Update README.md to avoid wrong hardware expectations

This commit is contained in:
Dennis Jaheruddin 2024-03-18 18:52:34 +01:00 committed by GitHub
parent 310e19eee2
commit 8f014f6822
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194

View File

@ -15,7 +15,7 @@ to test the code.
The script loads the checkpoint and samples from the model on a test input.
Due to the large size of the model (314B parameters), a machine with enough GPU memory is required to test the model with the example code.
Due to the large size of the model (314B parameters), a machine with enough GPU memory (314GB+ vRAM) is required to test the model with the example code.
The implementation of the MoE layer in this repository is not efficient. The implementation was chosen to avoid the need for custom kernels to validate the correctness of the model.
# Model Specifications