Instructions to use shed-e/Summary with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use shed-e/Summary 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="shed-e/Summary")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("shed-e/Summary") model = AutoModelForSeq2SeqLM.from_pretrained("shed-e/Summary", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download tokenizer_config.json from shed-e/Summary: direct link, hf CLI and curl.
- Browser
- Download file 428 Bytes
-
https://huggingface.co/shed-e/Summary/resolve/refs%2Fpr%2F2/tokenizer_config.json
- Command line
-
hf download hf://shed-e/Summary@refs/pr/2/tokenizer_config.json
-
curl -L -o tokenizer_config.json https://huggingface.co/shed-e/Summary/resolve/refs%2Fpr%2F2/tokenizer_config.json
428 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/transformers/685ac0ca8568ec593a48b61b0a3c272beee9bc194a3c7241d15dcadb5f875e53.f76030f3ec1b96a8199b2593390c610e76ca8028ef3d24680000619ffb646276", | |
| "tokenizer_class": "T5Tokenizer", | |
| "unk_token": "<unk>" | |
| } | |