Instructions to use voidful/Llama-Typhoon-8B-R1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use voidful/Llama-Typhoon-8B-R1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="voidful/Llama-Typhoon-8B-R1", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("voidful/Llama-Typhoon-8B-R1", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
Should <think> token included in assistant prompt?
#1 opened about 1 year ago
by
theblackcat102