Summarization
Transformers
PyTorch
Safetensors
Korean
t5
text2text-generation
text-generation-inference
Instructions to use psyche/KoT5-summarization with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use psyche/KoT5-summarization with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "summarization" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # 'pip install "transformers<5.0.0' from transformers import pipeline pipe = pipeline("summarization", model="psyche/KoT5-summarization")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("psyche/KoT5-summarization") model = AutoModelForSeq2SeqLM.from_pretrained("psyche/KoT5-summarization") - Notebooks
- Google Colab
- Kaggle
| model | sampling | ROUGE-1 (β) | ROUGE-2 (β) | ROUGE-L (β) |
|---|---|---|---|---|
| - | - | - | - | - |
| ours | greedy | 49.87 | 34.44 | 41.65 |
| ainize/kobart-news | greedy | 42.35 | 23.27 | 32.61 |
| gogamza/kobart-summarization | greedy | 39.92 | 25.26 | 33.86 |
| noahkim/KoT5_new_summarization | greedy | 40.75 | 19.60 | 29.44 |
- greedy λ μ΅λκΈΈμ΄ μ ν(max_length=256)κ³Ό repetition_penalty=2.0μΌλ‘ λ¨μ μνλ§ν λ°©λ²μ μλ―Έν©λλ€.
More Information of KoT5
- Downloads last month
- 125