CODI: Compressing Chain-of-Thought into Continuous Space via Self-Distillation
Paper
•
2502.21074
•
Published
•
4
The official weight of LLaMA-3.2-1b-Instruct trained with the CODI framework (https://arxiv.org/abs/2502.21074).
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for zen-E/CODI-llama3.2-1b-Instruct
Base model
meta-llama/Llama-3.2-1B-Instruct