Downloads · 30 days
77
1% of all-time downloads
ezelikman/quietstar-8-ahead
quietstar-8-ahead is a text generation model from ezelikman. Use it when you need the model to write or continue text. It is set up for transformers.
Mistral-7b with continued pretraining using Quiet-STaR (https://arxiv.org/abs/2403.09629) for generating 8 thought tokens before each output token.
Downloads · 30 days
77
1% of all-time downloads
All-time downloads
9.7K
Public
Parameters
7.3B
14.6 GB on disk
Likes
90
Public
Click a slice to open those files.
.safetensors14.6 GB · 100%
From the Hugging Face model README
Mistral-7b with continued pretraining using Quiet-STaR (https://arxiv.org/abs/2403.09629) for generating 8 thought tokens before each output token.