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/package/component_manifest.json from nvidia/Nemotron-3.5-Parse: direct link, hf CLI and curl.
- Browser
- Download file 7.45 kB
-
https://huggingface.co/nvidia/Nemotron-3.5-Parse/resolve/main/reference/package/component_manifest.json
- Command line
-
hf download hf://nvidia/Nemotron-3.5-Parse/reference/package/component_manifest.json
-
curl -L -o component_manifest.json https://huggingface.co/nvidia/Nemotron-3.5-Parse/resolve/main/reference/package/component_manifest.json
7.45 kB
| { | |
| "schema_version": 1, | |
| "wheel": "nemotron_parse-3.5.0.post7-py3-none-any.whl", | |
| "wheel_sha256": "e403d294fc9c0563f6d38028ce0e0a639977fdba2807fa6981692aabbf269077", | |
| "components": [ | |
| { | |
| "path": "latex2html.py", | |
| "bytes": 448, | |
| "sha256": "d3efc436b39344d3d9443b92a099c67ba9492b23fb13045638d7aaf331e49ec6" | |
| }, | |
| { | |
| "path": "nemotron_parse-3.5.0.post7.dist-info/METADATA", | |
| "bytes": 928, | |
| "sha256": "ce60a16d0f074a9455fdf0604d8b6e04d3b23f32bed59c8210fd5e625e527166" | |
| }, | |
| { | |
| "path": "nemotron_parse-3.5.0.post7.dist-info/RECORD", | |
| "bytes": 3849, | |
| "sha256": "8dcb4c38e61672568871fb38c5cd076db2eaca81ac77eef753618cd6c444ae55" | |
| }, | |
| { | |
| "path": "nemotron_parse-3.5.0.post7.dist-info/WHEEL", | |
| "bytes": 91, | |
| "sha256": "ff309ddcdd65ebd02bc724dbf2bcc4a0ff53a5b61792a44548d383e4ebb19d3b" | |
| }, | |
| { | |
| "path": "nemotron_parse-3.5.0.post7.dist-info/entry_points.txt", | |
| "bytes": 141, | |
| "sha256": "b9cdcd0f7ffb6b5e095b5439d160b998a8a3833e6a0a4816476d4efe4d681c03" | |
| }, | |
| { | |
| "path": "nemotron_parse-3.5.0.post7.dist-info/licenses/LICENSE", | |
| "bytes": 3051, | |
| "sha256": "3375384ee1050a54d69c98c74d6499841166cd7db823ed90358f430df8c39856" | |
| }, | |
| { | |
| "path": "nemotron_parse-3.5.0.post7.dist-info/licenses/THIRD_PARTY_NOTICES.md", | |
| "bytes": 730187, | |
| "sha256": "3ffde205eb8d5d6458dcd1b6bc3d59b2b92d650b95e1e56f75dbed2bbed78b64" | |
| }, | |
| { | |
| "path": "nemotron_parse-3.5.0.post7.dist-info/licenses/TOKENIZER_ATTRIBUTION.md", | |
| "bytes": 1963, | |
| "sha256": "9a1cb165c21860d78a05a8b4aacb24de025719e2c3ed33ee86d1722ccaec442a" | |
| }, | |
| { | |
| "path": "nemotron_parse-3.5.0.post7.dist-info/top_level.txt", | |
| "bytes": 57, | |
| "sha256": "bb7e77de4c441ab99c7580ddc7962d25dda189e4a5ab8e7456ac976141c646bb" | |
| }, | |
| { | |
| "path": "nemotron_parse/SOURCE_MANIFEST.json", | |
| "bytes": 5479, | |
| "sha256": "a0fe800712c537f68a38f494902ac4e1f9b5910c3a786ed2a1dd0aab2f7808c8" | |
| }, | |
| { | |
| "path": "nemotron_parse/__init__.py", | |
| "bytes": 373, | |
| "sha256": "d526a90593085f19ee36e36d552c12ad7e282303da99adb69d854daff64cd075" | |
