Instructions to use staka/fugumt-en-ja with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use staka/fugumt-en-ja with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "translation" 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("translation", model="staka/fugumt-en-ja")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("staka/fugumt-en-ja") model = AutoModelForSeq2SeqLM.from_pretrained("staka/fugumt-en-ja", device_map="auto") - Inference
- Notebooks
- Google Colab
- Kaggle
Download generation_config.json from staka/fugumt-en-ja: direct link, hf CLI and curl.
- Browser
- Download file 289 Bytes
-
https://huggingface.co/staka/fugumt-en-ja/resolve/main/generation_config.json
- Command line
-
hf download hf://staka/fugumt-en-ja/generation_config.json
-
curl -L -o generation_config.json https://huggingface.co/staka/fugumt-en-ja/resolve/main/generation_config.json
289 Bytes
| { | |
| "_from_model_config": true, | |
| "bad_words_ids": [ | |
| [ | |
| 32000 | |
| ] | |
| ], | |
| "bos_token_id": 0, | |
| "decoder_start_token_id": 32000, | |
| "eos_token_id": 0, | |
| "forced_eos_token_id": 0, | |
| "max_length": 512, | |
| "num_beams": 12, | |
| "pad_token_id": 32000, | |
| "transformers_version": "4.30.0" | |
| } | |