audio-classification, audio-text-to-text, voice-activity-detection, depth-estimation, image-classification, object-detection, image-segmentation, text-to-image, image-to-text, image-to-image, image-to-video, unconditional-image-generation, video-classification, reinforcement-learning, robotics, tabular-classification, tabular-regression, tabular-to-text, table-to-text, multiple-choice, text-ranking, text-retrieval, time-series-forecasting, text-to-video, image-text-to-text, visual-question-answering, document-question-answering, zero-shot-image-classification, graph-ml, mask-generation, zero-shot-object-detection, text-to-3d, image-to-3d, image-feature-extraction, video-text-to-text, keypoint-detection, visual-document-retrieval, any-to-any, video-to-video, other
FLAN T5
FLAN T5λ paust/pko-t5-large λͺ¨λΈμ κΈ°λ°μΌλ‘ λ€μν νμ€ν¬λ₯Ό instruction finetuningμ ν΅ν΄μ λ§λ λͺ¨λΈμ λλ€.
νμ¬ κ³μ Instruction Finetuning μ μ§ννλ©΄μ μ€κ°κ²°κ³Όλ₯Ό λͺ¨λΈλ‘ μ λ°μ΄νΈνκ³ μμ΅λλ€.
νμ΅λ νμ€ν¬
| Task name | Task type |
|---|---|
| NSMC | Classification |
| Klue Ynat | Classification |
| KorNLI | Classification |
| KorSTS | Classification |
| QuestionPair | Classification |
| Klue STS | Classification |
| AIHub news Summary | Summarization |
| AIHub document Summary | Summarization |
| AIHub book Summary | Summarization |
| AIHub conversation Summary | Summarization |
| AIHub ko-to-en | Translation |
| AIHub ko-to-en Expert | Translation |
| AIHub ko-to-en Tech | Translation |
| AIHub ko-to-en social | Translation |
| AIHub ko-to-jp | Translation |
| AIHub ko-to-cn Tech | Translation |
| AIHub Translation Corpus | Translation |
| korquad | QA |
| Klue MRC | QA |
| AIHub mindslab's MRC | QA |
λͺ¨λΈ
μ¬μ© μμ
from transformers import T5ForConditionalGeneration, T5TokenizerFast
tokenizer = T5TokenizerFast.from_pretrained('paust/pko-flan-t5-large')
model = T5ForConditionalGeneration.from_pretrained('paust/pko-flan-t5-large', device_map='cuda')
prompt = """μμΈνΉλ³μ(μμΈηΉε₯εΈ, μμ΄: Seoul Metropolitan Government)λ λνλ―Όκ΅ μλμ΄μ μ΅λ λμμ΄λ€. μ μ¬μλλΆν° μ¬λμ΄ κ±°μ£ΌνμμΌλ λ³Έ μμ¬λ λ°±μ 첫 μλ μλ‘μ±μ μμ΄λ‘ νλ€. μΌκ΅μλμλ μ λ΅μ μμΆ©μ§λ‘μ κ³ κ΅¬λ €, λ°±μ , μ λΌκ° λ²κ°μ μ°¨μ§νμμΌλ©°, κ³ λ € μλμλ μμ€μ λ³κΆμ΄ μΈμμ§ λ¨κ²½(εδΊ¬)μΌλ‘ μ΄λ¦νμλ€.
νκ΅μ μλλ μ΄λμ
λκΉ?"""
input_ids = tokenizer(prompt, add_special_tokens=True, return_tensors='pt').input_ids
output_ids = model.generate(input_ids=input_ids.cuda(), max_new_tokens=32, num_beams=12)
text = tokenizer.batch_decode(output_ids, skip_special_tokens=True)[0]
print(text) # μμΈνΉλ³μ
License
PAUSTμμ λ§λ pko-t5λ MIT license νμ 곡κ°λμ΄ μμ΅λλ€.
- Downloads last month
- 80