Instructions to use krm/BARTkrame-abstract-mT5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use krm/BARTkrame-abstract-mT5 with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "summarization" 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("summarization", model="krm/BARTkrame-abstract-mT5")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("krm/BARTkrame-abstract-mT5") model = AutoModelForSeq2SeqLM.from_pretrained("krm/BARTkrame-abstract-mT5", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download tokenizer_config.json from krm/BARTkrame-abstract-mT5: direct link, hf CLI and curl.
- Browser
- Download file 390 Bytes
-
https://huggingface.co/krm/BARTkrame-abstract-mT5/resolve/main/tokenizer_config.json
- Command line
-
hf download hf://krm/BARTkrame-abstract-mT5/tokenizer_config.json
-
curl -L -o tokenizer_config.json https://huggingface.co/krm/BARTkrame-abstract-mT5/resolve/main/tokenizer_config.json
390 Bytes
| { | |
| "additional_special_tokens": null, | |
| "eos_token": "</s>", | |
| "extra_ids": 0, | |
| "name_or_path": "google/mt5-small", | |
| "pad_token": "<pad>", | |
| "sp_model_kwargs": {}, | |
| "special_tokens_map_file": "/root/.cache/huggingface/hub/models--google--mt5-small/snapshots/f03a52d3eaa650878b6f52e443bc4d5b385e786e/special_tokens_map.json", | |
| "tokenizer_class": "T5Tokenizer", | |
| "unk_token": "<unk>" | |
| } | |