Instructions to use microsoft/prophetnet-large-uncased with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use microsoft/prophetnet-large-uncased with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("microsoft/prophetnet-large-uncased") model = AutoModelForSeq2SeqLM.from_pretrained("microsoft/prophetnet-large-uncased", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download generation_config.json from microsoft/prophetnet-large-uncased: direct link, hf CLI and curl.
- Browser
- Download file 293 Bytes
-
https://huggingface.co/microsoft/prophetnet-large-uncased/resolve/2a3eff1ed3ca8dbdd46f5e57b9742fb73009c7a5/generation_config.json
- Command line
-
hf download hf://microsoft/prophetnet-large-uncased@2a3eff1ed3ca8dbdd46f5e57b9742fb73009c7a5/generation_config.json
-
curl -L -o generation_config.json https://huggingface.co/microsoft/prophetnet-large-uncased/resolve/2a3eff1ed3ca8dbdd46f5e57b9742fb73009c7a5/generation_config.json
293 Bytes
| { | |
| "_from_model_config": true, | |
| "bos_token_id": 102, | |
| "decoder_start_token_id": 102, | |
| "early_stopping": true, | |
| "eos_token_id": 102, | |
| "length_penalty": 2.0, | |
| "max_length": 142, | |
| "no_repeat_ngram_size": 3, | |
| "num_beams": 4, | |
| "pad_token_id": 0, | |
| "transformers_version": "4.27.0.dev0" | |
| } | |