8000 Support transformers 4.50.0 by albertvillanova · Pull Request #1070 · huggingface/smolagents · GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

Support transformers 4.50.0 #1070

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 4 commits into from
Mar 25, 2025
Merged

Support transformers 4.50.0 #1070

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
d6b2a99
Unpin transformers
albertvillanova Mar 25, 2025
4b246a0
Inverse text/image model instantiation
albertvillanova Mar 25, 2025
974c41b
Update test patching
albertvillanova Mar 25, 2025
625575a
Update test patching
albertvillanova Mar 25, 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 pyproject.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -64,7 +64,7 @@ telemetry = [
]
transformers = [
"accelerate",
"transformers>=4.0.0,<4.50.0",
"transformers>=4.0.0",
"smolagents[torch]",
]
vision = [
Expand Down
10 changes: 5 additions & 5 deletions src/smolagents/models.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -682,23 +682,23 @@ def __init__(
logger.info(f"Using device: {device_map}")
self._is_vlm = False
try:
self.model = AutoModelForCausalLM.from_pretrained(
self.model = AutoModelForImageTextToText.from_pretrained(
model_id,
device_map=device_map,
torch_dtype=torch_dtype,
trust_remote_code=trust_remote_code,
)
self.tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=trust_remote_code)
self.processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=trust_remote_code)
self._is_vlm = True
except ValueError as e:
if "Unrecognized configuration class" in str(e):
self.model = AutoModelForImageTextToText.from_pretrained(
self.model = AutoModelForCausalLM.from_pretrained(
model_id,
device_map=device_map,
torch_dtype=torch_dtype,
trust_remote_code=trust_remote_code,
)
self.processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=trust_remote_code)
self._is_vlm = True
self.tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=trust_remote_code)
else:
raise e
except Exception as e:
Expand Down
4 changes: 4 additions & 0 deletions tests/test_cli.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -33,6 +33,10 @@ def test_load_model_litellm_model():

def test_load_model_transformers_model():
with (
patch(
"transformers.AutoModelForImageTextToText.from_pretrained",
side_effect=ValueError("Unrecognized configuration class"),
),
patch("transformers.AutoModelForCausalLM.from_pretrained"),
patch("transformers.AutoTokenizer.from_pretrained"),
):
Expand Down
16 changes: 8 additions & 8 deletions tests/test_models.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -237,14 +237,14 @@ class TestTransformersModel:
"patching",
[
[
(
"transformers.AutoModelForImageTextToText.from_pretrained",
{"side_effect": ValueError("Unrecognized configuration class")},
),
("transformers.AutoModelForCausalLM.from_pretrained", {}),
("transformers.AutoTokenizer.from_pretrained", {}),
],
[
(
"transformers.AutoModelForCausalLM.from_pretrained",
{"side_effect": ValueError("Unrecognized configuration class")},
),
("transformers.AutoModelForImageTextToText.from_pretrained", {}),
("transformers.AutoProcessor.from_pretrained", {}),
],
Expand Down Expand Up @@ -373,6 +373,10 @@ def test_get_clean_message_list_flatten_messages_as_text():
TransformersModel,
{},
[
(
"transformers.AutoModelForImageTextToText.from_pretrained",
{"side_effect": ValueError("Unrecognized configuration class")},
),
("transformers.AutoModelForCausalLM.from_pretrained", {}),
("transformers.AutoTokenizer.from_pretrained", {}),
],
Expand All @@ -382,10 +386,6 @@ def test_get_clean_message_list_flatten_messages_as_text():
TransformersModel,
{},
[
(
"transformers.AutoModelForCausalLM.from_pretrained",
{"side_effect": ValueError("Unrecognized configuration class")},
),
("transformers.AutoModelForImageTextToText.from_pretrained", {}),
("transformers.AutoProcessor.from_pretrained", {}),
],
Expand Down
0