Skip to content

fix: Map llama models to correct script #5159

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 5 commits into from
May 9, 2025
Merged

fix: Map llama models to correct script #5159

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
b0741bb
fix: Map llama models to correct script
benieric May 6, 2025
fdc00c4
add test
benieric May 6, 2025
07b589e
fix formatting
benieric May 8, 2025
ad81f0c
Merge branch 'master' into master-fix-recipe-mapping
benieric May 8, 2025
25bc8f7
Merge branch 'master' into master-fix-recipe-mapping
benieric May 9, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion src/sagemaker/modules/train/sm_recipes/utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -129,7 +129,7 @@ def _get_trainining_recipe_gpu_model_name_and_script(model_type: str):
"""Get the model base name and script for the training recipe."""

model_type_to_script = {
"llama_v3": ("llama", "llama_pretrain.py"),
"llama": ("llama", "llama_pretrain.py"),
"mistral": ("mistral", "mistral_pretrain.py"),
"mixtral": ("mixtral", "mixtral_pretrain.py"),
"deepseek": ("deepseek", "deepseek_pretrain.py"),
Expand Down
66 changes: 33 additions & 33 deletions tests/unit/sagemaker/modules/train/sm_recipes/test_utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -180,36 +180,36 @@ def test_get_args_from_recipe_compute(
assert mock_trainium_args.call_count == 0
assert args is None

@pytest.mark.parametrize(
"test_case",
[
{
"model_type": "llama_v3",
"script": "llama_pretrain.py",
"model_base_name": "llama_v3",
},
{
"model_type": "mistral",
"script": "mistral_pretrain.py",
"model_base_name": "mistral",
},
{
"model_type": "deepseek_llamav3",
"script": "deepseek_pretrain.py",
"model_base_name": "deepseek",
},
{
"model_type": "deepseek_qwenv2",
"script": "deepseek_pretrain.py",
"model_base_name": "deepseek",
},
],
)
def test_get_trainining_recipe_gpu_model_name_and_script(test_case):
model_type = test_case["model_type"]
script = test_case["script"]
model_base_name, script = _get_trainining_recipe_gpu_model_name_and_script(
model_type, script
)
assert model_base_name == test_case["model_base_name"]
assert script == test_case["script"]

@pytest.mark.parametrize(
"test_case",
[
{"model_type": "llama_v4", "script": "llama_pretrain.py", "model_base_name": "llama"},
{
"model_type": "llama_v3",
"script": "llama_pretrain.py",
"model_base_name": "llama",
},
{
"model_type": "mistral",
"script": "mistral_pretrain.py",
"model_base_name": "mistral",
},
{
"model_type": "deepseek_llamav3",
"script": "deepseek_pretrain.py",
"model_base_name": "deepseek",
},
{
"model_type": "deepseek_qwenv2",
"script": "deepseek_pretrain.py",
"model_base_name": "deepseek",
},
],
)
def test_get_trainining_recipe_gpu_model_name_and_script(test_case):
model_type = test_case["model_type"]
script = test_case["script"]
model_base_name, script = _get_trainining_recipe_gpu_model_name_and_script(model_type)
assert model_base_name == test_case["model_base_name"]
assert script == test_case["script"]