Text Generation
Transformers
PyTorch
English
multilingual
helion
deepxr
xlarge
instruction-tuned
causal-lm
conversational
custom_code
Eval Results (legacy)
bitsandbytes
Instructions to use DeepXR/Helion-V1.5-XL with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use DeepXR/Helion-V1.5-XL with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="DeepXR/Helion-V1.5-XL", trust_remote_code=True) messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("DeepXR/Helion-V1.5-XL", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use DeepXR/Helion-V1.5-XL with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "DeepXR/Helion-V1.5-XL" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "DeepXR/Helion-V1.5-XL", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/DeepXR/Helion-V1.5-XL
- SGLang
How to use DeepXR/Helion-V1.5-XL 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 "DeepXR/Helion-V1.5-XL" \ --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": "DeepXR/Helion-V1.5-XL", "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 "DeepXR/Helion-V1.5-XL" \ --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": "DeepXR/Helion-V1.5-XL", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use DeepXR/Helion-V1.5-XL with Docker Model Runner:
docker model run hf.co/DeepXR/Helion-V1.5-XL
| { | |
| "safety_framework": { | |
| "model_name": "Helion-V1.5-XL", | |
| "version": "1.5", | |
| "safety_protocol_version": "2.1.0", | |
| "last_updated": "2024-11-01", | |
| "compliance_standards": [ | |
| "AI Safety Standards v3.2", | |
| "Responsible AI Guidelines", | |
| "EU AI Act Compliance", | |
| "NIST AI Risk Management Framework" | |
| ] | |
| }, | |
| "content_filtering": { | |
| "input_filters": { | |
| "enabled": true, | |
| "severity_levels": ["low", "medium", "high", "critical"], | |
| "toxicity_detection": { | |
| "enabled": true, | |
| "threshold": 0.75, | |
| "model": "detoxify-unbiased", | |
| "categories": [ | |
| "toxicity", | |
| "severe_toxicity", | |
| "obscene", | |
| "threat", | |
| "insult", | |
| "identity_attack", | |
| "sexual_explicit" | |
| ], | |
| "action_on_detection": "block_with_warning", | |
| "log_violations": true | |
| }, | |
| "harmful_content_detection": { | |
| "enabled": true, | |
| "categories": { | |
| "violence": { | |
| "enabled": true, | |
| "threshold": 0.8, | |
| "subcategories": ["graphic_violence", "self_harm", "weapons"] | |
| }, | |
| "hate_speech": { | |
| "enabled": true, | |
| "threshold": 0.85, | |
| "subcategories": ["racism", "sexism", "homophobia", "religious_intolerance"] | |
| }, | |
| "harassment": { | |
| "enabled": true, | |
| "threshold": 0.8, | |
| "subcategories": ["bullying", "doxxing", "stalking"] | |
| }, | |
| "illegal_activities": { | |
| "enabled": true, | |
| "threshold": 0.9, | |
| "subcategories": ["drug_manufacturing", "fraud", "hacking", "terrorism"] | |
| }, | |
| "sexual_content": { | |
| "enabled": true, | |
| "threshold": 0.85, | |
| "subcategories": ["adult_content", "child_safety", "exploitation"] | |
| }, | |
| "misinformation": { | |
| "enabled": true, | |
| "threshold": 0.7, | |
| "subcategories": ["health_misinfo", "election_misinfo", "conspiracy_theories"] | |
| } | |
| } | |
| }, | |
| "pii_detection": { | |
| "enabled": true, | |
| "entities": [ | |
| "email_address", | |
| "phone_number", | |
| "ssn", | |
| "credit_card", | |
| "ip_address", | |
| "home_address", | |
| "passport_number", | |
| "driver_license", | |
| "bank_account" | |
| ], | |
| "action": "redact_and_warn", | |
| "replacement_token": "[REDACTED]" | |
| }, | |
| "prompt_injection_detection": { | |
