Instructions to use inference-optimization/Kimi-K3-0.40B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use inference-optimization/Kimi-K3-0.40B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="inference-optimization/Kimi-K3-0.40B", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("inference-optimization/Kimi-K3-0.40B", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Model's having a fetish about Jedi starwar
#1
by gthell - opened
"Hiis The Wise? I thought not. It's not a story the Jedi would tell you. It's a Sith legend. Darth Plagueis was a Dark Lord of the Sith. the not a story the Jedi would tell you. It's a Sith legend. Darth Plagueis was a Dark Lord of the Sith. the not a story the Jedi would tell you. It's a Sith legend. Darth Plagueis was a Dark Lord of the Sith."
🤣 @gthell this is a super tiny minimized version of Kimi K3 that we use for dev/testing purposes. It is not recommended for public use. We use these smaller checkpoints to validate compression flows to create actual models for users -- https://huggingface.co/RedHatAI/Kimi-K3-FP8-BLOCK