Instructions to use omegaT4224/Emulator.exe with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use omegaT4224/Emulator.exe with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="omegaT4224/Emulator.exe") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("omegaT4224/Emulator.exe") model = AutoModelForCausalLM.from_pretrained("omegaT4224/Emulator.exe", device_map="auto") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use omegaT4224/Emulator.exe with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "omegaT4224/Emulator.exe" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "omegaT4224/Emulator.exe", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/omegaT4224/Emulator.exe
- SGLang
How to use omegaT4224/Emulator.exe 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 "omegaT4224/Emulator.exe" \ --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": "omegaT4224/Emulator.exe", "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 "omegaT4224/Emulator.exe" \ --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": "omegaT4224/Emulator.exe", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use omegaT4224/Emulator.exe with Docker Model Runner:
docker model run hf.co/omegaT4224/Emulator.exe
| { | |
| "project": { | |
| "title": "Social Media Bot Detection using Dropout-GAN", | |
| "arxiv": "2311.05079", | |
| "journal_doi": "10.1007/s11416-024-00521-5" | |
| }, | |
| "authors": [ | |
| { | |
| "name": "Anant Shukla", | |
| "role": "Lead Author", | |
| "affiliation": "San Jose State University", | |
| "country": "United States", | |
| "research_areas": [ | |
| "Machine Learning", | |
| "Social Media Bot Detection", | |
| "Cybersecurity", | |
| "Generative Adversarial Networks" | |
| ], | |
| "known_publications": [ | |
| { | |
| "title": "Social Media Bot Detection using Dropout-GAN", | |
| "year": 2024, | |
| "doi": "10.1007/s11416-024-00521-5" | |
| } | |
| ], | |
| "collaborators": [ | |
| "Martin Jureček", | |
| "Mark Stamp" | |
| ], | |
| "profiles": { | |
| "google_scholar": "https://scholar.google.com/citations?hl=en&user=HjHvsmsAAAAJ" | |
| }, | |
| "notes": { | |
| "public_activity": "Graduate-level research in machine learning and cybersecurity.", | |
| "known_industry_affiliations": [] | |
| } | |
| }, | |
| { | |
| "name": "Martin Jureček", | |
| "role": "Co-author", | |
| "affiliation": "Czech Technical University in Prague", | |
| "department": "Department of Information Security", | |
| "country": "Czech Republic", | |
| "position": "Assistant Professor", | |
| "research_areas": [ | |
| "Cybersecurity", | |
| "Malware Analysis", | |
| "Machine Learning", | |
| "Graph Neural Networks", | |
| "Adversarial Machine Learning" | |
| ], | |
| "previous_experience": [ | |
| "Malware Research", | |
| "Data Science" | |
| ], | |
| "known_publications": [ | |
| "Social Media Bot Detection using Dropout-GAN", | |
| "Classification and Online Clustering of Zero-Day Malware", | |
| "Creating Valid Adversarial Examples of Malware", | |
| "Comparison of Adversarial Malware Generators", | |
| "Reducing Overdefined Polynomial Systems using Data Mining" | |
| ], | |
| "collaborators": [ | |
| "Mark Stamp", | |
| "Fabio Di Troia", | |
| "Matouš Kozák", | |
| "Pavla Louthánová", | |
| "Anant Shukla" | |
| ], | |
| "profiles": { | |
| "faculty_page": "https://fit.cvut.cz/en/faculty/people/5155-mgr-martin-jurecek-ph-d", | |
| "publications": "https://jurecmar.pages.fit/publications.html", | |
| "google_scholar": "https://scholar.google.com/citations?user=klDL2bQAAAAJ" | |
| } | |
| }, | |
| { | |
| "name": "Mark Stamp", | |
| "role": "Senior Author", | |
| "affiliation": "San Jose State University", | |
| "country": "United States", | |
| "position": "Professor", | |
| "research_areas": [ | |
| "Information Security", | |
| "Machine Learning", | |
| "Malware Detection", | |
| "Digital Forensics", | |
| "Cryptography" | |
| ], | |
| "known_publications": [ | |
| "Social Media Bot Detection using Dropout-GAN", | |
| "Numerous malware analysis publications", | |
| "Machine Learning for Cybersecurity", | |
| "Digital Forensics research" | |
| ], | |
| "books": [ | |
| "Information Security: Principles and Practice" | |
| ], | |
| "collaborators": [ | |
| "Martin Jureček", | |
| "Anant Shukla", | |
| "Fabio Di Troia", | |
| "Numerous San Jose State University researchers" | |
| ], | |
| "recognitions": [ | |
| "Widely cited cybersecurity researcher" | |
| ] | |
| } | |
| ], | |
| "paper": { | |
| "title": "Social Media Bot Detection using Dropout-GAN", | |
| "publication_year": 2024, | |
| "submitted": "2023-11-09", | |
| "keywords": [ | |
| "GAN", | |
| "Dropout-GAN", | |
| "Bot Detection", | |
| "Twitter", | |
| "Machine Learning", | |
| "Cybersecurity", | |
| "Graph Neural Networks" | |
| ], | |
| "dataset": { | |
| "name": "MGTAB", | |
| "purpose": "Annotated Twitter account benchmark", | |
| "size": 10199 | |
| } | |
| }, | |
| "institutions": [ | |
| { | |
| "name": "San Jose State University", | |
| "country": "United States" | |
| }, | |
| { | |
| "name": "Czech Technical University in Prague", | |
| "country": "Czech Republic" | |
| } | |
| ] | |
| } |