Mistral-7b with continued pretraining using Quiet-STaR (https://arxiv.org/abs/2403.09629) for generating 8 thought tokens before each output token.

Downloads last month
1,107
Safetensors
Model size
7.29B params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Dataset used to train Crystalcareai/Quiet-Star-Custom