Instructions to use mqy/mt5-small with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mqy/mt5-small 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="mqy/mt5-small")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("mqy/mt5-small") model = AutoModelForSeq2SeqLM.from_pretrained("mqy/mt5-small", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download pytorch_model.bin from mqy/mt5-small: direct link, hf CLI and curl.
- Browser
- Download file 1.2 GB
-
https://huggingface.co/mqy/mt5-small/resolve/main/pytorch_model.bin
- Command line
-
hf download hf://mqy/mt5-small/pytorch_model.bin
-
curl -L -o pytorch_model.bin https://huggingface.co/mqy/mt5-small/resolve/main/pytorch_model.bin
1.2 GB
- Xet hash:
- 0d63bbdd47c8599fe5d2a05fa1034a145021d6e279b0a21d5d6315ec931166f2
- Size of remote file:
- 1.2 GB
- SHA256:
- 8b419fc1e9c761ff1377ef07fb9b081dc6086900336e133935c0de265a0d99a0
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.