Skip to content
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.

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

[OV] Fix data-free VLM compression via optimum-cli #1058

Merged
Merged
Changes from 1 commit
Commits
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
Prev Previous commit
Next Next commit
Fix condition
  • Loading branch information
nikita-savelyevv committed Dec 12, 2024
commit 3b0851ddec293ba9e659ce2082816e523619c247
6 changes: 5 additions & 1 deletion optimum/commands/export/openvino.py
Original file line number Diff line number Diff line change
Expand Up @@ -361,7 +361,11 @@ def run(self):
model.save_pretrained(self.args.output)
if not self.args.disable_convert_tokenizer:
maybe_convert_tokenizers(library_name, self.args.output, model, task=task)
elif task.startswith("text-generation") and quantize_with_dataset or task == "image-text-to-text":
elif (
task.startswith("text-generation")
and quantize_with_dataset
or (task == "image-text-to-text" and quantization_config is not None)
):
if task.startswith("text-generation"):
from optimum.intel import OVModelForCausalLM

Expand Down