Instructions to use city96/mt5-xl-fp16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use city96/mt5-xl-fp16 with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("city96/mt5-xl-fp16") model = AutoModelForSeq2SeqLM.from_pretrained("city96/mt5-xl-fp16", device_map="auto") - Notebooks
- Google Colab
- Kaggle
File size: 378 Bytes
ee2fd80 3f75a62 | 1 2 3 4 5 6 7 | ---
license: apache-2.0
---
This is a fp16 safetensors version of [Google's mT5-xl model](https://huggingface.co/google/mt5-xl) to be used in downstream inference tasks.
This repository contains both the encoder and decoder part of the model. For just the encoder, use the following repository: [`city96/mt5-xl-encoder-fp16`](https://huggingface.co/city96/mt5-xl-encoder-fp16)
|