Standalone tree split from LLMRL/projects/kda. Includes Triton dt_bias backward fix, train_k3 --preset 0.5b, SFT, Docker runtime, and tests.
7 lines
121 B
Python
7 lines
121 B
Python
"""Toy causal-language-model training loop."""
|
|
|
|
from kda.training.toy import main
|
|
|
|
if __name__ == "__main__":
|
|
main()
|