NVIDIA-Nemotron-Parse-v1.1

Nemotron-Parse-v1.1 is NVIDIA’s document parsing VLM, specializing in extracting structured information from complex documents including tables, forms, and mixed-content PDFs.

Set up NeMo AutoModel with the latest container or follow the installation instructions.

Fine-Tune NVIDIA-Nemotron-Parse-v1.1

From the repository root, run:

uv run automodel --nproc-per-node=8 examples/vlm_finetune/nemotron/nemotron_parse_v1_1.yaml

Choose a Workflow

Goal	Start Here
Supervised fine-tuning (SFT) - Nemotron-Parse on CORD-v2	Use nemotron_parse_v1_1.yaml. Dataset: cord-v2.

Fine-Tuning Tutorial on Brev

Launch the end-to-end Nemotron Parse fine-tuning tutorial on Brev with a single click:

See also the tutorial notebook and the VLM Fine-Tuning Guide.

Model Reference

Model Architecture

Available Models

Related Resources

• VLM Fine-Tuning Guide