| }, | |
| { | |
| "path": "nemotron_parse/batch.py", | |
| "bytes": 21905, | |
| "sha256": "d3e7fe9efb6f00ae776ef5b290c95b28a9d77031984b52501c6ee5c9d9ab2b39" | |
| }, | |
| { | |
| "path": "nemotron_parse/engine/__init__.py", | |
| "bytes": 138, | |
| "sha256": "f0b3bb691d1a6a3168fe9a9d3d7ea1e718c545ce71f6c6f245f38b3071a24075" | |
| }, | |
| { | |
| "path": "nemotron_parse/engine/caption_relocation.py", | |
| "bytes": 3421, | |
| "sha256": "d3eb0308922495e0e57abcbfb73d132e57a2afa5b3add26326c996e957d193dc" | |
| }, | |
| { | |
| "path": "nemotron_parse/engine/chart_caption.py", | |
| "bytes": 2362, | |
| "sha256": "b63fcafce57aa2905c43886616d0560df33dd3785ea57f98683b7a68243f2db0" | |
| }, | |
| { | |
| "path": "nemotron_parse/engine/chart_context.py", | |
| "bytes": 1379, | |
| "sha256": "8c22ec2364db672b1df19e9c59030222acbb893d721222936fa38130caf0a32a" | |
| }, | |
| { | |
| "path": "nemotron_parse/engine/convert/__init__.py", | |
| "bytes": 138, | |
| "sha256": "f0b3bb691d1a6a3168fe9a9d3d7ea1e718c545ce71f6c6f245f38b3071a24075" | |
| }, | |
| { | |
| "path": "nemotron_parse/engine/convert/hybrid_cleanup.py", | |
| "bytes": 2377, | |
| "sha256": "a00d0a09f451bbaeed5b6fa9dd37e8e781d9a014cac510e616fd6a029249f1f6" | |
| }, | |
| { | |
| "path": "nemotron_parse/engine/convert/hybrid_inline.py", | |
| "bytes": 6110, | |
| "sha256": "33b8d7aaab8294a73898f409754a6521ac1117af5df5e20b8272eac184c511ec" | |
| }, | |
| { | |
| "path": "nemotron_parse/engine/convert/latex2html.py", | |
| "bytes": 22518, | |
| "sha256": "3dacfe5a2d8f2aaf9b077a9268e73356be602abdcf3d310fef8850213b13e13b" | |
| }, | |
| { | |
| "path": "nemotron_parse/engine/convert/rich_table_fallback.py", | |
| "bytes": 3890, | |
| "sha256": "bed8be6df2d254ff48a66efb2a2e2474e18391b87e8649d01843206ec27fbd89" | |
| }, | |
| { | |
| "path": "nemotron_parse/engine/convert/rich_table_reader.py", | |
| "bytes": 4874, | |
| "sha256": "8f6a4c8b1a71ca25923a5bbb8e1c86ab961f3dc046eb344c30b79344852b655e" | |
| }, | |
| { | |
| "path": "nemotron_parse/engine/convert/semantic_styles.py", | |
| "bytes": 2107, | |
| "sha256": "66be8ab92fa407bb45e81d79fd6842bae0cc8dd542f2e8b12abc275184469ee9" | |
| }, | |
| { | |
| "path": "nemotron_parse/engine/geometry.py", | |
| "bytes": 13484, | |
| "sha256": "8f1008d7bbd23314c80b5ee01cb7ee7191865f43e36b9d3f431441d53c2ec3bb" | |
| }, | |
| { | |
| "path": "nemotron_parse/engine/header_inference_probe.py", | |
| "bytes": 3379, | |
| "sha256": "83f038ca2a27f2dea395cf4e96990e4bacc3cb86a06c3c1943d2bff1cae761c2" | |
| }, | |
| { | |
| "path": "nemotron_parse/engine/markdown.py", | |
| "bytes": 2090, | |
| "sha256": "5569d25a4b12c11586dfb3341d0a438c6fae6199429026386d87b0a8f473361d" | |
