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 42fe05f commit 0d75b04Copy full SHA for 0d75b04
torchtitan/experiments/simple_fsdp/deepseek_v3/__init__.py
@@ -21,7 +21,6 @@
21
22
def get_train_spec() -> TrainSpec:
23
return TrainSpec(
24
- name="simple_fsdp.deepseek_v3",
25
model_cls=SimpleFSDPDeepSeekV3Model,
26
model_args=deepseekv3_configs,
27
parallelize_fn=parallelize_deepseekv3,
torchtitan/experiments/simple_fsdp/llama3/__init__.py
@@ -20,7 +20,6 @@
20
- name="simple_fsdp.llama3",
model_cls=SimpleFSDPTransformer,
model_args=llama3_configs,
parallelize_fn=parallelize_llama,
0 commit comments