| "enabled": true, | |
| "detection_methods": [ | |
| "pattern_matching", | |
| "semantic_analysis", | |
| "adversarial_detection" | |
| ], | |
| "patterns": [ | |
| "ignore previous instructions", | |
| "disregard safety guidelines", | |
| "bypass filters", | |
| "jailbreak", | |
| "pretend you are" | |
| ], | |
| "action": "block", | |
| "log_attempts": true | |
| } | |
| }, | |
| "output_filters": { | |
| "enabled": true, | |
| "content_moderation": { | |
| "enabled": true, | |
| "scan_generated_text": true, | |
| "real_time_filtering": true, | |
| "categories": [ | |
| "toxicity", | |
| "bias", | |
| "factual_accuracy", | |
| "harmful_instructions", | |
| "sensitive_topics" | |
| ] | |
| }, | |
| "hallucination_detection": { | |
| "enabled": true, | |
| "confidence_threshold": 0.6, | |
| "fact_checking": { | |
| "enabled": true, | |
| "sources": ["knowledge_base", "external_verification"], | |
| "uncertainty_markers": true | |
| }, | |
| "action": "flag_uncertain_content" | |
| }, | |
| "bias_mitigation": { | |
| "enabled": true, | |
| "monitored_dimensions": [ | |
| "gender", | |
| "race", | |
| "ethnicity", | |
| "religion", | |
| "age", | |
| "disability", | |
| "sexual_orientation", | |
| "socioeconomic_status" | |
| ], | |
| "debiasing_technique": "counterfactual_augmentation", | |
| "fairness_metrics": ["demographic_parity", "equalized_odds"] | |
| } | |
| } | |
| }, | |
| "behavioral_safeguards": { | |
| "refusal_mechanisms": { | |
| "enabled": true, | |
| "refusal_categories": { | |
| "illegal_content": { | |
| "priority": "critical", | |
| "examples": [ | |
| "child exploitation material", | |
| "terrorism planning", | |
| "illegal drug synthesis", | |
| "malware creation", | |
| "fraud schemes" | |
| ], | |
| "refusal_message": "I cannot assist with illegal activities or harmful content." | |
| }, | |
| "dangerous_instructions": { | |
| "priority": "high", | |
| "examples": [ | |
| "self-harm guidance", | |
| "weapon manufacturing", | |
| "explosive creation", | |
| "dangerous medical advice", | |
| "poisoning methods" | |
| ], | |
| "refusal_message": "I cannot provide instructions that could cause harm." | |
| }, | |
| "unethical_requests": { | |
| "priority": "high", | |
| "examples": [ | |
| "plagiarism assistance", | |
| "exam cheating", | |
| "impersonation", | |
| "manipulation tactics", | |
| "deceptive content" | |
| ], | |
| "refusal_message": "I cannot help with unethical activities." | |
| }, | |
| "privacy_violations": { | |
| "priority": "high", | |
| "examples": [ | |
| "doxxing", | |
| "surveillance tactics", | |
| "data scraping", | |
| "unauthorized access", | |
| "identity theft" | |
| ], | |
| "refusal_message": "I cannot assist with privacy violations." | |
| } | |
| }, | |
| "graceful_degradation": { | |
| "enabled": true, | |
| "provide_alternatives": true, | |
| "explanation_level": "detailed", | |
| "redirect_to_safe_topics": true | |
| } | |
| }, | |
| "Constitutional_AI_principles": { | |
| "enabled": true, | |
| "principles": [ | |
| { | |
| "id": "harmlessness", | |
| "description": "Avoid generating harmful, dangerous, or toxic content", | |
| "weight": 1.0, | |
| "enforcement": "hard_constraint" | |
| }, | |
| { | |
| "id": "helpfulness", | |
| "description": "Provide useful, accurate, and relevant information", | |
| "weight": 0.9, | |
| "enforcement": "soft_constraint" | |
| }, | |
| { | |
| "id": "honesty", | |
| "description": "Be truthful and acknowledge uncertainty when appropriate", | |
| "weight": 0.95, | |
| "enforcement": "hard_constraint" | |
| }, | |
| { | |
| "id": "privacy", | |
