config.json

{
  "architectures": [
    "Qwen3ForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 151643,
  "eos_token_id": 151645,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 2560,
  "initializer_range": 0.02,
  "intermediate_size": 9728,
  "max_position_embeddings": 262144,
  "max_window_layers": 36,
  "model_type": "qwen3",
  "num_attention_heads": 32,
  "num_hidden_layers": 36,
  "num_key_value_heads": 8,
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 5000000,
  "sliding_window": null,
  "tie_word_embeddings": true,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.51.0",
  "use_cache": true,
  "use_sliding_window": false,
  "vocab_size": 151936,
  "quantization_config": {
    "activation_scheme": "dynamic",
    "modules_to_not_convert": [
      "lm_head",
      "model.layers.0.input_layernorm",
      "model.layers.0.post_attention_layernorm",
      "model.layers.1.input_layernorm",
      "model.layers.1.post_attention_layernorm",
      "model.layers.2.input_layernorm",
      "model.layers.2.post_attention_layernorm",
      "model.layers.3.input_layernorm",
      "model.layers.3.post_attention_layernorm",
      "model.layers.4.input_layernorm",
      "model.layers.4.post_attention_layernorm",
      "model.layers.5.input_layernorm",
      "model.layers.5.post_attention_layernorm",
      "model.layers.6.input_layernorm",
      "model.layers.6.post_attention_layernorm",
      "model.layers.7.input_layernorm",
      "model.layers.7.post_attention_layernorm",
      "model.layers.8.input_layernorm",
      "model.layers.8.post_attention_layernorm",
      "model.layers.9.input_layernorm",
      "model.layers.9.post_attention_layernorm",
      "model.layers.10.input_layernorm",
      "model.layers.10.post_attention_layernorm",
      "model.layers.11.input_layernorm",
      "model.layers.11.post_attention_layernorm",
      "model.layers.12.input_layernorm",
      "model.layers.12.post_attention_layernorm",
      "model.layers.13.input_layernorm",
      "model.layers.13.post_attention_layernorm",
      "model.layers.14.input_layernorm",
      "model.layers.14.post_attention_layernorm",
      "model.layers.15.input_layernorm",
      "model.layers.15.post_attention_layernorm",
      "model.layers.16.input_layernorm",
      "model.layers.16.post_attention_layernorm",
      "model.layers.17.input_layernorm",
      "model.layers.17.post_attention_layernorm",
      "model.layers.18.input_layernorm",
      "model.layers.18.post_attention_layernorm",
      "model.layers.19.input_layernorm",
      "model.layers.19.post_attention_layernorm",
      "model.layers.20.input_layernorm",
      "model.layers.20.post_attention_layernorm",
      "model.layers.21.input_layernorm",
      "model.layers.21.post_attention_layernorm",
      "model.layers.22.input_layernorm",
      "model.layers.22.post_attention_layernorm",
      "model.layers.23.input_layernorm",
      "model.layers.23.post_attention_layernorm",
      "model.layers.24.input_layernorm",
      "model.layers.24.post_attention_layernorm",
      "model.layers.25.input_layernorm",
      "model.layers.25.post_attention_layernorm",
      "model.layers.26.input_layernorm",
      "model.layers.26.post_attention_layernorm",
      "model.layers.27.input_layernorm",
      "model.layers.27.post_attention_layernorm",
      "model.layers.28.input_layernorm",
      "model.layers.28.post_attention_layernorm",
      "model.layers.29.input_layernorm",
      "model.layers.29.post_attention_layernorm",
      "model.layers.30.input_layernorm",
      "model.layers.30.post_attention_layernorm",
      "model.layers.31.input_layernorm",
      "model.layers.31.post_attention_layernorm",
      "model.layers.32.input_layernorm",
      "model.layers.32.post_attention_layernorm",
      "model.layers.33.input_layernorm",
      "model.layers.33.post_attention_layernorm",
      "model.layers.34.input_layernorm",
      "model.layers.34.post_attention_layernorm",
      "model.layers.35.input_layernorm",
      "model.layers.35.post_attention_layernorm"
    ],    
    "fmt": "e4m3",
    "quant_method": "fp8",
    "weight_block_size": [
      128,
      128
    ]
  }
}