config.json

{
  "architectures": [
    "Qwen2ForCausalLM"
  ],
  "attention_dropout": 0.0,
  "dtype": "bfloat16",
  "eos_token_id": 151643,
  "hidden_act": "silu",
  "hidden_size": 2048,
  "initializer_range": 0.02,
  "intermediate_size": 11008,
  "layer_types": [
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention"
  ],
  "max_position_embeddings": 32768,
  "max_window_layers": 36,
  "model_type": "qwen2",
  "num_attention_heads": 16,
  "num_hidden_layers": 36,
  "num_key_value_heads": 2,
  "pad_token_id": 151654,
  "quantization_config": {
    "bnb_4bit_compute_dtype": "bfloat16",
    "bnb_4bit_quant_type": "nf4",
    "bnb_4bit_use_double_quant": true,
    "llm_int8_enable_fp32_cpu_offload": false,
    "llm_int8_has_fp16_weight": false,
    "llm_int8_skip_modules": [
      "model.layers.1.mlp.gate_proj",
      "model.layers.1.mlp.up_proj",
      "model.layers.1.mlp.down_proj",
      "model.layers.2.mlp.gate_proj",
      "model.layers.2.mlp.up_proj",
      "model.layers.2.mlp.down_proj",
      "model.layers.3.mlp.gate_proj",
      "model.layers.3.mlp.up_proj",
      "model.layers.3.mlp.down_proj",
      "model.layers.28.mlp.gate_proj",
      "model.layers.28.mlp.up_proj",
      "model.layers.28.mlp.down_proj",
      "model.layers.30.mlp.gate_proj",
      "model.layers.30.mlp.up_proj",
      "model.layers.30.mlp.down_proj",
      "lm_head"
    ],
    "llm_int8_threshold": 6.0,
    "load_in_4bit": true,
    "load_in_8bit": false,
    "quant_method": "bitsandbytes"
  },
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 1000000.0,
  "sliding_window": null,
  "tie_word_embeddings": true,
  "transformers_version": "4.56.0",
  "unsloth_fixed": true,
  "unsloth_version": "2025.9.2",
  "use_cache": true,
  "use_mrope": false,
  "use_sliding_window": false,
  "vocab_size": 151936
}