Instructions to use Synth-Ecosystem/synthos with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Synth-Ecosystem/synthos with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Synth-Ecosystem/synthos", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download tokenizer_config.json from Synth-Ecosystem/synthos: direct link, hf CLI and curl.
- Browser
- Download file 499 Bytes
-
https://huggingface.co/Synth-Ecosystem/synthos/resolve/main/tokenizer_config.json
- Command line
-
hf download hf://Synth-Ecosystem/synthos/tokenizer_config.json
-
curl -L -o tokenizer_config.json https://huggingface.co/Synth-Ecosystem/synthos/resolve/main/tokenizer_config.json
499 Bytes
| { | |
| "add_prefix_space": null, | |
| "backend": "tokenizers", | |
| "bos_token": null, | |
| "clean_up_tokenization_spaces": false, | |
| "do_lower_case": false, | |
| "eos_token": "<|endoftext|>", | |
| "extra_special_tokens": [], | |
| "image_size": 448, | |
| "is_local": true, | |
| "model_input_names": [ | |
| "input_ids", | |
| "attention_mask" | |
| ], | |
| "model_max_length": 8192, | |
| "pad_token": "<|endoftext|>", | |
| "padding_side": "left", | |
| "remove_space": false, | |
| "tokenizer_class": "Qwen2Tokenizer", | |
| "unk_token": "<|endoftext|>" | |
| } | |