Instructions to use OneThink/OneThinker-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use OneThink/OneThinker-8B with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("OneThink/OneThinker-8B") model = AutoModelForMultimodalLM.from_pretrained("OneThink/OneThinker-8B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download tokenizer.json from OneThink/OneThinker-8B: direct link, hf CLI and curl.
- Browser
- Download file 11.4 MB
-
https://huggingface.co/OneThink/OneThinker-8B/resolve/main/tokenizer.json
- Command line
-
hf download hf://OneThink/OneThinker-8B/tokenizer.json
-
curl -L -o tokenizer.json https://huggingface.co/OneThink/OneThinker-8B/resolve/main/tokenizer.json
11.4 MB
- Xet hash:
- 9ffb7683bd77a6dc2fb2ce617fae25c0340fac8c7b3a6bc20d62f4afdcb3025d
- Size of remote file:
- 11.4 MB
- SHA256:
- 3c3dfe474a8bbe89b0e83627fd9ff784ad71027f12fd8c618708c818e808789d
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.