Mistral-7b with continued pretraining using Quiet-STaR (https://arxiv.org/abs/2403.09629) for generating 8 thought tokens before each output token.
Forked from Crystalcareai/Quiet-Star-Custom
- Downloads last month
- 0
Mistral-7b with continued pretraining using Quiet-STaR (https://arxiv.org/abs/2403.09629) for generating 8 thought tokens before each output token.
Forked from Crystalcareai/Quiet-Star-Custom