Instructions to use TRI-ML/DCLM-1B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use TRI-ML/DCLM-1B with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("TRI-ML/DCLM-1B", dtype="auto") - Notebooks
- Google Colab
- Kaggle
Is this model supported for finetuning with flash attention ?
#4 opened 11 months ago
by
thaodd11
MMLU Performance After Token Training
👍 2
#3 opened over 1 year ago
by
adol01