config.json

{
  "architectures": [
    "Qwen3ForCausalLM"
  ],
  "hidden_size": 32,
  "intermediate_size": 64,
  "num_attention_heads": 4,
  "num_hidden_layers": 2,
  "num_key_value_heads": 2,
  "vocab_size": 1024,
  "head_dim": 8,
  "rms_norm_eps": 1e-06,
  "rope_theta": 1000000.0,
  "max_position_embeddings": 512,
  "torch_dtype": "float8_e4m3fn",
  "model_type": "qwen3",
  "use_qk_norm": true,
  "tie_word_embeddings": true,
  "quantization_config": {
    "quant_method": "fp8",
    "weight_block_size": [
      128,
      128
    ]
  }
}