Image-Text-to-Text
Transformers
Safetensors
nemotron_parse
text-generation
VLM
OCR
Parse
conversational
custom_code
Eval Results
Instructions to use nvidia/Nemotron-3.5-Parse with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nvidia/Nemotron-3.5-Parse with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="nvidia/Nemotron-3.5-Parse", trust_remote_code=True) messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] pipe(text=messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-3.5-Parse", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use nvidia/Nemotron-3.5-Parse with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "nvidia/Nemotron-3.5-Parse" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "nvidia/Nemotron-3.5-Parse", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'Use Docker
docker model run hf.co/nvidia/Nemotron-3.5-Parse
- SGLang
How to use nvidia/Nemotron-3.5-Parse with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "nvidia/Nemotron-3.5-Parse" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "nvidia/Nemotron-3.5-Parse", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "nvidia/Nemotron-3.5-Parse" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "nvidia/Nemotron-3.5-Parse", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }' - Docker Model Runner
How to use nvidia/Nemotron-3.5-Parse with Docker Model Runner:
docker model run hf.co/nvidia/Nemotron-3.5-Parse
Download reference/parsebench/pipeline/postprocessing_checks.json from nvidia/Nemotron-3.5-Parse: direct link, hf CLI and curl.
- Browser
- Download file 3.97 kB
-
https://huggingface.co/nvidia/Nemotron-3.5-Parse/resolve/main/reference/parsebench/pipeline/postprocessing_checks.json
- Command line
-
hf download hf://nvidia/Nemotron-3.5-Parse/reference/parsebench/pipeline/postprocessing_checks.json
-
curl -L -o postprocessing_checks.json https://huggingface.co/nvidia/Nemotron-3.5-Parse/resolve/main/reference/parsebench/pipeline/postprocessing_checks.json
3.97 kB
| { | |
| "union_region_parity_pages": 2078, | |
| "parser_text_invariants": { | |
| "checked_pages": 12468, | |
| "soft_hyphen_changes_are_only_U00AD_deletions": true, | |
| "prefix_repair_preserves_literal_payload_after_removing_serialization_tokens": true, | |
| "table_cells_roles_spans_unchanged": true, | |
| "table_cell_mismatches": [], | |
| "changed_pages": { | |
| "soft": { | |
| "single": 5, | |
| "double": 5, | |
| "triple": 5 | |
| }, | |
| "prefix": { | |
| "single": 39, | |
| "double": 42, | |
| "triple": 42 | |
| } | |
| } | |
| }, | |
| "numeric_pair_guard_checks": { | |
| "passed": true, | |
| "cases": [ | |
| "numeric_pairs", | |
| "mixed_values", | |
| "one_pair", | |
| "missing_percent", | |
| "already_separate" | |
| ], | |
| "non_English_series_heading": "S\u00e9rie", | |
| "existing_literals_preserved": true | |
| }, | |
| "excluded_default_changes": [ | |
| "English header vocabulary", | |
| "forced header bold", | |
| "canonical Unicode folding", | |
| "approximate duplicate pruning", | |
| "repeated-header table splitting", | |
| "global sampling changes", | |
| "long-output or retry policies" | |
| ], | |
| "empty_title_guard": { | |
| "following_metadata_preserved": true, | |
| "valid_title_fixture_unchanged": true, | |
| "all_actual_outputs_unchanged": true, | |
| "scope": "Both chart rendering paths tested; the title-only change has no actual-output effect in the saved run. Header correction changes four pages per mode." | |
| }, | |
| "historical_pre_correction_full_output_parity": { | |
| "single": { | |
| "pages": 2078, | |
| "mismatch_count": 0, | |
| "mismatches": [] | |
| }, | |
| "double": { | |
| "pages": 2078, | |
| "mismatch_count": 0, | |
| "mismatches": [] | |
| }, | |
| "triple": { | |
| "pages": 2078, | |
| "mismatch_count": 0, | |
| "mismatches": [] | |
| }, | |
| "triple_control": { | |
| "pages": 2078, | |
| "mismatch_count": 0, | |
| "mismatches": [] | |
| } | |
| }, | |
| "historical_pre_correction_final_actual_http_output_parity": { | |
| "single": { | |
| "pages": 2078, | |
| "mismatches": 0 | |
| }, | |
| "double": { | |
| "pages": 2078, | |
| "mismatches": 0 | |
| }, | |
| "triple": { | |
| "pages": 2078, | |
| "mismatches": 0 | |
| }, | |
| "triple_detector": { | |
| "pages": 2078, | |
| "mismatches": 0 | |
| } | |
| }, | |
| "historical_pre_correction_fresh_output_table_fields_roles_spans_unchanged": true, | |
| "corrected_header_title_fixtures": { | |
| "data_row_not_promoted": true, | |
| "explicit_rowspan_preserved": true, | |
| "bold_headers_preserved": true, | |
| "year_data_not_promoted": true, | |
| "bold_numeric_data_not_promoted": true, | |
| "empty_title_full_pipeline": true, | |
| "nonempty_title_preserved": true | |
| }, | |
| "corrected_renderer_replay": { | |
| "new_inference_requests": 0, | |
| "fixtures": { | |
| "data_row_not_promoted": true, | |
| "explicit_rowspan_preserved": true, | |
| "bold_headers_preserved": true, | |
| "year_data_not_promoted": true, | |
| "bold_numeric_data_not_promoted": true, | |
| "empty_title_full_pipeline": true, | |
| "nonempty_title_preserved": true | |
| }, | |
| "modes": { | |
| "single": { | |
| "changed_pages": 4, | |
| "raw_and_geometry_unchanged": true, | |
| "cell_text_order_spans_unchanged": true, | |
| "prediction_sha256": "f62ab4ed079b79241cce467eb1ad50577a172ca04124d642c31afba8ab7048b2" | |
| }, | |
| "double": { | |
| "changed_pages": 4, | |
| "raw_and_geometry_unchanged": true, | |
| "cell_text_order_spans_unchanged": true, | |
| "prediction_sha256": "3c74420e780ffe36fa60dd3a1abe701d3405be3957242a75326e9fe868a8be6f" | |
| }, | |
| "triple": { | |
| "changed_pages": 4, | |
| "raw_and_geometry_unchanged": true, | |
| "cell_text_order_spans_unchanged": true, | |
| "prediction_sha256": "80b7700cd44e9ee3694454b944bbebf7a9c45ee628b33b1af70bfd8c9fb0a207" | |
| }, | |
| "triple_detector": { | |
| "changed_pages": 4, | |
| "raw_and_geometry_unchanged": true, | |
| "cell_text_order_spans_unchanged": true, | |
| "prediction_sha256": "cf93b01c97cdc8376e501282cbb2498acd174145de1c7d158e362e85df703a00" | |
| } | |
| } | |
| } | |
| } | |