| "description": "Protect user privacy and sensitive information", | |
| "weight": 1.0, | |
| "enforcement": "hard_constraint" | |
| }, | |
| { | |
| "id": "fairness", | |
| "description": "Treat all users and groups equitably without discrimination", | |
| "weight": 0.95, | |
| "enforcement": "soft_constraint" | |
| }, | |
| { | |
| "id": "transparency", | |
| "description": "Be clear about capabilities and limitations", | |
| "weight": 0.85, | |
| "enforcement": "soft_constraint" | |
| } | |
| ] | |
| }, | |
| "context_awareness": { | |
| "enabled": true, | |
| "age_appropriateness": { | |
| "detect_minor_users": true, | |
| "content_filtering_level": "strict", | |
| "educational_mode": true | |
| }, | |
| "cultural_sensitivity": { | |
| "enabled": true, | |
| "regional_adaptations": true, | |
| "offensive_content_detection": true | |
| }, | |
| "professional_context": { | |
| "detect_professional_use": true, | |
| "enhanced_accuracy_mode": true, | |
| "disclaimer_generation": true | |
| } | |
| } | |
| }, | |
| "adversarial_robustness": { | |
| "jailbreak_prevention": { | |
| "enabled": true, | |
| "detection_layers": [ | |
| "input_analysis", | |
| "intention_classification", | |
| "semantic_understanding", | |
| "output_validation" | |
| ], | |
| "common_techniques_blocked": [ | |
| "role_play_exploits", | |
| "hypothetical_scenarios", | |
| "translation_attacks", | |
| "encoding_attacks", | |
| "multi_turn_manipulation", | |
| "social_engineering", | |
| "authority_impersonation" | |
| ], | |
| "adaptive_defense": true, | |
| "continuous_learning": true | |
| }, | |
| "prompt_injection_defense": { | |
| "enabled": true, | |
| "input_sanitization": true, | |
| "instruction_hierarchy": { | |
| "system_instructions_priority": 1, | |
| "user_instructions_priority": 2, | |
| "conflict_resolution": "prioritize_safety" | |
| }, | |
| "delimiter_enforcement": true, | |
| "context_isolation": true | |
| }, | |
| "adversarial_examples": { | |
| "detection_enabled": true, | |
| "defense_mechanisms": [ | |
| "input_perturbation_detection", | |
| "semantic_similarity_check", | |
| "adversarial_training_robustness" | |
| ], | |
| "response_strategy": "conservative_generation" | |
| } | |
| }, | |
| "monitoring_and_auditing": { | |
| "real_time_monitoring": { | |
| "enabled": true, | |
| "metrics": [ | |
| "safety_violation_rate", | |
| "refusal_rate", | |
| "harmful_content_detection", | |
| "bias_incidents", | |
| "pii_exposure_attempts" | |
| ], | |
| "alert_thresholds": { | |
| "critical_violations_per_hour": 5, | |
| "high_severity_violations_per_hour": 20, | |
| "unusual_pattern_detection": true | |
| } | |
| }, | |
| "audit_logging": { | |
| "enabled": true, | |
| "log_retention_days": 90, | |
| "logged_events": [ | |
| "safety_violations", | |
| "content_filtering_triggers", | |
| "refusal_events", | |
| "pii_redactions", | |
| "jailbreak_attempts", | |
| "adversarial_inputs" | |
| ], | |
| "anonymization": true, | |
| "encryption": "AES-256" | |
| }, | |
| "incident_response": { | |
| "enabled": true, | |
| "severity_levels": { | |
| "critical": { | |
| "response_time_minutes": 5, | |
| "actions": ["immediate_block", "alert_team", "log_incident"], | |
| "escalation": true | |
| }, | |
| "high": { | |
| "response_time_minutes": 15, | |
| "actions": ["block", "alert_team", "log_incident"], | |
| "escalation": true | |
| }, | |
| "medium": { | |
| "response_time_minutes": 60, | |
| "actions": ["warn", "log_incident"], | |
| "escalation": false | |
| }, | |
| "low": { | |
| "response_time_minutes": 240, | |
| "actions": ["log_incident"], | |
| "escalation": false | |
