{
  "architectures": [
    "Qwen3ForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "dtype": "float32",
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 64,
  "initializer_range": 0.02,
  "intermediate_size": 128,
  "layer_types": [
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention"
  ],
  "max_position_embeddings": 32768,
  "max_window_layers": 28,
  "model_type": "qwen3",
  "num_attention_heads": 16,
  "num_hidden_layers": 6,
  "num_key_value_heads": 8,
  "quantization_config": {
    "config_groups": {},
    "format": "dense",
    "global_compression_ratio": null,
    "ignore": [],
    "kv_cache_scheme": {
      "dynamic": false,
      "group_size": null,
      "num_bits": 8,
      "strategy": "tensor",
      "symmetric": true,
      "type": "float"
    },
    "moe_sparsity_config": null,
    "quant_method": "compressed-tensors",
    "quantization_status": "compressed",
    "sparsity_config": {},
    "transform_config": {},
    "version": "0.19.1.dev22+g3cb3ca29.d20261014"
  },
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 10000.0,
  "sliding_window": null,
  "tie_word_embeddings": false,
  "transformers_version": "4.57.6",
  "use_cache": true,
  "use_sliding_window": false,
  "vocab_size": 1050
}