Instructions to use pk4041/summarize2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use pk4041/summarize2 with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("pk4041/summarize2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Unsloth Desktop
Download tokenizer_config.json from pk4041/summarize2: direct link, hf CLI and curl.
- Browser
- Download file 395 Bytes
-
https://huggingface.co/pk4041/summarize2/resolve/main/tokenizer_config.json
- Command line
-
hf download hf://pk4041/summarize2/tokenizer_config.json
-
curl -L -o tokenizer_config.json https://huggingface.co/pk4041/summarize2/resolve/main/tokenizer_config.json
395 Bytes
| { | |
| "backend": "tokenizers", | |
| "bos_token": "<|begin_of_text|>", | |
| "clean_up_tokenization_spaces": true, | |
| "eos_token": "<|eot_id|>", | |
| "from_slow": true, | |
| "is_local": false, | |
| "legacy": false, | |
| "model_input_names": [ | |
| "input_ids", | |
| "attention_mask" | |
| ], | |
| "model_max_length": 8192, | |
| "pad_token": "<|end_of_text|>", | |
| "padding_side": "right", | |
| "tokenizer_class": "TokenizersBackend" | |
| } | |