dela
584f7e9e73
Standalone tree split from LLMRL/projects/kda. Includes Triton dt_bias backward fix, train_k3 --preset 0.5b, SFT, Docker runtime, and tests.
2 lines
67 B
Plaintext
2 lines
67 B
Plaintext
# Mount bilingual pretrain shards here (not baked into the image).
|