llama-43m-beta / README.md
cpayne1303's picture
fixed model card
1f85bec
metadata
base_model: JackFram/llama-68m
language:
  - en
license: apache-2.0
library_name: transformers
datasets:
  - allenai/c4

Model Description

This model is based of llama-68m and was initialized from this model with tied embeddings and then further pretrained on the uncleaned c4 dataset. This model is obviously a beta based on the name and has not been trained on the full training set which is the first 1 million samples of the uncleaned c4 dataset as mentioned above.