Just Read Twice!
Collection
Here we provide models and benchmarks for the Just Read Twice work: https://arxiv.org/abs/2407.05483
•
16 items
•
Updated
Configuration Parsing
Warning:
In config.json: "architectures" must be an array
Model Card
This model is an Attention (Llama architecture) model pretrained on 30Bn tokens of the Pile corpus.
Model Sources
The model implementation and training code that produced the model are provided here: https://github.com/HazyResearch/based
- Downloads last month
- 5