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.
- Downloads last month
- 134
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for cpayne1303/llama-43m-beta
Base model
JackFram/llama-68m