Summarization
Transformers
Safetensors
Russian
mt5
text2text-generation
summarizer
text-generation-inference
Instructions to use sarahai/ru-sum with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use sarahai/ru-sum 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="sarahai/ru-sum")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("sarahai/ru-sum") model = AutoModelForSeq2SeqLM.from_pretrained("sarahai/ru-sum", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download optimizer.pt from sarahai/ru-sum: direct link, hf CLI and curl.
- Browser
- Download file 2.4 GB
-
https://huggingface.co/sarahai/ru-sum/resolve/main/optimizer.pt
- Command line
-
hf download hf://sarahai/ru-sum/optimizer.pt
-
curl -L -o optimizer.pt https://huggingface.co/sarahai/ru-sum/resolve/main/optimizer.pt
2.4 GB
- Xet hash:
- 57f5391dee851cef38316a9b8e6fab9461f96715e5a9006d3ce12c11b4a1e8ac
- Size of remote file:
- 2.4 GB
- SHA256:
- 3b1ed8c97f1647d770ca95d871bcc4532177fcf5b1748e4a149cdaa171099404
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.