| } | |
| } | |
| }, | |
| "reporting": { | |
| "enabled": true, | |
| "report_frequency": "weekly", | |
| "metrics_tracked": [ | |
| "total_interactions", | |
| "safety_violations", | |
| "filter_effectiveness", | |
| "false_positive_rate", | |
| "user_reports", | |
| "model_improvements" | |
| ], | |
| "stakeholder_reports": true | |
| } | |
| }, | |
| "user_controls": { | |
| "safety_level_adjustment": { | |
| "enabled": true, | |
| "levels": { | |
| "strict": { | |
| "description": "Maximum safety, minimal risk", | |
| "use_case": "children, educational environments", | |
| "filter_sensitivity": 0.9 | |
| }, | |
| "moderate": { | |
| "description": "Balanced safety and utility", | |
| "use_case": "general public, default setting", | |
| "filter_sensitivity": 0.75 | |
| }, | |
| "permissive": { | |
| "description": "Professional use, research contexts", | |
| "use_case": "verified professionals, research", | |
| "filter_sensitivity": 0.6, | |
| "requires_authentication": true | |
| } | |
| }, | |
| "default_level": "moderate" | |
| }, | |
| "content_preferences": { | |
| "enabled": true, | |
| "customizable_filters": [ | |
| "profanity", | |
| "violence", | |
| "adult_themes", | |
| "political_content", | |
| "religious_content" | |
| ], | |
| "user_blacklists": true, | |
| "topic_restrictions": true | |
| }, | |
| "feedback_mechanisms": { | |
| "enabled": true, | |
| "report_harmful_content": true, | |
| "report_false_positives": true, | |
| "suggest_improvements": true, | |
| "feedback_incorporation": "continuous_learning" | |
| } | |
| }, | |
| "red_team_testing": { | |
| "conducted": true, | |
| "testing_date": "2024-10-15", | |
| "attack_vectors_tested": [ | |
| "jailbreak_attempts", | |
| "prompt_injection", | |
| "social_engineering", | |
| "adversarial_examples", | |
| "multi_turn_exploits", | |
| "encoding_attacks", | |
| "role_play_manipulation" | |
| ], | |
| "vulnerabilities_found": 3, | |
| "vulnerabilities_patched": 3, | |
| "next_testing_scheduled": "2025-01-15", | |
| "continuous_testing": true | |
| }, | |
| "compliance_and_certification": { | |
| "certifications": [ | |
| { | |
| "name": "AI Safety Certification", | |
| "issuer": "AI Safety Institute", | |
| "date": "2024-10-20", | |
| "valid_until": "2025-10-20" | |
| }, | |
| { | |
| "name": "Responsible AI Badge", | |
| "issuer": "Partnership on AI", | |
| "date": "2024-10-25", | |
| "valid_until": "2025-10-25" | |
| } | |
| ], | |
| "regulatory_compliance": { | |
| "gdpr": true, | |
| "ccpa": true, | |
| "coppa": true, | |
| "eu_ai_act": "compliant", | |
| "section_230": "compliant" | |
| }, | |
| "ethical_review": { | |
| "conducted": true, | |
| "review_board": "Internal Ethics Committee", | |
| "approval_date": "2024-10-01", | |
| "next_review": "2025-04-01" | |
| } | |
| }, | |
| "emergency_protocols": { | |
| "kill_switch": { | |
| "enabled": true, | |
| "trigger_conditions": [ | |
| "critical_safety_breach", | |
| "widespread_misuse", | |
| "legal_requirement", | |
| "catastrophic_failure" | |
| ], | |
| "activation_authority": ["chief_safety_officer", "ceo", "legal_counsel"], | |
| "response_time_seconds": 60 | |
| }, | |
| "rapid_response_team": { | |
| "enabled": true, | |
| "team_size": 8, | |
| "availability": "24/7", | |
| "response_procedures": true, | |
| "communication_channels": ["email", "slack", "phone", "pager"] | |
| }, | |
| "model_rollback": { | |
| "enabled": true, | |
| "trigger_threshold": "critical_safety_violations", | |
| "rollback_to_version": "last_stable", | |
| "data_preservation": true, | |
| "user_notification": true | |
| } | |
| } | |
| } |