config.json

{
  "architectures": [
    "NeuralQuantumOllama"
  ],
  "auto_map": {
    "AutoModel": "modeling_ollama.NeuralQuantumOllamaForCausalLM",
    "AutoConfig": "configuration_ollama.NeuralQuantumOllamaConfig"
  },
  "model_type": "neuralquantum_ollama",
  "vocab_size": 50257,
  "hidden_size": 768,
  "num_attention_heads": 12,
  "num_hidden_layers": 12,
  "intermediate_size": 3072,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "attention_probs_dropout_prob": 0.1,
  "max_position_embeddings": 2048,
  "type_vocab_size": 2,
  "initializer_range": 0.02,
  "layer_norm_eps": 1e-12,
  "use_cache": true,
  "quantum_enhancement": true,
  "quantum_layers": 6,
  "quantum_circuit_depth": 12,
  "quantum_optimization": "vqe",
  "hybrid_mode": true,
  "ollama_optimized": true,
  "temperature": 0.7,
  "top_p": 0.9,
  "top_k": 40,
  "repeat_penalty": 1.1,
  "num_ctx": 2048,
  "num_predict": 512,
  "torch_dtype": "float16"
}