Instructions to use hai2131/sailor2-test with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use hai2131/sailor2-test with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, QwenCrossAttentionEncDec tokenizer = AutoTokenizer.from_pretrained("hai2131/sailor2-test") model = QwenCrossAttentionEncDec.from_pretrained("hai2131/sailor2-test", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download generation_config.json from hai2131/sailor2-test: direct link, hf CLI and curl.
- Browser
- Download file 179 Bytes
-
https://huggingface.co/hai2131/sailor2-test/resolve/main/generation_config.json
- Command line
-
hf download hf://hai2131/sailor2-test/generation_config.json
-
curl -L -o generation_config.json https://huggingface.co/hai2131/sailor2-test/resolve/main/generation_config.json
179 Bytes
| { | |
| "_from_model_config": true, | |
| "bos_token_id": 151643, | |
| "decoder_start_token_id": 151643, | |
| "eos_token_id": 151645, | |
| "transformers_version": "4.56.0", | |
| "use_cache": false | |
| } | |