{
  "architectures": [
    "MobilintLlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "auto_map": {
    "AutoConfig": "proxy_llama.MobilintLlamaConfig",
    "AutoModelForCausalLM": "proxy_llama.MobilintLlamaForCausalLM"
  },
  "bos_token_id": 128000,
  "dev_no": 0,
  "eos_token_id": [
    128001,
    128008,
    128009
  ],
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 3072,
  "initializer_range": 0.02,
  "intermediate_size": 8192,
  "max_position_embeddings": 4096,
  "mlp_bias": false,
  "model_type": "mobilint-llama",
  "mxq_path": "Llama-3.2-3B-Instruct-Batch16-W4V8.mxq",
  "num_attention_heads": 24,
  "num_hidden_layers": 28,
  "num_key_value_heads": 8,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_scaling": {
    "factor": 32.0,
    "high_freq_factor": 4.0,
    "low_freq_factor": 1.0,
    "original_max_position_embeddings": 2048,
    "rope_type": "llama3"
  },
  "rope_theta": 500000.0,
  "target_cores": [
    "0:0",
    "0:1",
    "0:2",
    "0:3",
    "1:0",
    "1:1",
    "1:2",
    "1:3"
  ],
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.45.0.dev0",
  "use_cache": true,
  "vocab_size": 128256,
  "npu_prefill_chunk_size": {
    "single": 128
  },
  "max_batch_size": 16
}