config.json

{
  "architectures": [
    "Qwen2ForCausalLM"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 151643,
  "eos_token_id": 151645,
  "hidden_act": "silu",
  "hidden_size": 1536,
  "initializer_range": 0.02,
  "intermediate_size": 8960,
  "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"
  ],
  "max_position_embeddings": 32768,
  "max_window_layers": 21,
  "model_type": "qwen2",
  "num_attention_heads": 12,
  "num_hidden_layers": 28,
  "num_key_value_heads": 2,
  "quantization_config": {
    "algo_config": [],
    "exclude": [
      "lm_head"
    ],
    "export": {
      "kv_cache_group": [],
      "min_kv_scale": 0.0,
      "pack_method": "reorder",
      "weight_format": "real_quantized",
      "weight_merge_groups": null
    },
    "global_quant_config": {
      "bias": null,
      "input_tensors": {
        "ch_axis": 1,
        "dtype": "fp8_e4m3",
        "group_size": null,
        "is_dynamic": true,
        "is_scale_quant": false,
        "mx_element_dtype": null,
        "observer_cls": "PerChannelMinMaxObserver",
        "qscheme": "per_channel",
        "round_method": null,
        "scale_calculation_mode": null,
        "scale_format": null,
        "scale_type": null,
        "symmetric": null
      },
      "output_tensors": null,
      "target_device": null,
      "weight": {
        "ch_axis": 0,
        "dtype": "fp8_e4m3",
        "group_size": null,
        "is_dynamic": false,
        "is_scale_quant": false,
        "mx_element_dtype": null,
        "observer_cls": "PerChannelMinMaxObserver",
        "qscheme": "per_channel",
        "round_method": null,
        "scale_calculation_mode": null,
        "scale_format": null,
        "scale_type": null,
        "symmetric": null
      }
    },
    "kv_cache_quant_config": {},
    "layer_quant_config": {},
    "layer_type_quant_config": {},
    "quant_method": "quark",
    "quant_mode": "eager_mode",
    "softmax_quant_spec": null,
    "version": "0.10+cdd93fc33d"
  },
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 1000000.0,
  "sliding_window": null,
  "tie_word_embeddings": true,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.55.0",
  "use_cache": true,
  "use_sliding_window": false,
  "vocab_size": 151936
}