Instructions to use leafyseay/LaME-2B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use leafyseay/LaME-2B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="leafyseay/LaME-2B")# pip install -U transformers accelerate # Load model directly from transformers import LaMEMultimodal model = LaMEMultimodal.from_pretrained("leafyseay/LaME-2B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download tokenizer.json from leafyseay/LaME-2B: direct link, hf CLI and curl.
- Browser
- Download file 11.4 MB
-
https://huggingface.co/leafyseay/LaME-2B/resolve/main/tokenizer.json
- Command line
-
hf download hf://leafyseay/LaME-2B/tokenizer.json
-
curl -L -o tokenizer.json https://huggingface.co/leafyseay/LaME-2B/resolve/main/tokenizer.json
11.4 MB
- Xet hash:
- 43db41f337fe2f55143c333528e26d019c6b4a3c79f1a0d1ebf0ad453bb0e178
- Size of remote file:
- 11.4 MB
- SHA256:
- adc6cd196ef9dad618795deafb95ae56fc64ee666216e71d1616f32be0c487b3
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.