Compare commits

...

2 Commits

Author SHA1 Message Date
Dennis Jaheruddin
1334687cf6
Merge 8f014f6822 into d6d9447e2d 2024-03-18 11:40:04 -07:00
Dennis Jaheruddin
8f014f6822
Update README.md to avoid wrong hardware expectations 2024-03-18 18:52:34 +01:00

View File

@ -15,7 +15,7 @@ to test the code.
The script loads the checkpoint and samples from the model on a test input. 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. 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 # Model Specifications