model_info.json

{
  "model_name": "wraith-coder-7b",
  "base_model": "Qwen/Qwen2.5-Coder-7B-Instruct",
  "version": "1.0.0",
  "release_date": "2025-11-19",
  
  "architecture": {
    "type": "CausalLM",
    "parameters": "7.6B",
    "layers": 28,
    "hidden_size": 3584,
    "attention_heads": 28,
    "kv_heads": 4,
    "context_length": 32768,
    "vocab_size": 152064
  },
  
  "training": {
    "method": "LoRA Fine-tuning",
    "iterations": 3,
    "total_examples": 14244,
    "lora_rank": 16,
    "lora_alpha": 32,
    "learning_rate": 5e-5,
    "epochs_per_iteration": 2,
    "optimizer": "adamw_8bit"
  },
  
  "performance": {
    "conciseness_improvement": "62.6%",
    "complexity_analysis_coverage": "60%",
    "base_model_complexity_coverage": "40%",
    "evaluation_questions": 20,
    "correctness_rate": "100%"
  },
  
  "recommended_parameters": {
    "temperature": 0.7,
    "top_p": 0.9,
    "top_k": 40,
    "repeat_penalty": 1.1,
    "max_tokens": 2048
  },
  
  "quantization": {
    "supported_formats": ["fp16", "q8_0", "q4_k_m", "q4_0"],
    "recommended": "q4_k_m",
    "model_size_q4_k_m": "4.4GB"
  },
  
  "license": "Apache-2.0",
  "languages": ["en"],
  "tags": [
    "code-generation",
    "algorithms",
    "systems-programming",
    "complexity-analysis",
    "qwen2.5",
    "fine-tuned"
  ]
}