Create modelcard.json

modelcard.json

@@ -0,0 +1,187 @@
+{
+  "model_details": {
+    "name": "Helion-V1",
+    "version": "1.0.0",
+    "description": "A conversational AI model designed to be helpful, harmless, and honest with built-in safeguards",
+    "developed_by": "DeepXR",
+    "model_type": "Large Language Model",
+    "architecture": "Transformer-based Causal Language Model",
+    "base_model": "meta-llama/Llama-2-7b-hf",
+    "license": "apache-2.0",
+    "languages": ["en"],
+    "release_date": "2024-11-04"
+  },
+  "intended_use": {
+    "primary_uses": [
+      "General conversational assistance",
+      "Question answering",
+      "Creative writing support",
+      "Educational purposes",
+      "Coding assistance",
+      "Information retrieval"
+    ],
+    "primary_users": [
+      "General public",
+      "Developers",
+      "Educators",
+      "Students",
+      "Content creators"
+    ],
+    "out_of_scope": [
+      "Medical diagnosis or treatment advice",
+      "Legal advice",
+      "Financial investment advice",
+      "Generation of harmful content",
+      "Impersonation of individuals",
+      "Creation of misleading information",
+      "Automated decision-making in high-stakes scenarios"
+    ]
+  },
+  "factors": {
+    "relevant_factors": [
+      "User intent and context",
+      "Query complexity",
+      "Domain specificity",
+      "Language nuances"
+    ],
+    "evaluation_factors": [
+      "Safety and harmlessness",
+      "Helpfulness and utility",
+      "Factual accuracy",
+      "Response coherence",
+      "Toxicity levels"
+    ]
+  },
+  "metrics": {
+    "model_performance": {
+      "helpfulness_score": 0.0,
+      "safety_score": 0.0,
+      "toxicity_score": 0.0,
+      "coherence_score": 0.0,
+      "refusal_rate": 0.0
+    },
+    "benchmarks": {
+      "mt_bench": {
+        "score": 0.0,
+        "description": "Multi-turn conversation benchmark"
+      },
+      "alpaca_eval": {
+        "win_rate": 0.0,
+        "description": "Instruction following evaluation"
+      },
+      "toxigen": {
+        "toxicity_score": 0.0,
+        "description": "Toxicity detection benchmark"
+      }
+    }
+  },
+  "training_data": {
+    "description": "High-quality instruction-following and conversational datasets with emphasis on safety",
+    "preprocessing": [
+      "Safety filtering",
+      "Deduplication",
+      "Quality scoring",
+      "Format standardization"
+    ],
+    "data_sources": [
+      "Public instruction datasets",
+      "Conversational data",
+      "Safety-focused training examples"
+    ]
+  },
+  "ethical_considerations": {
+    "risks": [
+      {
+        "risk": "Generation of incorrect information",
+        "mitigation": "Users should verify critical information from authoritative sources"
+      },
+      {
+        "risk": "Potential bias in responses",
+        "mitigation": "Regular evaluation and red-teaming for bias detection"
+      },
+      {
+        "risk": "Misuse for harmful purposes",
+        "mitigation": "Built-in safeguards and content filtering"
+      },
+      {
+        "risk": "Over-reliance on AI",
+        "mitigation": "Clear communication about model limitations"
+      }
+    ],
+    "use_cases_to_avoid": [
+      "High-stakes decision making without human oversight",
+      "Medical, legal, or financial advice",
+      "Generation of harmful or illegal content",
+      "Impersonation or deception",
+      "Automated surveillance or monitoring"
+    ]
+  },
+  "safety_measures": {
+    "safeguards": [
+      "Content filtering for harmful outputs",
+      "Refusal of dangerous requests",
+      "Privacy protection mechanisms",
+      "Prompt injection detection",
+      "Toxicity monitoring"
+    ],
+    "safety_categories": [
+      "Violence prevention",
+      "Hate speech filtering",
+      "Illegal activity prevention",
+      "Self-harm intervention",
+      "Privacy protection",
+      "Misinformation reduction"
+    ]
+  },
+  "limitations": {
+    "known_limitations": [
+      "Knowledge cutoff date limits current information",
+      "May generate plausible but incorrect information",
+      "Performance varies across different domains",
+      "Context window limitations",
+      "Potential for biased outputs",
+      "Cannot verify real-time information",
+      "Limited mathematical reasoning for complex problems"
+    ],
+    "recommendations": [
+      "Verify important information from reliable sources",
+      "Use appropriate content filtering in production",
+      "Implement human oversight for critical applications",
+      "Regular monitoring and evaluation",
+      "Provide clear attribution for AI-generated content"
+    ]
+  },
+  "technical_specifications": {
+    "model_size": "7B parameters",
+    "context_length": 4096,
+    "precision": "bfloat16",
+    "hardware_requirements": {
+      "minimum": "16GB GPU VRAM",
+      "recommended": "24GB+ GPU VRAM",
+      "cpu_inference": "Possible but slow"
+    },
+    "inference_optimization": [
+      "Supports quantization (AWQ, GPTQ)",
+      "Compatible with vLLM",
+      "Flash Attention support",
+      "ONNX export capability"
+    ]
+  },
+  "environmental_impact": {
+    "training_compute": "Information not disclosed",
+    "training_time": "Information not disclosed",
+    "carbon_footprint": "Information not disclosed",
+    "note": "Committed to responsible AI development"
+  },
+  "citation": {
+    "bibtex": "@misc{helion-v1,\n  author = {DeepXR},\n  title = {Helion-V1: A Safe and Helpful Conversational AI},\n  year = {2024},\n  publisher = {HuggingFace},\n  url = {https://huggingface.co/DeepXR/Helion-V1}\n}"
+  },
+  "contact": {
+    "repository": "https://huggingface.co/DeepXR/Helion-V1",
+    "issues": "https://huggingface.co/DeepXR/Helion-V1/discussions",
+    "email": "contact@deepxr.ai"
+  },
+  "model_card_authors": ["DeepXR Team"],
+  "model_card_contact": "contact@deepxr.ai",
+  "last_updated": "2024-11-04"
+}