We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent 5ce829b commit cf57c28Copy full SHA for cf57c28
examples/deepseek_v3/run_pretrain.sh
@@ -17,7 +17,7 @@ pushd "${MEGATRON_PATH}/megatron/core/datasets" && make && popd || exit 1
17
# avaliable model configs:
18
# deepseek_v2_lite, deepseek_v2
19
# deepseek_v3, deepseek_v3_17B, deepseek_v3_45B
20
-export MODEL_CONFIG=deepseek_v3_17B
+export MODEL_CONFIG=deepseek_v2_lite
21
22
# network envs
23
export OMP_NUM_THREADS=1
0 commit comments