Instructions to use mogesa/amharic_summarization_mt5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mogesa/amharic_summarization_mt5 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="mogesa/amharic_summarization_mt5")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("mogesa/amharic_summarization_mt5") model = AutoModelForSeq2SeqLM.from_pretrained("mogesa/amharic_summarization_mt5", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download training_args.bin from mogesa/amharic_summarization_mt5: direct link, hf CLI and curl.
- Browser
- Download file 3.71 kB
-
https://huggingface.co/mogesa/amharic_summarization_mt5/resolve/main/training_args.bin
- Command line
-
hf download hf://mogesa/amharic_summarization_mt5/training_args.bin
-
curl -L -o training_args.bin https://huggingface.co/mogesa/amharic_summarization_mt5/resolve/main/training_args.bin
3.71 kB
- Xet hash:
- 0641fba8a5bf476d48f157e3c0bea91ae7e304cbae7dea85ed6a55247ae5f1eb
- Size of remote file:
- 3.71 kB
- SHA256:
- 1b1ceafe9094be3e0a1334791c25503e93bfe7c48a2ea04328ddb88b1d6e4dae
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.