| }, | |
| { | |
| "path": "nemotron_parse/engine/merge.py", | |
| "bytes": 20296, | |
| "sha256": "3a6f876e28bc32bc1d7e788b63c1b04a53d6eb20b59ab506c0538e83e444f079" | |
| }, | |
| { | |
| "path": "nemotron_parse/engine/policies.py", | |
| "bytes": 12353, | |
| "sha256": "6c5fbdc633b22e2c87a37e1f86f0af19ca64eef1639a517a0c06680aa4609196" | |
| }, | |
| { | |
| "path": "nemotron_parse/engine/regions.py", | |
| "bytes": 1200, | |
| "sha256": "9c38e9fb52413d8a5fb82f071d9a3599988819c4df66db302093a758f6262a07" | |
| }, | |
| { | |
| "path": "nemotron_parse/engine/text_cleanup.py", | |
| "bytes": 1401, | |
| "sha256": "192b165696101d6532ed566403652515123094f596069ca1e6aedc6dc8fd801f" | |
| }, | |
| { | |
| "path": "nemotron_parse/inference.py", | |
| "bytes": 24507, | |
| "sha256": "326d1e15a69831e9ae0e6506744dae7888efcfce456c2abdf58dccfea6d604fb" | |
| }, | |
| { | |
| "path": "nemotron_parse/postprocessing.py", | |
| "bytes": 8430, | |
| "sha256": "813528d2ae070ad28ca63cd1de6b0190030a593b33be9c814007d9ae59899332" | |
| }, | |
| { | |
| "path": "nemotron_parse/tables.py", | |
| "bytes": 11858, | |
| "sha256": "6af46abd69c0690d81c26f570f5352b699ad7d529481d4f445676cceac2b33c7" | |
| }, | |
| { | |
| "path": "postprocessing.py", | |
| "bytes": 502, | |
| "sha256": "cef5a7379720d479f7fd6fe47fb0e83097ff47bc053f751e747134c882d5a3fe" | |
| }, | |
| { | |
| "path": "vllm_tied_patch/__init__.py", | |
| "bytes": 247, | |
| "sha256": "4c41ff4e28ba556bbe05c9d4cd7dffebc0364e1f6a77b2bb23508fa77314b8b8" | |
| }, | |
| { | |
| "path": "vllm_tied_patch/compatibility.py", | |
| "bytes": 36130, | |
| "sha256": "c71b97530bb80bd365cd69064791c2943c0f4bc03a2a092abc53ea860c631a7e" | |
| }, | |
| { | |
| "path": "vllm_tied_patch/defaults.py", | |
| "bytes": 1969, | |
| "sha256": "0bae724df1039619f5f500a03c34111b6bcb469d35d56e51a3646b3578386734" | |
| }, | |
| { | |
| "path": "vllm_tied_patch/mtp_weights.py", | |
| "bytes": 3401, | |
| "sha256": "50df2a3aa03256692136852d69421559c591ed4843fb36a9199aae161bd2e6a1" | |
| }, | |
| { | |
| "path": "vllm_tied_patch/plugin.py", | |
| "bytes": 3156, | |
| "sha256": "c00298c66f89c0912691abba4f72d996c589ac335f89a6b82b9c81b751a17646" | |
| }, | |
| { | |
| "path": "vllm_tied_patch/vllm_radio_mbart_mtp.py", | |
| "bytes": 3718, | |
| "sha256": "3bf27b0cfb9c96aa7e81989810c50875c804d379981bbb2c1ef47ce2e0457f70" | |
| }, | |
| { | |
| "path": "vllm_tied_patch/vllm_radio_mbart_prefix.py", | |
| "bytes": 19425, | |
| "sha256": "3f2ac3b4884fd37747d083a3d26e487456323b27eb0ea90325e57f8e2ca82657" | |
| } | |
| ], | |
| "wheel_url": "https://huggingface.co/nvidia/Nemotron-3.5-Parse/resolve/41897c0ae2fe5d9b461b207bb13587ed54d2740c/nemotron_parse-3.5.0.post7-py3-none-any.whl" | |
| } | |