Transformers
PyTorch
Chinese
mt5
text2text-generation
mt5-small
natural language understanding
conversational system
task-oriented dialog
Eval Results (legacy)
Instructions to use ConvLab/mt5-small-nlu-all-crosswoz with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ConvLab/mt5-small-nlu-all-crosswoz with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("ConvLab/mt5-small-nlu-all-crosswoz") model = AutoModelForSeq2SeqLM.from_pretrained("ConvLab/mt5-small-nlu-all-crosswoz", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "additional_special_tokens": null, | |
| "eos_token": "</s>", | |
| "extra_ids": 0, | |
| "name_or_path": "/data/zhuqi/pre-trained-models/mt5-small", | |
| "pad_token": "<pad>", | |
| "sp_model_kwargs": {}, | |
| "special_tokens_map_file": "/data/zhuqi/pre-trained-models/mt5-small/special_tokens_map.json", | |
| "tokenizer_class": "T5Tokenizer", | |
| "truncation_side": "left", | |
| "unk_token": "<unk>" | |
| } | |