Instructions to use city96/mt5-xl-encoder-fp16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use city96/mt5-xl-encoder-fp16 with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("city96/mt5-xl-encoder-fp16") model = AutoModel.from_pretrained("city96/mt5-xl-encoder-fp16", device_map="auto") - Notebooks
- Google Colab
- Kaggle
|
Download README.md from city96/mt5-xl-encoder-fp16: direct link, hf CLI and curl.
- Browser
- Download file 449 Bytes
-
https://huggingface.co/city96/mt5-xl-encoder-fp16/resolve/main/README.md
- Command line
-
hf download hf://city96/mt5-xl-encoder-fp16/README.md
-
curl -L -o README.md https://huggingface.co/city96/mt5-xl-encoder-fp16/resolve/main/README.md
449 Bytes
metadata
license: apache-2.0
This is a fp16 safetensors version of Google's mT5-xl model to be used in downstream inference tasks.
This repository only contains the encoder part of the model. For the full model, use the following repository: city96/mt5-xl-fp16
This model is meant to be used with HunYuanDiT.