{
  "_name_or_path": "NER-Small",
  "architectures": ["LlamaForCausalLM"],
  "vocab_size": 49152,
  "context_length": 2048,
  "hidden_size": 576,
  "num_attention_heads": 9,
  "num_hidden_layers": 30,
  "intermediate_size": 1536,
  "quantization_config": {
    "quant_method": "gguf",
    "quantization_type": "Q8_0",
    "quantization_bits": 8,
    "compression_ratio": 0.5,
    "quantization_version": "2",
    "quantization_fidelity": "high",
    "quantization_format": "GGUF",
    "quantization_description": "8-bit quantization with optimized weights for high fidelity"
  },
  "file_size": 143025408,
  "file_size_mb": 143,
  "gguf_file": "model.gguf",
  "model_family": "llama",
  "model_version": "1.0.0",
  "hardware_requirements": {
    "minimum_ram": "8GB",
    "recommended_ram": "16GB",
    "cpu_compatibility": "Any modern CPU",
    "gpu_compatibility": {
      "nvidia": "Any CUDA-compatible GPU",
      "amd": "Any ROCm-compatible GPU",
      "apple_silicon": "M1/M2/M3/M4 chips with Metal"
    },
    "os_compatibility": ["linux", "macos", "windows"],
    "recommended_hardware": "Apple Silicon M2/M3/M4, Intel i7/i9, or NVIDIA RTX 30-series",
    "memory_usage_estimate": "~2GB during inference",
    "storage_requirements": "150MB free space"
  },
  "performance_metrics": {
    "ner_f1_score": 0.850,
    "entity_recognition_accuracy": 0.920,
    "entity_types_supported": ["PERSON", "ORG", "LOC", "MISC"],
    "latency_ms": 350.0,
    "throughput_requests_per_second": 2.8,
    "benchmark_dataset": "CoNLL-2003 NER Dataset",
    "benchmark_samples": 100,
    "evaluation_date": "2025-10-07"
  },
  "model_creator": "Minibase AI",
  "model_url": "https://minibase.ai",
  "discord_url": "https://discord.com/invite/BrJn4D2Guh",
  "repository_url": "https://github.com/minibase-ai/ner-small",
  "paper_url": "https://minibase.ai/research/ner-small",
  "license": "apache-2.0",
  "tags": [
    "text-generation",
    "named-entity-recognition",
    "ner",
    "nlp",
    "information-extraction",
    "person",
    "organization",
    "location",
    "miscellaneous",
    "llama",
    "gguf",
    "quantized",
    "cpu-inference",
    "apple-silicon",
    "minibase",
    "small-model",
    "2048-context",
    "q8_0"
  ]
}