Text Generation
Transformers
Safetensors
English
qwen3_5
image-text-to-text
security
vulnerability-detection
cybersecurity
cwe
cve
code-analysis
reasoning
qwen3
sft
conversational
Instructions to use glyphsoftware/sentinel-r1-9B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use glyphsoftware/sentinel-r1-9B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="glyphsoftware/sentinel-r1-9B") 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)# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("glyphsoftware/sentinel-r1-9B") model = AutoModelForMultimodalLM.from_pretrained("glyphsoftware/sentinel-r1-9B", device_map="auto") 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?"} ] }, ] inputs = processor.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=40) print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use glyphsoftware/sentinel-r1-9B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "glyphsoftware/sentinel-r1-9B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "glyphsoftware/sentinel-r1-9B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/glyphsoftware/sentinel-r1-9B
- SGLang
How to use glyphsoftware/sentinel-r1-9B 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 "glyphsoftware/sentinel-r1-9B" \ --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": "glyphsoftware/sentinel-r1-9B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'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 "glyphsoftware/sentinel-r1-9B" \ --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": "glyphsoftware/sentinel-r1-9B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use glyphsoftware/sentinel-r1-9B with Docker Model Runner:
docker model run hf.co/glyphsoftware/sentinel-r1-9B
| GLYPH PROPRIETARY LICENSE | |
| Version 1.0 | |
| Copyright (c) 2026 Glyph Software LLP. All Rights Reserved. | |
| This license governs the model known as "Sentinel-R1-9B", including its | |
| weights, configuration files, tokenizer, source code, documentation, and any | |
| associated artifacts or derivatives (collectively, the "Model"). The Model is | |
| the confidential and proprietary property of Glyph Software LLP ("Licensor"). | |
| BY ACCESSING, DOWNLOADING, COPYING, OR USING THE MODEL, YOU ("Licensee") AGREE | |
| TO BE BOUND BY THE TERMS OF THIS LICENSE. IF YOU DO NOT AGREE, YOU MUST NOT | |
| ACCESS OR USE THE MODEL. | |
| 1. OWNERSHIP | |
| The Model is licensed, not sold. Licensor retains all right, title, and | |
| interest in and to the Model, including all intellectual property rights. | |
| No ownership rights are transferred to Licensee under this license. | |
| 2. GRANT OF LICENSE | |
| Subject to a separate, signed written agreement with Licensor and Licensee's | |
| continuous compliance with this license, Licensor may grant Licensee a | |
| limited, non-exclusive, non-transferable, non-sublicensable, revocable right | |
| to use the Model solely for the internal, authorized purposes specified in | |
| that written agreement. Absent such a signed agreement, no rights are | |
| granted. | |
| 3. RESTRICTIONS | |
| Except as expressly permitted in a signed written agreement, Licensee shall | |
| NOT, and shall not permit any third party to: | |
| (a) copy, publish, distribute, disclose, sell, rent, lease, lend, or | |
| otherwise make the Model available to any third party; | |
| (b) sublicense, assign, or transfer the Model or any rights herein; | |
| (c) use the Model, in whole or in part, to train, fine-tune, distill, | |
| evaluate, benchmark, or otherwise create or improve any other model or | |
| machine-learning system; | |
| (d) reverse engineer, decompile, disassemble, or attempt to extract or | |
| reconstruct the Model's weights, training data, or architecture beyond | |
| what is permitted by applicable mandatory law; | |
| (e) remove, alter, or obscure any proprietary notices, identity strings, or | |
| attribution contained in or produced by the Model; | |
| (f) use the Model to develop, generate, or distribute functional exploits, | |
| malware, or to conduct attacks against any system without explicit prior | |
| authorization from the system owner; | |
| (g) use the Model in violation of any applicable law, regulation, or | |
| third-party right, or in any high-risk setting as the sole basis for a | |
| security or safety decision without qualified human review. | |
| 4. DEFENSIVE AND AUTHORIZED-USE INTENT | |
| The Model is provided for defensive application-security purposes and for | |
| authorized security research only. Any proof-of-concept content produced by | |
| the Model is intended solely for analysis in environments the Licensee owns | |
| or is explicitly authorized to test. | |
| 5. CONFIDENTIALITY | |
| The Model and any non-public information about it are Confidential | |
| Information of Licensor. Licensee shall protect such Confidential Information | |
| using at least a reasonable standard of care and shall not disclose it except | |
| as expressly authorized in writing. | |
| 6. NO WARRANTY | |
| THE MODEL IS PROVIDED "AS IS" AND "AS AVAILABLE", WITHOUT WARRANTY OF ANY | |
| KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF | |
| MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE, ACCURACY, AND | |
| NON-INFRINGEMENT. LICENSOR DOES NOT WARRANT THAT THE MODEL'S OUTPUTS ARE | |
| ACCURATE, COMPLETE, OR FREE OF FALSE POSITIVES OR FALSE NEGATIVES. | |
| 7. LIMITATION OF LIABILITY | |
| TO THE MAXIMUM EXTENT PERMITTED BY LAW, IN NO EVENT SHALL LICENSOR BE LIABLE | |
| FOR ANY INDIRECT, INCIDENTAL, SPECIAL, CONSEQUENTIAL, OR PUNITIVE DAMAGES, OR | |
| FOR ANY LOSS OF PROFITS, DATA, OR GOODWILL, ARISING OUT OF OR RELATED TO THE | |
| MODEL OR THIS LICENSE, WHETHER IN CONTRACT, TORT, OR OTHERWISE, EVEN IF | |
| ADVISED OF THE POSSIBILITY OF SUCH DAMAGES. | |
| 8. TERMINATION | |
| This license and any rights granted hereunder terminate automatically and | |
| immediately upon any breach by Licensee, or at Licensor's discretion. Upon | |
| termination, Licensee shall cease all use of the Model and permanently delete | |
| all copies in its possession or control. Sections 1, 3, 5, 6, 7, and 9 | |
| survive termination. | |
| 9. GENERAL | |
| This license constitutes the entire agreement regarding the Model except as | |
| supplemented by a signed written agreement with Licensor, which controls in | |
| the event of conflict. If any provision is held unenforceable, the remaining | |
| provisions remain in effect. Failure to enforce any provision is not a | |
| waiver. This license is governed by the laws of the jurisdiction of | |
| Licensor's principal place of business, without regard to conflict-of-laws | |
| rules. | |
| For licensing inquiries and written authorization, contact Glyph Software LLP. | |
| © 2026 Glyph Software LLP. All Rights Reserved. | |